gsd-trae 1.0.0 → 1.0.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +40 -0
- package/README.md +7 -76
- package/assets/screenshot.png +0 -0
- package/package.json +12 -3
- package/.claude/settings.local.json +0 -8
- package/.gitmodules +0 -6
- package/.trae/project_rules.md +0 -56
- package/.trae/rules/project_rules.md +0 -56
- package/.vscode/code-counter/code-counter.db +0 -0
- package/.vscode/settings.json +0 -5
- package/refs/gsd/.github/CODEOWNERS +0 -2
- package/refs/gsd/.github/FUNDING.yml +0 -1
- package/refs/gsd/.github/ISSUE_TEMPLATE/bug_report.yml +0 -59
- package/refs/gsd/.github/ISSUE_TEMPLATE/feature_request.yml +0 -37
- package/refs/gsd/.github/pull_request_template.md +0 -24
- package/refs/gsd/.github/workflows/auto-label-issues.yml +0 -21
- package/refs/gsd/CHANGELOG.md +0 -1520
- package/refs/gsd/LICENSE +0 -21
- package/refs/gsd/README.md +0 -704
- package/refs/gsd/SECURITY.md +0 -33
- package/refs/gsd/agents/gsd-codebase-mapper.md +0 -764
- package/refs/gsd/agents/gsd-debugger.md +0 -1246
- package/refs/gsd/agents/gsd-executor.md +0 -469
- package/refs/gsd/agents/gsd-integration-checker.md +0 -443
- package/refs/gsd/agents/gsd-phase-researcher.md +0 -546
- package/refs/gsd/agents/gsd-plan-checker.md +0 -690
- package/refs/gsd/agents/gsd-planner.md +0 -1275
- package/refs/gsd/agents/gsd-project-researcher.md +0 -621
- package/refs/gsd/agents/gsd-research-synthesizer.md +0 -239
- package/refs/gsd/agents/gsd-roadmapper.md +0 -642
- package/refs/gsd/agents/gsd-verifier.md +0 -573
- package/refs/gsd/assets/gsd-logo-2000-transparent.png +0 -0
- package/refs/gsd/assets/gsd-logo-2000-transparent.svg +0 -17
- package/refs/gsd/assets/gsd-logo-2000.png +0 -0
- package/refs/gsd/assets/gsd-logo-2000.svg +0 -21
- package/refs/gsd/assets/terminal.svg +0 -68
- package/refs/gsd/bin/install.js +0 -2090
- package/refs/gsd/commands/gsd/add-phase.md +0 -43
- package/refs/gsd/commands/gsd/add-tests.md +0 -41
- package/refs/gsd/commands/gsd/add-todo.md +0 -47
- package/refs/gsd/commands/gsd/audit-milestone.md +0 -36
- package/refs/gsd/commands/gsd/check-todos.md +0 -45
- package/refs/gsd/commands/gsd/cleanup.md +0 -18
- package/refs/gsd/commands/gsd/complete-milestone.md +0 -136
- package/refs/gsd/commands/gsd/debug.md +0 -167
- package/refs/gsd/commands/gsd/discuss-phase.md +0 -83
- package/refs/gsd/commands/gsd/execute-phase.md +0 -41
- package/refs/gsd/commands/gsd/health.md +0 -22
- package/refs/gsd/commands/gsd/help.md +0 -22
- package/refs/gsd/commands/gsd/insert-phase.md +0 -32
- package/refs/gsd/commands/gsd/join-discord.md +0 -18
- package/refs/gsd/commands/gsd/list-phase-assumptions.md +0 -46
- package/refs/gsd/commands/gsd/map-codebase.md +0 -71
- package/refs/gsd/commands/gsd/new-milestone.md +0 -44
- package/refs/gsd/commands/gsd/new-project.md +0 -42
- package/refs/gsd/commands/gsd/new-project.md.bak +0 -1041
- package/refs/gsd/commands/gsd/pause-work.md +0 -38
- package/refs/gsd/commands/gsd/plan-milestone-gaps.md +0 -34
- package/refs/gsd/commands/gsd/plan-phase.md +0 -45
- package/refs/gsd/commands/gsd/progress.md +0 -24
- package/refs/gsd/commands/gsd/quick.md +0 -41
- package/refs/gsd/commands/gsd/reapply-patches.md +0 -110
- package/refs/gsd/commands/gsd/remove-phase.md +0 -31
- package/refs/gsd/commands/gsd/research-phase.md +0 -189
- package/refs/gsd/commands/gsd/resume-work.md +0 -40
- package/refs/gsd/commands/gsd/set-profile.md +0 -34
- package/refs/gsd/commands/gsd/settings.md +0 -36
- package/refs/gsd/commands/gsd/update.md +0 -37
- package/refs/gsd/commands/gsd/verify-work.md +0 -38
- package/refs/gsd/docs/USER-GUIDE.md +0 -471
- package/refs/gsd/docs/context-monitor.md +0 -96
- package/refs/gsd/get-shit-done/bin/gsd-tools.cjs +0 -585
- package/refs/gsd/get-shit-done/bin/lib/commands.cjs +0 -553
- package/refs/gsd/get-shit-done/bin/lib/config.cjs +0 -162
- package/refs/gsd/get-shit-done/bin/lib/core.cjs +0 -411
- package/refs/gsd/get-shit-done/bin/lib/frontmatter.cjs +0 -299
- package/refs/gsd/get-shit-done/bin/lib/init.cjs +0 -710
- package/refs/gsd/get-shit-done/bin/lib/milestone.cjs +0 -215
- package/refs/gsd/get-shit-done/bin/lib/phase.cjs +0 -870
- package/refs/gsd/get-shit-done/bin/lib/roadmap.cjs +0 -298
- package/refs/gsd/get-shit-done/bin/lib/state.cjs +0 -521
- package/refs/gsd/get-shit-done/bin/lib/template.cjs +0 -222
- package/refs/gsd/get-shit-done/bin/lib/verify.cjs +0 -772
- package/refs/gsd/get-shit-done/references/checkpoints.md +0 -776
- package/refs/gsd/get-shit-done/references/continuation-format.md +0 -249
- package/refs/gsd/get-shit-done/references/decimal-phase-calculation.md +0 -65
- package/refs/gsd/get-shit-done/references/git-integration.md +0 -248
- package/refs/gsd/get-shit-done/references/git-planning-commit.md +0 -38
- package/refs/gsd/get-shit-done/references/model-profile-resolution.md +0 -34
- package/refs/gsd/get-shit-done/references/model-profiles.md +0 -92
- package/refs/gsd/get-shit-done/references/phase-argument-parsing.md +0 -61
- package/refs/gsd/get-shit-done/references/planning-config.md +0 -196
- package/refs/gsd/get-shit-done/references/questioning.md +0 -145
- package/refs/gsd/get-shit-done/references/tdd.md +0 -263
- package/refs/gsd/get-shit-done/references/ui-brand.md +0 -160
- package/refs/gsd/get-shit-done/references/verification-patterns.md +0 -612
- package/refs/gsd/get-shit-done/templates/DEBUG.md +0 -164
- package/refs/gsd/get-shit-done/templates/UAT.md +0 -247
- package/refs/gsd/get-shit-done/templates/VALIDATION.md +0 -76
- package/refs/gsd/get-shit-done/templates/codebase/architecture.md +0 -255
- package/refs/gsd/get-shit-done/templates/codebase/concerns.md +0 -310
- package/refs/gsd/get-shit-done/templates/codebase/conventions.md +0 -307
- package/refs/gsd/get-shit-done/templates/codebase/integrations.md +0 -280
- package/refs/gsd/get-shit-done/templates/codebase/stack.md +0 -186
- package/refs/gsd/get-shit-done/templates/codebase/structure.md +0 -285
- package/refs/gsd/get-shit-done/templates/codebase/testing.md +0 -480
- package/refs/gsd/get-shit-done/templates/config.json +0 -37
- package/refs/gsd/get-shit-done/templates/context.md +0 -283
- package/refs/gsd/get-shit-done/templates/continue-here.md +0 -78
- package/refs/gsd/get-shit-done/templates/debug-subagent-prompt.md +0 -91
- package/refs/gsd/get-shit-done/templates/discovery.md +0 -146
- package/refs/gsd/get-shit-done/templates/milestone-archive.md +0 -123
- package/refs/gsd/get-shit-done/templates/milestone.md +0 -115
- package/refs/gsd/get-shit-done/templates/phase-prompt.md +0 -569
- package/refs/gsd/get-shit-done/templates/planner-subagent-prompt.md +0 -117
- package/refs/gsd/get-shit-done/templates/project.md +0 -184
- package/refs/gsd/get-shit-done/templates/requirements.md +0 -231
- package/refs/gsd/get-shit-done/templates/research-project/ARCHITECTURE.md +0 -204
- package/refs/gsd/get-shit-done/templates/research-project/FEATURES.md +0 -147
- package/refs/gsd/get-shit-done/templates/research-project/PITFALLS.md +0 -200
- package/refs/gsd/get-shit-done/templates/research-project/STACK.md +0 -120
- package/refs/gsd/get-shit-done/templates/research-project/SUMMARY.md +0 -170
- package/refs/gsd/get-shit-done/templates/research.md +0 -552
- package/refs/gsd/get-shit-done/templates/retrospective.md +0 -54
- package/refs/gsd/get-shit-done/templates/roadmap.md +0 -202
- package/refs/gsd/get-shit-done/templates/state.md +0 -176
- package/refs/gsd/get-shit-done/templates/summary-complex.md +0 -59
- package/refs/gsd/get-shit-done/templates/summary-minimal.md +0 -41
- package/refs/gsd/get-shit-done/templates/summary-standard.md +0 -48
- package/refs/gsd/get-shit-done/templates/summary.md +0 -248
- package/refs/gsd/get-shit-done/templates/user-setup.md +0 -311
- package/refs/gsd/get-shit-done/templates/verification-report.md +0 -322
- package/refs/gsd/get-shit-done/workflows/add-phase.md +0 -111
- package/refs/gsd/get-shit-done/workflows/add-tests.md +0 -350
- package/refs/gsd/get-shit-done/workflows/add-todo.md +0 -157
- package/refs/gsd/get-shit-done/workflows/audit-milestone.md +0 -297
- package/refs/gsd/get-shit-done/workflows/check-todos.md +0 -176
- package/refs/gsd/get-shit-done/workflows/cleanup.md +0 -152
- package/refs/gsd/get-shit-done/workflows/complete-milestone.md +0 -763
- package/refs/gsd/get-shit-done/workflows/diagnose-issues.md +0 -219
- package/refs/gsd/get-shit-done/workflows/discovery-phase.md +0 -289
- package/refs/gsd/get-shit-done/workflows/discuss-phase.md +0 -542
- package/refs/gsd/get-shit-done/workflows/execute-phase.md +0 -449
- package/refs/gsd/get-shit-done/workflows/execute-plan.md +0 -448
- package/refs/gsd/get-shit-done/workflows/health.md +0 -156
- package/refs/gsd/get-shit-done/workflows/help.md +0 -489
- package/refs/gsd/get-shit-done/workflows/insert-phase.md +0 -129
- package/refs/gsd/get-shit-done/workflows/list-phase-assumptions.md +0 -178
- package/refs/gsd/get-shit-done/workflows/map-codebase.md +0 -315
- package/refs/gsd/get-shit-done/workflows/new-milestone.md +0 -382
- package/refs/gsd/get-shit-done/workflows/new-project.md +0 -1116
- package/refs/gsd/get-shit-done/workflows/pause-work.md +0 -122
- package/refs/gsd/get-shit-done/workflows/plan-milestone-gaps.md +0 -274
- package/refs/gsd/get-shit-done/workflows/plan-phase.md +0 -569
- package/refs/gsd/get-shit-done/workflows/progress.md +0 -381
- package/refs/gsd/get-shit-done/workflows/quick.md +0 -453
- package/refs/gsd/get-shit-done/workflows/remove-phase.md +0 -154
- package/refs/gsd/get-shit-done/workflows/research-phase.md +0 -73
- package/refs/gsd/get-shit-done/workflows/resume-project.md +0 -306
- package/refs/gsd/get-shit-done/workflows/set-profile.md +0 -80
- package/refs/gsd/get-shit-done/workflows/settings.md +0 -213
- package/refs/gsd/get-shit-done/workflows/transition.md +0 -544
- package/refs/gsd/get-shit-done/workflows/update.md +0 -219
- package/refs/gsd/get-shit-done/workflows/verify-phase.md +0 -242
- package/refs/gsd/get-shit-done/workflows/verify-work.md +0 -569
- package/refs/gsd/hooks/gsd-check-update.js +0 -62
- package/refs/gsd/hooks/gsd-context-monitor.js +0 -122
- package/refs/gsd/hooks/gsd-statusline.js +0 -108
- package/refs/gsd/package.json +0 -50
- package/refs/gsd/scripts/build-hooks.js +0 -43
- package/refs/gsd/tests/commands.test.cjs +0 -661
- package/refs/gsd/tests/helpers.cjs +0 -40
- package/refs/gsd/tests/init.test.cjs +0 -205
- package/refs/gsd/tests/milestone.test.cjs +0 -98
- package/refs/gsd/tests/phase.test.cjs +0 -1241
- package/refs/gsd/tests/roadmap.test.cjs +0 -265
- package/refs/gsd/tests/state.test.cjs +0 -302
- package/refs/gsd/tests/verify.test.cjs +0 -80
- package/refs/vbenchmark/.agent/agents/codebase-explorer.md +0 -224
- package/refs/vbenchmark/.agent/agents/debugger.md +0 -180
- package/refs/vbenchmark/.agent/agents/documenter.md +0 -166
- package/refs/vbenchmark/.agent/agents/implementer.md +0 -70
- package/refs/vbenchmark/.agent/agents/orchestrator.md +0 -212
- package/refs/vbenchmark/.agent/agents/researcher.md +0 -80
- package/refs/vbenchmark/.agent/agents/reviewer.md +0 -184
- package/refs/vbenchmark/.agent/agents/tester.md +0 -170
- package/refs/vbenchmark/.agent/commands/commit.md +0 -29
- package/refs/vbenchmark/.agent/commands/debug.md +0 -59
- package/refs/vbenchmark/.agent/commands/document.md +0 -52
- package/refs/vbenchmark/.agent/commands/gather-context.md +0 -58
- package/refs/vbenchmark/.agent/commands/init.md +0 -56
- package/refs/vbenchmark/.agent/commands/preset-help.md +0 -50
- package/refs/vbenchmark/.agent/commands/refactor.md +0 -71
- package/refs/vbenchmark/.agent/commands/research.md +0 -37
- package/refs/vbenchmark/.agent/commands/review.md +0 -38
- package/refs/vbenchmark/.agent/commands/test.md +0 -61
- package/refs/vbenchmark/.agent/rules/01-code-quality.md +0 -33
- package/refs/vbenchmark/.agent/rules/02-typescript-go.md +0 -46
- package/refs/vbenchmark/.agent/rules/03-security-git.md +0 -34
- package/refs/vbenchmark/.agent/rules/04-architecture.md +0 -40
- package/refs/vbenchmark/.agent/sync.js +0 -536
- package/refs/vbenchmark/.agent/workflows/commit.md +0 -29
- package/refs/vbenchmark/.agent/workflows/debug.md +0 -59
- package/refs/vbenchmark/.agent/workflows/document.md +0 -52
- package/refs/vbenchmark/.agent/workflows/gather-context.md +0 -58
- package/refs/vbenchmark/.agent/workflows/init.md +0 -56
- package/refs/vbenchmark/.agent/workflows/preset-help.md +0 -50
- package/refs/vbenchmark/.agent/workflows/refactor.md +0 -71
- package/refs/vbenchmark/.agent/workflows/research.md +0 -37
- package/refs/vbenchmark/.agent/workflows/review.md +0 -38
- package/refs/vbenchmark/.agent/workflows/test.md +0 -61
- package/refs/vbenchmark/.claude/commands/agentic-dev/apply.md +0 -222
- package/refs/vbenchmark/.claude/commands/agentic-dev/done.md +0 -166
- package/refs/vbenchmark/.claude/commands/agentic-dev/proposal.md +0 -220
- package/refs/vbenchmark/.claude/commands/openspec/apply.md +0 -23
- package/refs/vbenchmark/.claude/commands/openspec/archive.md +0 -27
- package/refs/vbenchmark/.claude/commands/openspec/proposal.md +0 -28
- package/refs/vbenchmark/.clinerules/01-rules.md +0 -73
- package/refs/vbenchmark/.clinerules/02-agents.md +0 -34
- package/refs/vbenchmark/.cursor/commands/commit.md +0 -29
- package/refs/vbenchmark/.cursor/commands/debug.md +0 -59
- package/refs/vbenchmark/.cursor/commands/document.md +0 -52
- package/refs/vbenchmark/.cursor/commands/gather-context.md +0 -58
- package/refs/vbenchmark/.cursor/commands/init.md +0 -56
- package/refs/vbenchmark/.cursor/commands/preset-help.md +0 -50
- package/refs/vbenchmark/.cursor/commands/refactor.md +0 -71
- package/refs/vbenchmark/.cursor/commands/research.md +0 -37
- package/refs/vbenchmark/.cursor/commands/review.md +0 -38
- package/refs/vbenchmark/.cursor/commands/test.md +0 -61
- package/refs/vbenchmark/.cursor/rules/agents.mdc +0 -1357
- package/refs/vbenchmark/.factory/droids/codebase-explorer.md +0 -224
- package/refs/vbenchmark/.factory/droids/debugger.md +0 -180
- package/refs/vbenchmark/.factory/droids/documenter.md +0 -166
- package/refs/vbenchmark/.factory/droids/implementer.md +0 -70
- package/refs/vbenchmark/.factory/droids/orchestrator.md +0 -212
- package/refs/vbenchmark/.factory/droids/researcher.md +0 -80
- package/refs/vbenchmark/.factory/droids/reviewer.md +0 -184
- package/refs/vbenchmark/.factory/droids/tester.md +0 -170
- package/refs/vbenchmark/.gemini/workflows/commit.md +0 -29
- package/refs/vbenchmark/.gemini/workflows/debug.md +0 -59
- package/refs/vbenchmark/.gemini/workflows/document.md +0 -52
- package/refs/vbenchmark/.gemini/workflows/gather-context.md +0 -58
- package/refs/vbenchmark/.gemini/workflows/init.md +0 -56
- package/refs/vbenchmark/.gemini/workflows/preset-help.md +0 -50
- package/refs/vbenchmark/.gemini/workflows/refactor.md +0 -71
- package/refs/vbenchmark/.gemini/workflows/research.md +0 -37
- package/refs/vbenchmark/.gemini/workflows/review.md +0 -38
- package/refs/vbenchmark/.gemini/workflows/test.md +0 -61
- package/refs/vbenchmark/.github/CODEOWNERS +0 -20
- package/refs/vbenchmark/.github/FUNDING.yml +0 -4
- package/refs/vbenchmark/.github/ISSUE_TEMPLATE/bug-report.yml +0 -76
- package/refs/vbenchmark/.github/ISSUE_TEMPLATE/new-task.yml +0 -106
- package/refs/vbenchmark/.github/PULL_REQUEST_TEMPLATE.md +0 -38
- package/refs/vbenchmark/.github/copilot-instructions.md +0 -73
- package/refs/vbenchmark/.github/workflows/ci.yaml +0 -33
- package/refs/vbenchmark/.github/workflows/vercel-auto-pr.yml +0 -478
- package/refs/vbenchmark/.github/workflows/vercel-deploy.yaml +0 -487
- package/refs/vbenchmark/.github/workflows/vercel-pr-command.yaml +0 -337
- package/refs/vbenchmark/.github/workflows/vercel-project-init.yaml +0 -208
- package/refs/vbenchmark/.opencode/agent/codebase-explorer.md +0 -224
- package/refs/vbenchmark/.opencode/agent/debugger.md +0 -180
- package/refs/vbenchmark/.opencode/agent/documenter.md +0 -166
- package/refs/vbenchmark/.opencode/agent/implementer.md +0 -70
- package/refs/vbenchmark/.opencode/agent/orchestrator.md +0 -212
- package/refs/vbenchmark/.opencode/agent/researcher.md +0 -80
- package/refs/vbenchmark/.opencode/agent/reviewer.md +0 -184
- package/refs/vbenchmark/.opencode/agent/tester.md +0 -170
- package/refs/vbenchmark/.opencode/command/commit.md +0 -29
- package/refs/vbenchmark/.opencode/command/debug.md +0 -59
- package/refs/vbenchmark/.opencode/command/document.md +0 -52
- package/refs/vbenchmark/.opencode/command/gather-context.md +0 -58
- package/refs/vbenchmark/.opencode/command/init.md +0 -56
- package/refs/vbenchmark/.opencode/command/preset-help.md +0 -50
- package/refs/vbenchmark/.opencode/command/refactor.md +0 -71
- package/refs/vbenchmark/.opencode/command/research.md +0 -37
- package/refs/vbenchmark/.opencode/command/review.md +0 -38
- package/refs/vbenchmark/.opencode/command/test.md +0 -61
- package/refs/vbenchmark/.trae/project_rules.md +0 -73
- package/refs/vbenchmark/.windsurf/rules/rules.md +0 -85
- package/refs/vbenchmark/AGENTS.md +0 -73
- package/refs/vbenchmark/CONTRIBUTING.md +0 -332
- package/refs/vbenchmark/Caddyfile +0 -3
- package/refs/vbenchmark/LICENSE +0 -47
- package/refs/vbenchmark/README.md +0 -354
- package/refs/vbenchmark/docker-compose.prod.yaml +0 -35
- package/refs/vbenchmark/docker-compose.yaml +0 -53
- package/refs/vbenchmark/docs/TASK_EXPANSION_PLAN.md +0 -211
- package/refs/vbenchmark/docs/THESIS.md +0 -441
- package/refs/vbenchmark/docs/categories/code-evolution.md +0 -138
- package/refs/vbenchmark/openspec/changes/init-vibecodingbench/design.md +0 -111
- package/refs/vbenchmark/openspec/changes/init-vibecodingbench/proposal.md +0 -15
- package/refs/vbenchmark/openspec/changes/init-vibecodingbench/specs/evaluation/spec.md +0 -105
- package/refs/vbenchmark/openspec/changes/init-vibecodingbench/specs/leaderboard/spec.md +0 -68
- package/refs/vbenchmark/openspec/changes/init-vibecodingbench/specs/task-definition/spec.md +0 -45
- package/refs/vbenchmark/openspec/changes/init-vibecodingbench/specs/task-runner/spec.md +0 -49
- package/refs/vbenchmark/openspec/changes/init-vibecodingbench/tasks.md +0 -413
- package/refs/vbenchmark/package.json +0 -51
- package/refs/vbenchmark/packages/cli/eslint.config.js +0 -16
- package/refs/vbenchmark/packages/cli/package.json +0 -35
- package/refs/vbenchmark/packages/cli/src/agents/index.ts +0 -655
- package/refs/vbenchmark/packages/cli/src/commands/eval.ts +0 -197
- package/refs/vbenchmark/packages/cli/src/commands/list.ts +0 -63
- package/refs/vbenchmark/packages/cli/src/commands/run.ts +0 -147
- package/refs/vbenchmark/packages/cli/src/evaluator.ts +0 -125
- package/refs/vbenchmark/packages/cli/src/index.ts +0 -21
- package/refs/vbenchmark/packages/cli/src/lib/task-variation.ts +0 -153
- package/refs/vbenchmark/packages/cli/src/loader.ts +0 -258
- package/refs/vbenchmark/packages/cli/src/reporter.ts +0 -222
- package/refs/vbenchmark/packages/cli/src/runtime/docker.ts +0 -385
- package/refs/vbenchmark/packages/cli/tsconfig.json +0 -8
- package/refs/vbenchmark/packages/dashboard/Dockerfile +0 -42
- package/refs/vbenchmark/packages/dashboard/index.html +0 -21
- package/refs/vbenchmark/packages/dashboard/package.json +0 -29
- package/refs/vbenchmark/packages/dashboard/postcss.config.js +0 -6
- package/refs/vbenchmark/packages/dashboard/public/favicon.svg +0 -24
- package/refs/vbenchmark/packages/dashboard/public/logo.png +0 -0
- package/refs/vbenchmark/packages/dashboard/public/logo.svg +0 -39
- package/refs/vbenchmark/packages/dashboard/src/App.tsx +0 -1468
- package/refs/vbenchmark/packages/dashboard/src/data/category-performance.json +0 -1
- package/refs/vbenchmark/packages/dashboard/src/data/leaderboard.json +0 -1
- package/refs/vbenchmark/packages/dashboard/src/data/task-results.json +0 -1
- package/refs/vbenchmark/packages/dashboard/src/data/tasks.json +0 -1
- package/refs/vbenchmark/packages/dashboard/src/index.css +0 -3
- package/refs/vbenchmark/packages/dashboard/src/main.tsx +0 -13
- package/refs/vbenchmark/packages/dashboard/src/vite-env.d.ts +0 -9
- package/refs/vbenchmark/packages/dashboard/tailwind.config.js +0 -11
- package/refs/vbenchmark/packages/dashboard/tsconfig.json +0 -21
- package/refs/vbenchmark/packages/dashboard/tsconfig.node.json +0 -11
- package/refs/vbenchmark/packages/dashboard/vercel.json +0 -6
- package/refs/vbenchmark/packages/dashboard/vite.config.ts +0 -28
- package/refs/vbenchmark/packages/evaluator/eslint.config.js +0 -16
- package/refs/vbenchmark/packages/evaluator/package.json +0 -24
- package/refs/vbenchmark/packages/evaluator/src/index.ts +0 -15
- package/refs/vbenchmark/packages/evaluator/src/runners/functional.ts +0 -88
- package/refs/vbenchmark/packages/evaluator/src/runners/quality.ts +0 -140
- package/refs/vbenchmark/packages/evaluator/src/runners/security.ts +0 -94
- package/refs/vbenchmark/packages/evaluator/src/runners/visual.ts +0 -108
- package/refs/vbenchmark/packages/evaluator/src/types.d.ts +0 -19
- package/refs/vbenchmark/packages/evaluator/tsconfig.json +0 -8
- package/refs/vbenchmark/packages/leaderboard/Dockerfile +0 -38
- package/refs/vbenchmark/packages/leaderboard/drizzle.config.ts +0 -10
- package/refs/vbenchmark/packages/leaderboard/eslint.config.js +0 -16
- package/refs/vbenchmark/packages/leaderboard/fly.toml +0 -29
- package/refs/vbenchmark/packages/leaderboard/package.json +0 -36
- package/refs/vbenchmark/packages/leaderboard/src/app.ts +0 -29
- package/refs/vbenchmark/packages/leaderboard/src/components/BrowserPreview.tsx +0 -190
- package/refs/vbenchmark/packages/leaderboard/src/components/ComparisonView.tsx +0 -205
- package/refs/vbenchmark/packages/leaderboard/src/components/LeaderboardTable.tsx +0 -150
- package/refs/vbenchmark/packages/leaderboard/src/components/LiveRunCard.tsx +0 -133
- package/refs/vbenchmark/packages/leaderboard/src/components/SubmissionForm.tsx +0 -406
- package/refs/vbenchmark/packages/leaderboard/src/components/SubmitForm.tsx +0 -293
- package/refs/vbenchmark/packages/leaderboard/src/components/TerminalStream.tsx +0 -111
- package/refs/vbenchmark/packages/leaderboard/src/config/pricing.ts +0 -206
- package/refs/vbenchmark/packages/leaderboard/src/db/index.ts +0 -31
- package/refs/vbenchmark/packages/leaderboard/src/db/schema.ts +0 -125
- package/refs/vbenchmark/packages/leaderboard/src/index.ts +0 -13
- package/refs/vbenchmark/packages/leaderboard/src/lib/websocket.ts +0 -124
- package/refs/vbenchmark/packages/leaderboard/src/routes/leaderboard.ts +0 -698
- package/refs/vbenchmark/packages/leaderboard/src/routes/live.ts +0 -175
- package/refs/vbenchmark/packages/leaderboard/src/routes/submissions.ts +0 -183
- package/refs/vbenchmark/packages/leaderboard/src/routes/tasks.ts +0 -215
- package/refs/vbenchmark/packages/leaderboard/tests/api.test.ts +0 -228
- package/refs/vbenchmark/packages/leaderboard/tsconfig.json +0 -9
- package/refs/vbenchmark/scripts/deploy.sh +0 -70
- package/refs/vbenchmark/tasks/ai-integration/advanced/context-management/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/ai-integration/advanced/context-management/task.yaml +0 -16
- package/refs/vbenchmark/tasks/ai-integration/advanced/evaluation-framework/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/ai-integration/advanced/evaluation-framework/task.yaml +0 -16
- package/refs/vbenchmark/tasks/ai-integration/advanced/guardrails-safety/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/ai-integration/advanced/guardrails-safety/task.yaml +0 -16
- package/refs/vbenchmark/tasks/ai-integration/advanced/memory-system/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/ai-integration/advanced/memory-system/task.yaml +0 -16
- package/refs/vbenchmark/tasks/ai-integration/advanced/model-routing/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/ai-integration/advanced/model-routing/task.yaml +0 -16
- package/refs/vbenchmark/tasks/ai-integration/advanced/multi-agent-system/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/ai-integration/advanced/multi-agent-system/task.yaml +0 -16
- package/refs/vbenchmark/tasks/ai-integration/advanced/prompt-optimization/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/ai-integration/advanced/prompt-optimization/task.yaml +0 -16
- package/refs/vbenchmark/tasks/ai-integration/advanced/reasoning-chain/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/ai-integration/advanced/reasoning-chain/task.yaml +0 -16
- package/refs/vbenchmark/tasks/ai-integration/advanced/streaming-pipeline/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/ai-integration/advanced/streaming-pipeline/task.yaml +0 -16
- package/refs/vbenchmark/tasks/ai-integration/advanced/tool-use-orchestration/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/ai-integration/advanced/tool-use-orchestration/task.yaml +0 -16
- package/refs/vbenchmark/tasks/ai-integration/agents/code-review-agent/PROMPT.md +0 -64
- package/refs/vbenchmark/tasks/ai-integration/agents/code-review-agent/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/agents/research-agent/PROMPT.md +0 -61
- package/refs/vbenchmark/tasks/ai-integration/agents/research-agent/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/agents/web-scraper-agent/PROMPT.md +0 -57
- package/refs/vbenchmark/tasks/ai-integration/agents/web-scraper-agent/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/embeddings/duplicate-detection/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/ai-integration/embeddings/duplicate-detection/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/embeddings/recommendation-engine/PROMPT.md +0 -51
- package/refs/vbenchmark/tasks/ai-integration/embeddings/recommendation-engine/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/embeddings/semantic-search/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/ai-integration/embeddings/semantic-search/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/fine-tuning/classification-model/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/ai-integration/fine-tuning/classification-model/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/function-calling/api-orchestrator/PROMPT.md +0 -60
- package/refs/vbenchmark/tasks/ai-integration/function-calling/api-orchestrator/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/function-calling/calendar-assistant/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/ai-integration/function-calling/calendar-assistant/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/function-calling/database-query/PROMPT.md +0 -62
- package/refs/vbenchmark/tasks/ai-integration/function-calling/database-query/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/multimodal/chart-interpreter/PROMPT.md +0 -60
- package/refs/vbenchmark/tasks/ai-integration/multimodal/chart-interpreter/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/multimodal/image-captioning/PROMPT.md +0 -49
- package/refs/vbenchmark/tasks/ai-integration/multimodal/image-captioning/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/rag-chatbot/code-assistant/PROMPT.md +0 -51
- package/refs/vbenchmark/tasks/ai-integration/rag-chatbot/code-assistant/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/rag-chatbot/doc-search/PROMPT.md +0 -51
- package/refs/vbenchmark/tasks/ai-integration/rag-chatbot/doc-search/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/rag-chatbot/pdf-qa/PROMPT.md +0 -76
- package/refs/vbenchmark/tasks/ai-integration/rag-chatbot/pdf-qa/docker-compose.yaml +0 -30
- package/refs/vbenchmark/tasks/ai-integration/rag-chatbot/pdf-qa/task.yaml +0 -30
- package/refs/vbenchmark/tasks/ai-integration/rag-chatbot/pdf-qa/tests/functional/qa.test.py +0 -146
- package/refs/vbenchmark/tasks/ai-integration/rag-chatbot/support-bot/PROMPT.md +0 -51
- package/refs/vbenchmark/tasks/ai-integration/rag-chatbot/support-bot/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/structured-output/contract-analyzer/PROMPT.md +0 -67
- package/refs/vbenchmark/tasks/ai-integration/structured-output/contract-analyzer/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/structured-output/invoice-parser/PROMPT.md +0 -61
- package/refs/vbenchmark/tasks/ai-integration/structured-output/invoice-parser/task.yaml +0 -27
- package/refs/vbenchmark/tasks/ai-integration/structured-output/receipt-scanner/PROMPT.md +0 -65
- package/refs/vbenchmark/tasks/ai-integration/structured-output/receipt-scanner/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/structured-output/resume-parser/PROMPT.md +0 -70
- package/refs/vbenchmark/tasks/ai-integration/structured-output/resume-parser/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/advanced/api-analytics/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/api-integrations/advanced/api-analytics/task.yaml +0 -16
- package/refs/vbenchmark/tasks/api-integrations/advanced/api-gateway/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/api-integrations/advanced/api-gateway/task.yaml +0 -16
- package/refs/vbenchmark/tasks/api-integrations/advanced/api-mocking/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/api-integrations/advanced/api-mocking/task.yaml +0 -16
- package/refs/vbenchmark/tasks/api-integrations/advanced/contract-testing/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/api-integrations/advanced/contract-testing/task.yaml +0 -16
- package/refs/vbenchmark/tasks/api-integrations/advanced/graphql-federation/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/api-integrations/advanced/graphql-federation/task.yaml +0 -16
- package/refs/vbenchmark/tasks/api-integrations/advanced/grpc-gateway/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/api-integrations/advanced/grpc-gateway/task.yaml +0 -16
- package/refs/vbenchmark/tasks/api-integrations/advanced/rate-limiter/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/api-integrations/advanced/rate-limiter/task.yaml +0 -16
- package/refs/vbenchmark/tasks/api-integrations/advanced/request-validator/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/api-integrations/advanced/request-validator/task.yaml +0 -16
- package/refs/vbenchmark/tasks/api-integrations/advanced/sdk-generator/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/api-integrations/advanced/sdk-generator/task.yaml +0 -16
- package/refs/vbenchmark/tasks/api-integrations/advanced/webhook-processor/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/api-integrations/advanced/webhook-processor/task.yaml +0 -16
- package/refs/vbenchmark/tasks/api-integrations/analytics/mixpanel-events/PROMPT.md +0 -42
- package/refs/vbenchmark/tasks/api-integrations/analytics/mixpanel-events/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/analytics/segment-tracking/PROMPT.md +0 -42
- package/refs/vbenchmark/tasks/api-integrations/analytics/segment-tracking/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/auth-provider/oauth2-github/PROMPT.md +0 -42
- package/refs/vbenchmark/tasks/api-integrations/auth-provider/oauth2-github/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/auth-provider/okta-integration/PROMPT.md +0 -44
- package/refs/vbenchmark/tasks/api-integrations/auth-provider/okta-integration/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/auth-provider/saml-sso/PROMPT.md +0 -42
- package/refs/vbenchmark/tasks/api-integrations/auth-provider/saml-sso/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/communication/discord-webhook/PROMPT.md +0 -44
- package/refs/vbenchmark/tasks/api-integrations/communication/discord-webhook/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/communication/slack-bot/PROMPT.md +0 -42
- package/refs/vbenchmark/tasks/api-integrations/communication/slack-bot/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/communication/twilio-sms/PROMPT.md +0 -42
- package/refs/vbenchmark/tasks/api-integrations/communication/twilio-sms/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/email/transactional/PROMPT.md +0 -82
- package/refs/vbenchmark/tasks/api-integrations/email/transactional/task.yaml +0 -27
- package/refs/vbenchmark/tasks/api-integrations/maps/google-maps-geocoding/PROMPT.md +0 -41
- package/refs/vbenchmark/tasks/api-integrations/maps/google-maps-geocoding/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/maps/mapbox-directions/PROMPT.md +0 -41
- package/refs/vbenchmark/tasks/api-integrations/maps/mapbox-directions/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/payment/crypto-payments/PROMPT.md +0 -43
- package/refs/vbenchmark/tasks/api-integrations/payment/crypto-payments/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/payment/paypal-integration/PROMPT.md +0 -41
- package/refs/vbenchmark/tasks/api-integrations/payment/paypal-integration/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/social/twitter-api/PROMPT.md +0 -41
- package/refs/vbenchmark/tasks/api-integrations/social/twitter-api/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/storage/cloudinary-upload/PROMPT.md +0 -43
- package/refs/vbenchmark/tasks/api-integrations/storage/cloudinary-upload/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/storage/gcs-streaming/PROMPT.md +0 -43
- package/refs/vbenchmark/tasks/api-integrations/storage/gcs-streaming/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/storage/s3-presigned-urls/PROMPT.md +0 -41
- package/refs/vbenchmark/tasks/api-integrations/storage/s3-presigned-urls/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/stripe/checkout-session/PROMPT.md +0 -41
- package/refs/vbenchmark/tasks/api-integrations/stripe/checkout-session/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/stripe/payment-webhook/PROMPT.md +0 -60
- package/refs/vbenchmark/tasks/api-integrations/stripe/payment-webhook/docker-compose.yaml +0 -38
- package/refs/vbenchmark/tasks/api-integrations/stripe/payment-webhook/task.yaml +0 -31
- package/refs/vbenchmark/tasks/api-integrations/stripe/payment-webhook/tests/webhook.test.ts +0 -193
- package/refs/vbenchmark/tasks/api-integrations/stripe/subscription-portal/PROMPT.md +0 -41
- package/refs/vbenchmark/tasks/api-integrations/stripe/subscription-portal/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/advanced/api-deprecation/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/code-evolution/advanced/api-deprecation/task.yaml +0 -16
- package/refs/vbenchmark/tasks/code-evolution/advanced/ast-refactoring/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/code-evolution/advanced/ast-refactoring/task.yaml +0 -16
- package/refs/vbenchmark/tasks/code-evolution/advanced/concurrency-fix/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/code-evolution/advanced/concurrency-fix/task.yaml +0 -16
- package/refs/vbenchmark/tasks/code-evolution/advanced/database-schema-migration/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/code-evolution/advanced/database-schema-migration/task.yaml +0 -16
- package/refs/vbenchmark/tasks/code-evolution/advanced/dead-code-elimination/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/code-evolution/advanced/dead-code-elimination/task.yaml +0 -16
- package/refs/vbenchmark/tasks/code-evolution/advanced/dependency-upgrade/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/code-evolution/advanced/dependency-upgrade/task.yaml +0 -16
- package/refs/vbenchmark/tasks/code-evolution/advanced/memory-optimization/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/code-evolution/advanced/memory-optimization/task.yaml +0 -16
- package/refs/vbenchmark/tasks/code-evolution/advanced/monorepo-extraction/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/code-evolution/advanced/monorepo-extraction/task.yaml +0 -16
- package/refs/vbenchmark/tasks/code-evolution/advanced/performance-profiling/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/code-evolution/advanced/performance-profiling/task.yaml +0 -16
- package/refs/vbenchmark/tasks/code-evolution/advanced/type-migration/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/code-evolution/advanced/type-migration/task.yaml +0 -16
- package/refs/vbenchmark/tasks/code-evolution/legacy-migration/callback-to-async/PROMPT.md +0 -47
- package/refs/vbenchmark/tasks/code-evolution/legacy-migration/callback-to-async/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/legacy-migration/express-to-fastify/PROMPT.md +0 -49
- package/refs/vbenchmark/tasks/code-evolution/legacy-migration/express-to-fastify/base-code/src/app.ts +0 -22
- package/refs/vbenchmark/tasks/code-evolution/legacy-migration/express-to-fastify/task.yaml +0 -37
- package/refs/vbenchmark/tasks/code-evolution/legacy-migration/express-to-fastify/tests/api.test.ts +0 -70
- package/refs/vbenchmark/tasks/code-evolution/legacy-migration/flask-to-fastapi/PROMPT.md +0 -46
- package/refs/vbenchmark/tasks/code-evolution/legacy-migration/flask-to-fastapi/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/legacy-migration/java-to-kotlin/PROMPT.md +0 -45
- package/refs/vbenchmark/tasks/code-evolution/legacy-migration/java-to-kotlin/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/legacy-migration/jquery-to-react/PROMPT.md +0 -47
- package/refs/vbenchmark/tasks/code-evolution/legacy-migration/jquery-to-react/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/legacy-migration/rest-to-grpc/PROMPT.md +0 -47
- package/refs/vbenchmark/tasks/code-evolution/legacy-migration/rest-to-grpc/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/performance/async-refactor/PROMPT.md +0 -47
- package/refs/vbenchmark/tasks/code-evolution/performance/async-refactor/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/performance/memory-leak-fix/PROMPT.md +0 -47
- package/refs/vbenchmark/tasks/code-evolution/performance/memory-leak-fix/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/performance/query-optimization/PROMPT.md +0 -49
- package/refs/vbenchmark/tasks/code-evolution/performance/query-optimization/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/refactoring/class-to-hooks/PROMPT.md +0 -96
- package/refs/vbenchmark/tasks/code-evolution/refactoring/class-to-hooks/task.yaml +0 -27
- package/refs/vbenchmark/tasks/code-evolution/refactoring/dependency-injection/PROMPT.md +0 -47
- package/refs/vbenchmark/tasks/code-evolution/refactoring/dependency-injection/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/refactoring/error-handling/PROMPT.md +0 -48
- package/refs/vbenchmark/tasks/code-evolution/refactoring/error-handling/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/refactoring/monolith-to-modules/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/code-evolution/refactoring/monolith-to-modules/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/refactoring/orm-migration/PROMPT.md +0 -47
- package/refs/vbenchmark/tasks/code-evolution/refactoring/orm-migration/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/security/secrets-rotation/PROMPT.md +0 -49
- package/refs/vbenchmark/tasks/code-evolution/security/secrets-rotation/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/security/sql-injection-fix/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/code-evolution/security/sql-injection-fix/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/security/xss-prevention/PROMPT.md +0 -47
- package/refs/vbenchmark/tasks/code-evolution/security/xss-prevention/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/testing/add-unit-tests/PROMPT.md +0 -48
- package/refs/vbenchmark/tasks/code-evolution/testing/add-unit-tests/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/testing/e2e-playwright/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/code-evolution/testing/e2e-playwright/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/testing/pytest-fixtures/PROMPT.md +0 -47
- package/refs/vbenchmark/tasks/code-evolution/testing/pytest-fixtures/task.yaml +0 -24
- package/refs/vbenchmark/tasks/frontend/accessibility/keyboard-shortcuts/PROMPT.md +0 -44
- package/refs/vbenchmark/tasks/frontend/accessibility/keyboard-shortcuts/task.yaml +0 -24
- package/refs/vbenchmark/tasks/frontend/accessibility/screen-reader-nav/PROMPT.md +0 -44
- package/refs/vbenchmark/tasks/frontend/accessibility/screen-reader-nav/task.yaml +0 -24
- package/refs/vbenchmark/tasks/frontend/advanced/canvas-editor/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/frontend/advanced/canvas-editor/task.yaml +0 -16
- package/refs/vbenchmark/tasks/frontend/advanced/micro-frontend/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/frontend/advanced/micro-frontend/task.yaml +0 -16
- package/refs/vbenchmark/tasks/frontend/advanced/offline-first/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/frontend/advanced/offline-first/task.yaml +0 -16
- package/refs/vbenchmark/tasks/frontend/advanced/realtime-collab/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/frontend/advanced/realtime-collab/task.yaml +0 -16
- package/refs/vbenchmark/tasks/frontend/advanced/service-worker/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/frontend/advanced/service-worker/task.yaml +0 -16
- package/refs/vbenchmark/tasks/frontend/advanced/state-machine/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/frontend/advanced/state-machine/task.yaml +0 -16
- package/refs/vbenchmark/tasks/frontend/advanced/virtual-list/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/frontend/advanced/virtual-list/task.yaml +0 -16
- package/refs/vbenchmark/tasks/frontend/advanced/wasm-integration/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/frontend/advanced/wasm-integration/task.yaml +0 -16
- package/refs/vbenchmark/tasks/frontend/advanced/web-worker/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/frontend/advanced/web-worker/task.yaml +0 -16
- package/refs/vbenchmark/tasks/frontend/advanced/webgl-visualization/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/frontend/advanced/webgl-visualization/task.yaml +0 -16
- package/refs/vbenchmark/tasks/frontend/animation/page-transitions/PROMPT.md +0 -44
- package/refs/vbenchmark/tasks/frontend/animation/page-transitions/task.yaml +0 -24
- package/refs/vbenchmark/tasks/frontend/components/data-grid/PROMPT.md +0 -59
- package/refs/vbenchmark/tasks/frontend/components/data-grid/task.yaml +0 -24
- package/refs/vbenchmark/tasks/frontend/components/date-range-picker/PROMPT.md +0 -57
- package/refs/vbenchmark/tasks/frontend/components/date-range-picker/task.yaml +0 -24
- package/refs/vbenchmark/tasks/frontend/components/file-uploader/PROMPT.md +0 -55
- package/refs/vbenchmark/tasks/frontend/components/file-uploader/task.yaml +0 -24
- package/refs/vbenchmark/tasks/frontend/components/form-builder/PROMPT.md +0 -96
- package/refs/vbenchmark/tasks/frontend/components/form-builder/task.yaml +0 -28
- package/refs/vbenchmark/tasks/frontend/components/rich-text-editor/PROMPT.md +0 -45
- package/refs/vbenchmark/tasks/frontend/components/rich-text-editor/task.yaml +0 -24
- package/refs/vbenchmark/tasks/frontend/figma-to-code/dashboard-layout/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/frontend/figma-to-code/dashboard-layout/task.yaml +0 -25
- package/refs/vbenchmark/tasks/frontend/figma-to-code/landing-page/PROMPT.md +0 -49
- package/refs/vbenchmark/tasks/frontend/figma-to-code/landing-page/task.yaml +0 -25
- package/refs/vbenchmark/tasks/frontend/figma-to-code/mobile-app-screen/PROMPT.md +0 -51
- package/refs/vbenchmark/tasks/frontend/figma-to-code/mobile-app-screen/task.yaml +0 -24
- package/refs/vbenchmark/tasks/frontend/figma-to-code/pricing-card/PROMPT.md +0 -93
- package/refs/vbenchmark/tasks/frontend/figma-to-code/pricing-card/docker-compose.yaml +0 -23
- package/refs/vbenchmark/tasks/frontend/figma-to-code/pricing-card/task.yaml +0 -30
- package/refs/vbenchmark/tasks/frontend/figma-to-code/pricing-card/tests/visual/diff.test.ts +0 -107
- package/refs/vbenchmark/tasks/frontend/figma-to-code/pricing-card/tests/visual/interaction.test.ts +0 -88
- package/refs/vbenchmark/tasks/frontend/performance/image-lazy-load/PROMPT.md +0 -43
- package/refs/vbenchmark/tasks/frontend/performance/image-lazy-load/task.yaml +0 -24
- package/refs/vbenchmark/tasks/frontend/performance/infinite-scroll/PROMPT.md +0 -44
- package/refs/vbenchmark/tasks/frontend/performance/infinite-scroll/task.yaml +0 -24
- package/refs/vbenchmark/tasks/frontend/state-management/collaborative-editor/PROMPT.md +0 -44
- package/refs/vbenchmark/tasks/frontend/state-management/collaborative-editor/task.yaml +0 -24
- package/refs/vbenchmark/tasks/frontend/state-management/shopping-cart/PROMPT.md +0 -53
- package/refs/vbenchmark/tasks/frontend/state-management/shopping-cart/task.yaml +0 -24
- package/refs/vbenchmark/tasks/frontend/visualization/chart-dashboard/PROMPT.md +0 -83
- package/refs/vbenchmark/tasks/frontend/visualization/chart-dashboard/task.yaml +0 -28
- package/refs/vbenchmark/tasks/frontend/visualization/gantt-chart/PROMPT.md +0 -57
- package/refs/vbenchmark/tasks/frontend/visualization/gantt-chart/task.yaml +0 -24
- package/refs/vbenchmark/tasks/frontend/visualization/map-dashboard/PROMPT.md +0 -44
- package/refs/vbenchmark/tasks/frontend/visualization/map-dashboard/task.yaml +0 -24
- package/refs/vbenchmark/tasks/frontend/visualization/realtime-charts/PROMPT.md +0 -43
- package/refs/vbenchmark/tasks/frontend/visualization/realtime-charts/task.yaml +0 -24
- package/refs/vbenchmark/tasks/glue-code/advanced/blue-green-deploy/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/glue-code/advanced/blue-green-deploy/task.yaml +0 -16
- package/refs/vbenchmark/tasks/glue-code/advanced/canary-release/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/glue-code/advanced/canary-release/task.yaml +0 -16
- package/refs/vbenchmark/tasks/glue-code/advanced/change-data-capture/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/glue-code/advanced/change-data-capture/task.yaml +0 -16
- package/refs/vbenchmark/tasks/glue-code/advanced/config-management/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/glue-code/advanced/config-management/task.yaml +0 -16
- package/refs/vbenchmark/tasks/glue-code/advanced/data-pipeline/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/glue-code/advanced/data-pipeline/task.yaml +0 -16
- package/refs/vbenchmark/tasks/glue-code/advanced/distributed-tracing/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/glue-code/advanced/distributed-tracing/task.yaml +0 -16
- package/refs/vbenchmark/tasks/glue-code/advanced/log-aggregation/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/glue-code/advanced/log-aggregation/task.yaml +0 -16
- package/refs/vbenchmark/tasks/glue-code/advanced/schema-registry/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/glue-code/advanced/schema-registry/task.yaml +0 -16
- package/refs/vbenchmark/tasks/glue-code/advanced/secret-rotation/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/glue-code/advanced/secret-rotation/task.yaml +0 -16
- package/refs/vbenchmark/tasks/glue-code/advanced/stream-processing/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/glue-code/advanced/stream-processing/task.yaml +0 -16
- package/refs/vbenchmark/tasks/glue-code/api-sync/rest-to-graphql/PROMPT.md +0 -66
- package/refs/vbenchmark/tasks/glue-code/api-sync/rest-to-graphql/task.yaml +0 -27
- package/refs/vbenchmark/tasks/glue-code/caching/redis-cache/PROMPT.md +0 -82
- package/refs/vbenchmark/tasks/glue-code/caching/redis-cache/task.yaml +0 -27
- package/refs/vbenchmark/tasks/glue-code/data-transform/avro-schema-evolution/PROMPT.md +0 -51
- package/refs/vbenchmark/tasks/glue-code/data-transform/avro-schema-evolution/task.yaml +0 -24
- package/refs/vbenchmark/tasks/glue-code/data-transform/csv-normalizer/PROMPT.md +0 -49
- package/refs/vbenchmark/tasks/glue-code/data-transform/csv-normalizer/task.yaml +0 -24
- package/refs/vbenchmark/tasks/glue-code/data-transform/excel-to-json/PROMPT.md +0 -67
- package/refs/vbenchmark/tasks/glue-code/data-transform/excel-to-json/task.yaml +0 -28
- package/refs/vbenchmark/tasks/glue-code/data-transform/excel-to-json/tests/transform.test.py +0 -137
- package/refs/vbenchmark/tasks/glue-code/data-transform/json-to-xml/PROMPT.md +0 -45
- package/refs/vbenchmark/tasks/glue-code/data-transform/json-to-xml/task.yaml +0 -24
- package/refs/vbenchmark/tasks/glue-code/data-transform/protobuf-converter/PROMPT.md +0 -44
- package/refs/vbenchmark/tasks/glue-code/data-transform/protobuf-converter/task.yaml +0 -24
- package/refs/vbenchmark/tasks/glue-code/etl/cdc-pipeline/PROMPT.md +0 -52
- package/refs/vbenchmark/tasks/glue-code/etl/cdc-pipeline/task.yaml +0 -27
- package/refs/vbenchmark/tasks/glue-code/etl/database-sync/PROMPT.md +0 -51
- package/refs/vbenchmark/tasks/glue-code/etl/database-sync/task.yaml +0 -24
- package/refs/vbenchmark/tasks/glue-code/etl/s3-to-warehouse/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/glue-code/etl/s3-to-warehouse/task.yaml +0 -24
- package/refs/vbenchmark/tasks/glue-code/file-processing/image-resizer/PROMPT.md +0 -52
- package/refs/vbenchmark/tasks/glue-code/file-processing/image-resizer/task.yaml +0 -24
- package/refs/vbenchmark/tasks/glue-code/file-processing/pdf-merger/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/glue-code/file-processing/pdf-merger/task.yaml +0 -24
- package/refs/vbenchmark/tasks/glue-code/file-processing/video-transcoder/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/glue-code/file-processing/video-transcoder/task.yaml +0 -27
- package/refs/vbenchmark/tasks/glue-code/migration/data-backfill/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/glue-code/migration/data-backfill/task.yaml +0 -24
- package/refs/vbenchmark/tasks/glue-code/migration/database-versioning/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/glue-code/migration/database-versioning/task.yaml +0 -24
- package/refs/vbenchmark/tasks/glue-code/queue/kafka-producer/PROMPT.md +0 -49
- package/refs/vbenchmark/tasks/glue-code/queue/kafka-producer/task.yaml +0 -27
- package/refs/vbenchmark/tasks/glue-code/queue/rabbitmq-consumer/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/glue-code/queue/rabbitmq-consumer/task.yaml +0 -27
- package/refs/vbenchmark/tasks/glue-code/queue/sqs-batch-processor/PROMPT.md +0 -47
- package/refs/vbenchmark/tasks/glue-code/queue/sqs-batch-processor/task.yaml +0 -24
- package/refs/vbenchmark/tasks/glue-code/scheduler/cron-job-manager/PROMPT.md +0 -52
- package/refs/vbenchmark/tasks/glue-code/scheduler/cron-job-manager/task.yaml +0 -27
- package/refs/vbenchmark/tasks/glue-code/scheduler/delayed-tasks/PROMPT.md +0 -51
- package/refs/vbenchmark/tasks/glue-code/scheduler/delayed-tasks/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/advanced/api-versioning/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/saas-core/advanced/api-versioning/task.yaml +0 -16
- package/refs/vbenchmark/tasks/saas-core/advanced/circuit-breaker/PROMPT.md +0 -13
- package/refs/vbenchmark/tasks/saas-core/advanced/circuit-breaker/task.yaml +0 -16
- package/refs/vbenchmark/tasks/saas-core/advanced/compliance-gdpr/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/saas-core/advanced/compliance-gdpr/task.yaml +0 -16
- package/refs/vbenchmark/tasks/saas-core/advanced/cqrs-pattern/PROMPT.md +0 -13
- package/refs/vbenchmark/tasks/saas-core/advanced/cqrs-pattern/task.yaml +0 -16
- package/refs/vbenchmark/tasks/saas-core/advanced/data-encryption/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/saas-core/advanced/data-encryption/task.yaml +0 -16
- package/refs/vbenchmark/tasks/saas-core/advanced/distributed-locking/PROMPT.md +0 -46
- package/refs/vbenchmark/tasks/saas-core/advanced/distributed-locking/task.yaml +0 -24
- package/refs/vbenchmark/tasks/saas-core/advanced/event-sourcing/PROMPT.md +0 -23
- package/refs/vbenchmark/tasks/saas-core/advanced/event-sourcing/task.yaml +0 -16
- package/refs/vbenchmark/tasks/saas-core/advanced/feature-flags-ab/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/saas-core/advanced/feature-flags-ab/task.yaml +0 -16
- package/refs/vbenchmark/tasks/saas-core/advanced/saga-orchestration/PROMPT.md +0 -13
- package/refs/vbenchmark/tasks/saas-core/advanced/saga-orchestration/task.yaml +0 -16
- package/refs/vbenchmark/tasks/saas-core/advanced/webhook-delivery/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/saas-core/advanced/webhook-delivery/task.yaml +0 -16
- package/refs/vbenchmark/tasks/saas-core/audit/activity-logging/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/saas-core/audit/activity-logging/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/auth/jwt-refresh-tokens/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/saas-core/auth/jwt-refresh-tokens/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/auth/magic-link-email/PROMPT.md +0 -53
- package/refs/vbenchmark/tasks/saas-core/auth/magic-link-email/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/auth/mfa-totp/PROMPT.md +0 -79
- package/refs/vbenchmark/tasks/saas-core/auth/mfa-totp/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/auth/rbac-permissions/PROMPT.md +0 -51
- package/refs/vbenchmark/tasks/saas-core/auth/rbac-permissions/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/auth/session-management/PROMPT.md +0 -52
- package/refs/vbenchmark/tasks/saas-core/auth/session-management/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/auth/supabase-oauth/PROMPT.md +0 -45
- package/refs/vbenchmark/tasks/saas-core/auth/supabase-oauth/docker-compose.yaml +0 -47
- package/refs/vbenchmark/tasks/saas-core/auth/supabase-oauth/task.yaml +0 -32
- package/refs/vbenchmark/tasks/saas-core/auth/supabase-oauth/tests/auth.test.ts +0 -59
- package/refs/vbenchmark/tasks/saas-core/billing/invoice-generation/PROMPT.md +0 -53
- package/refs/vbenchmark/tasks/saas-core/billing/invoice-generation/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/billing/stripe-subscriptions/PROMPT.md +0 -51
- package/refs/vbenchmark/tasks/saas-core/billing/stripe-subscriptions/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/billing/usage-metering/PROMPT.md +0 -52
- package/refs/vbenchmark/tasks/saas-core/billing/usage-metering/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/crud/dashboard-table/PROMPT.md +0 -48
- package/refs/vbenchmark/tasks/saas-core/crud/dashboard-table/task.yaml +0 -28
- package/refs/vbenchmark/tasks/saas-core/multi-tenant/org-isolation/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/saas-core/multi-tenant/org-isolation/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/multi-tenant/subdomain-routing/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/saas-core/multi-tenant/subdomain-routing/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/notifications/email-queue/PROMPT.md +0 -53
- package/refs/vbenchmark/tasks/saas-core/notifications/email-queue/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/notifications/in-app-alerts/PROMPT.md +0 -51
- package/refs/vbenchmark/tasks/saas-core/notifications/in-app-alerts/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/notifications/push-notifications/PROMPT.md +0 -51
- package/refs/vbenchmark/tasks/saas-core/notifications/push-notifications/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/realtime/websocket-chat/PROMPT.md +0 -80
- package/refs/vbenchmark/tasks/saas-core/realtime/websocket-chat/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/search/full-text-search/PROMPT.md +0 -51
- package/refs/vbenchmark/tasks/saas-core/search/full-text-search/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/security/rate-limiter/PROMPT.md +0 -99
- package/refs/vbenchmark/tasks/saas-core/security/rate-limiter/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/settings/user-preferences/PROMPT.md +0 -78
- package/refs/vbenchmark/tasks/saas-core/settings/user-preferences/task.yaml +0 -27
- package/refs/vbenchmark/templates/fastapi-postgres/docker-compose.yaml +0 -36
- package/refs/vbenchmark/templates/fastapi-postgres/pyproject.toml +0 -34
- package/refs/vbenchmark/templates/fastapi-postgres/src/__init__.py +0 -0
- package/refs/vbenchmark/templates/fastapi-postgres/src/config.py +0 -12
- package/refs/vbenchmark/templates/fastapi-postgres/src/database.py +0 -15
- package/refs/vbenchmark/templates/fastapi-postgres/src/main.py +0 -51
- package/refs/vbenchmark/templates/fastapi-postgres/src/models.py +0 -12
- package/refs/vbenchmark/templates/fastapi-postgres/src/schemas.py +0 -20
- package/refs/vbenchmark/templates/go-fiber/docker-compose.yaml +0 -34
- package/refs/vbenchmark/templates/go-fiber/go.mod +0 -33
- package/refs/vbenchmark/templates/go-fiber/go.sum +0 -68
- package/refs/vbenchmark/templates/go-fiber/main.go +0 -98
- package/refs/vbenchmark/templates/nextjs-supabase/.env.example +0 -3
- package/refs/vbenchmark/templates/nextjs-supabase/docker-compose.yaml +0 -68
- package/refs/vbenchmark/templates/nextjs-supabase/src/app/globals.css +0 -13
- package/refs/vbenchmark/templates/nextjs-supabase/src/app/layout.tsx +0 -19
- package/refs/vbenchmark/templates/nextjs-supabase/src/app/page.tsx +0 -38
- package/refs/vbenchmark/templates/nextjs-supabase/src/lib/supabase/client.ts +0 -8
- package/refs/vbenchmark/templates/nextjs-supabase/src/lib/supabase/server.ts +0 -32
- package/refs/vbenchmark/templates/rust-axum/Cargo.lock +0 -2371
- package/refs/vbenchmark/templates/rust-axum/Cargo.toml +0 -16
- package/refs/vbenchmark/templates/rust-axum/docker-compose.yaml +0 -34
- package/refs/vbenchmark/templates/rust-axum/migrations/20240101000000_init.sql +0 -20
- package/refs/vbenchmark/templates/rust-axum/src/main.rs +0 -121
- package/refs/vbenchmark/tsconfig.base.json +0 -18
- package/refs/vbenchmark/turbo.json +0 -23
- package/refs/vbenchmark/vercel.json +0 -10
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"performance":[{"category":"saas-core","models":[{"modelName":"GLM 4-Plus","avgScore":90.2,"passRate":100.9,"avgTokens":132351,"avgTimeMs":105831,"avgCost":0.155},{"modelName":"MiniMax M2.1","avgScore":89.4,"passRate":101.4,"avgTokens":463079,"avgTimeMs":181398,"avgCost":0.4},{"modelName":"GLM-4.7","avgScore":85.9,"passRate":87.6,"avgTokens":103912,"avgTimeMs":62486,"avgCost":0.122},{"modelName":"Gemini 3 Flash","avgScore":85.4,"passRate":94.2,"avgTokens":63999,"avgTimeMs":30604,"avgCost":0.143},{"modelName":"Gemini 3 Pro Preview","avgScore":88.2,"passRate":96.7,"avgTokens":122975,"avgTimeMs":40000,"avgCost":1.72},{"modelName":"Claude Sonnet 4.5","avgScore":90.6,"passRate":100.3,"avgTokens":102000,"avgTimeMs":46200,"avgCost":1.163},{"modelName":"Claude Opus 4.5","avgScore":91.2,"passRate":102,"avgTokens":107958,"avgTimeMs":48354,"avgCost":2.052},{"modelName":"Claude Haiku 4.5","avgScore":91,"passRate":101.4,"avgTokens":133049,"avgTimeMs":23727,"avgCost":0.505},{"modelName":"DeepSeek v3.2","avgScore":90.2,"passRate":100.3,"avgTokens":90448,"avgTimeMs":98596,"avgCost":0.083},{"modelName":"OpenAI GPT-5.2","avgScore":90.8,"passRate":100.3,"avgTokens":80833,"avgTimeMs":30800,"avgCost":0.835},{"modelName":"GLM 4.7 Flash","avgScore":80.3,"passRate":83.3,"avgTokens":108333,"avgTimeMs":45000,"avgCost":0.185},{"modelName":"Grok 4 Fast","avgScore":90.8,"passRate":100.9,"avgTokens":86667,"avgTimeMs":77000,"avgCost":0.035},{"modelName":"Grok 4","avgScore":90,"passRate":99.8,"avgTokens":80000,"avgTimeMs":82500,"avgCost":0.912},{"modelName":"Grok 4.1 Fast","avgScore":88.8,"passRate":99.2,"avgTokens":96667,"avgTimeMs":97350,"avgCost":0.04},{"modelName":"Qwen3 Max","avgScore":88.4,"passRate":100,"avgTokens":158202,"avgTimeMs":45000,"avgCost":0.9}]},{"category":"glue-code","models":[{"modelName":"GLM 4-Plus","avgScore":87.2,"passRate":97.9,"avgTokens":132351,"avgTimeMs":91400,"avgCost":0.155},{"modelName":"MiniMax M2.1","avgScore":86.4,"passRate":98.4,"avgTokens":463079,"avgTimeMs":156662,"avgCost":0.4},{"modelName":"GLM-4.7","avgScore":82.9,"passRate":84.6,"avgTokens":103912,"avgTimeMs":53965,"avgCost":0.122},{"modelName":"Gemini 3 Flash","avgScore":82.4,"passRate":91.2,"avgTokens":63999,"avgTimeMs":26431,"avgCost":0.143},{"modelName":"Gemini 3 Pro Preview","avgScore":82.2,"passRate":90,"avgTokens":122975,"avgTimeMs":40000,"avgCost":1.72},{"modelName":"Claude Sonnet 4.5","avgScore":87.6,"passRate":97.3,"avgTokens":102000,"avgTimeMs":39900,"avgCost":1.163},{"modelName":"Claude Opus 4.5","avgScore":88.2,"passRate":99,"avgTokens":107958,"avgTimeMs":41760,"avgCost":2.052},{"modelName":"Claude Haiku 4.5","avgScore":88,"passRate":98.4,"avgTokens":133049,"avgTimeMs":20492,"avgCost":0.505},{"modelName":"DeepSeek v3.2","avgScore":87.2,"passRate":97.3,"avgTokens":90448,"avgTimeMs":85151,"avgCost":0.083},{"modelName":"OpenAI GPT-5.2","avgScore":87.8,"passRate":97.3,"avgTokens":80833,"avgTimeMs":26600,"avgCost":0.835},{"modelName":"GLM 4.7 Flash","avgScore":81.6,"passRate":90,"avgTokens":108333,"avgTimeMs":45000,"avgCost":0.185},{"modelName":"Grok 4 Fast","avgScore":87.8,"passRate":97.9,"avgTokens":86667,"avgTimeMs":66500,"avgCost":0.035},{"modelName":"Grok 4","avgScore":87,"passRate":96.8,"avgTokens":80000,"avgTimeMs":71250,"avgCost":0.912},{"modelName":"Grok 4.1 Fast","avgScore":85.8,"passRate":96.2,"avgTokens":96667,"avgTimeMs":84075,"avgCost":0.04},{"modelName":"Qwen3 Max","avgScore":88.5,"passRate":100,"avgTokens":158202,"avgTimeMs":45000,"avgCost":0.9}]},{"category":"ai-integration","models":[{"modelName":"GLM 4-Plus","avgScore":86.2,"passRate":96.9,"avgTokens":132351,"avgTimeMs":86589,"avgCost":0.155},{"modelName":"MiniMax M2.1","avgScore":85.4,"passRate":97.4,"avgTokens":463079,"avgTimeMs":148416,"avgCost":0.4},{"modelName":"GLM-4.7","avgScore":81.9,"passRate":83.6,"avgTokens":103912,"avgTimeMs":51125,"avgCost":0.122},{"modelName":"Gemini 3 Flash","avgScore":81.4,"passRate":90.2,"avgTokens":63999,"avgTimeMs":25040,"avgCost":0.143},{"modelName":"Gemini 3 Pro Preview","avgScore":83.5,"passRate":93.3,"avgTokens":122975,"avgTimeMs":40000,"avgCost":1.72},{"modelName":"Claude Sonnet 4.5","avgScore":86.6,"passRate":96.3,"avgTokens":102000,"avgTimeMs":37800,"avgCost":1.163},{"modelName":"Claude Opus 4.5","avgScore":87.2,"passRate":98,"avgTokens":107958,"avgTimeMs":39562,"avgCost":2.052},{"modelName":"Claude Haiku 4.5","avgScore":87,"passRate":97.4,"avgTokens":133049,"avgTimeMs":19413,"avgCost":0.505},{"modelName":"DeepSeek v3.2","avgScore":86.2,"passRate":96.3,"avgTokens":90448,"avgTimeMs":80670,"avgCost":0.083},{"modelName":"OpenAI GPT-5.2","avgScore":86.8,"passRate":96.3,"avgTokens":80833,"avgTimeMs":25200,"avgCost":0.835},{"modelName":"GLM 4.7 Flash","avgScore":87.6,"passRate":100,"avgTokens":108333,"avgTimeMs":45000,"avgCost":0.185},{"modelName":"Grok 4 Fast","avgScore":86.8,"passRate":96.9,"avgTokens":86667,"avgTimeMs":63000,"avgCost":0.035},{"modelName":"Grok 4","avgScore":86,"passRate":95.8,"avgTokens":80000,"avgTimeMs":67500,"avgCost":0.912},{"modelName":"Grok 4.1 Fast","avgScore":84.8,"passRate":95.2,"avgTokens":96667,"avgTimeMs":79650,"avgCost":0.04},{"modelName":"Qwen3 Max","avgScore":88.8,"passRate":100,"avgTokens":158202,"avgTimeMs":45000,"avgCost":0.9}]},{"category":"frontend","models":[{"modelName":"GLM 4-Plus","avgScore":91.2,"passRate":101.9,"avgTokens":132351,"avgTimeMs":110641,"avgCost":0.155},{"modelName":"MiniMax M2.1","avgScore":90.4,"passRate":102.4,"avgTokens":463079,"avgTimeMs":189643,"avgCost":0.4},{"modelName":"GLM-4.7","avgScore":86.9,"passRate":88.6,"avgTokens":103912,"avgTimeMs":65326,"avgCost":0.122},{"modelName":"Gemini 3 Flash","avgScore":86.4,"passRate":95.2,"avgTokens":63999,"avgTimeMs":31995,"avgCost":0.143},{"modelName":"Gemini 3 Pro Preview","avgScore":88,"passRate":96.7,"avgTokens":122975,"avgTimeMs":40000,"avgCost":1.72},{"modelName":"Claude Sonnet 4.5","avgScore":91.6,"passRate":101.3,"avgTokens":102000,"avgTimeMs":48300,"avgCost":1.163},{"modelName":"Claude Opus 4.5","avgScore":92.2,"passRate":103,"avgTokens":107958,"avgTimeMs":50552,"avgCost":2.052},{"modelName":"Claude Haiku 4.5","avgScore":92,"passRate":102.4,"avgTokens":133049,"avgTimeMs":24805,"avgCost":0.505},{"modelName":"DeepSeek v3.2","avgScore":91.2,"passRate":101.3,"avgTokens":90448,"avgTimeMs":103078,"avgCost":0.083},{"modelName":"OpenAI GPT-5.2","avgScore":91.8,"passRate":101.3,"avgTokens":80833,"avgTimeMs":32200,"avgCost":0.835},{"modelName":"GLM 4.7 Flash","avgScore":85.2,"passRate":96.7,"avgTokens":108333,"avgTimeMs":45000,"avgCost":0.185},{"modelName":"Grok 4 Fast","avgScore":91.8,"passRate":101.9,"avgTokens":86667,"avgTimeMs":80500,"avgCost":0.035},{"modelName":"Grok 4","avgScore":91,"passRate":100.8,"avgTokens":80000,"avgTimeMs":86250,"avgCost":0.912},{"modelName":"Grok 4.1 Fast","avgScore":89.8,"passRate":100.2,"avgTokens":96667,"avgTimeMs":101775,"avgCost":0.04},{"modelName":"Qwen3 Max","avgScore":88.3,"passRate":100,"avgTokens":158202,"avgTimeMs":45000,"avgCost":0.9}]},{"category":"api-integrations","models":[{"modelName":"GLM 4-Plus","avgScore":89.2,"passRate":99.9,"avgTokens":132351,"avgTimeMs":101021,"avgCost":0.155},{"modelName":"MiniMax M2.1","avgScore":88.4,"passRate":100.4,"avgTokens":463079,"avgTimeMs":173152,"avgCost":0.4},{"modelName":"GLM-4.7","avgScore":84.9,"passRate":86.6,"avgTokens":103912,"avgTimeMs":59645,"avgCost":0.122},{"modelName":"Gemini 3 Flash","avgScore":84.4,"passRate":93.2,"avgTokens":63999,"avgTimeMs":29213,"avgCost":0.143},{"modelName":"Gemini 3 Pro Preview","avgScore":83.3,"passRate":93.3,"avgTokens":122975,"avgTimeMs":40000,"avgCost":1.72},{"modelName":"Claude Sonnet 4.5","avgScore":89.6,"passRate":99.3,"avgTokens":102000,"avgTimeMs":44100,"avgCost":1.163},{"modelName":"Claude Opus 4.5","avgScore":90.2,"passRate":101,"avgTokens":107958,"avgTimeMs":46156,"avgCost":2.052},{"modelName":"Claude Haiku 4.5","avgScore":90,"passRate":100.4,"avgTokens":133049,"avgTimeMs":22649,"avgCost":0.505},{"modelName":"DeepSeek v3.2","avgScore":89.2,"passRate":99.3,"avgTokens":90448,"avgTimeMs":94115,"avgCost":0.083},{"modelName":"OpenAI GPT-5.2","avgScore":89.8,"passRate":99.3,"avgTokens":80833,"avgTimeMs":29400,"avgCost":0.835},{"modelName":"GLM 4.7 Flash","avgScore":81.3,"passRate":86.7,"avgTokens":108333,"avgTimeMs":45000,"avgCost":0.185},{"modelName":"Grok 4 Fast","avgScore":89.8,"passRate":99.9,"avgTokens":86667,"avgTimeMs":73500,"avgCost":0.035},{"modelName":"Grok 4","avgScore":89,"passRate":98.8,"avgTokens":80000,"avgTimeMs":78750,"avgCost":0.912},{"modelName":"Grok 4.1 Fast","avgScore":87.8,"passRate":98.2,"avgTokens":96667,"avgTimeMs":92925,"avgCost":0.04},{"modelName":"Qwen3 Max","avgScore":88.6,"passRate":100,"avgTokens":158202,"avgTimeMs":45000,"avgCost":0.9}]},{"category":"code-evolution","models":[{"modelName":"GLM 4-Plus","avgScore":85.2,"passRate":95.9,"avgTokens":132351,"avgTimeMs":81779,"avgCost":0.155},{"modelName":"MiniMax M2.1","avgScore":84.4,"passRate":96.4,"avgTokens":463079,"avgTimeMs":140171,"avgCost":0.4},{"modelName":"GLM-4.7","avgScore":80.9,"passRate":82.6,"avgTokens":103912,"avgTimeMs":48284,"avgCost":0.122},{"modelName":"Gemini 3 Flash","avgScore":80.4,"passRate":89.2,"avgTokens":63999,"avgTimeMs":23649,"avgCost":0.143},{"modelName":"Gemini 3 Pro Preview","avgScore":89.4,"passRate":100,"avgTokens":122975,"avgTimeMs":40000,"avgCost":1.72},{"modelName":"Claude Sonnet 4.5","avgScore":85.6,"passRate":95.3,"avgTokens":102000,"avgTimeMs":35700,"avgCost":1.163},{"modelName":"Claude Opus 4.5","avgScore":86.2,"passRate":97,"avgTokens":107958,"avgTimeMs":37364,"avgCost":2.052},{"modelName":"Claude Haiku 4.5","avgScore":86,"passRate":96.4,"avgTokens":133049,"avgTimeMs":18335,"avgCost":0.505},{"modelName":"DeepSeek v3.2","avgScore":85.2,"passRate":95.3,"avgTokens":90448,"avgTimeMs":76188,"avgCost":0.083},{"modelName":"OpenAI GPT-5.2","avgScore":85.8,"passRate":95.3,"avgTokens":80833,"avgTimeMs":23800,"avgCost":0.835},{"modelName":"GLM 4.7 Flash","avgScore":86.9,"passRate":100,"avgTokens":108333,"avgTimeMs":45000,"avgCost":0.185},{"modelName":"Grok 4 Fast","avgScore":85.8,"passRate":95.9,"avgTokens":86667,"avgTimeMs":59500,"avgCost":0.035},{"modelName":"Grok 4","avgScore":85,"passRate":94.8,"avgTokens":80000,"avgTimeMs":63750,"avgCost":0.912},{"modelName":"Grok 4.1 Fast","avgScore":83.8,"passRate":94.2,"avgTokens":96667,"avgTimeMs":75225,"avgCost":0.04},{"modelName":"Qwen3 Max","avgScore":88.9,"passRate":100,"avgTokens":158202,"avgTimeMs":45000,"avgCost":0.9}]}],"categories":["saas-core","glue-code","ai-integration","frontend","api-integrations","code-evolution"],"models":["GLM 4-Plus","MiniMax M2.1","GLM-4.7","Gemini 3 Flash","Gemini 3 Pro Preview","Claude Sonnet 4.5","Claude Opus 4.5","Claude Haiku 4.5","DeepSeek v3.2","OpenAI GPT-5.2","GLM 4.7 Flash","Grok 4 Fast","Grok 4","Grok 4.1 Fast","Qwen3 Max"]}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"leaderboard":[{"rank":1,"agentName":"Claude Opus","agentVersion":"Opus-4.5","modelName":"Claude Opus 4.5","tasksCompleted":180,"passedTasks":180,"failedTasks":0,"avgScore":89.15,"avgFunctional":85,"avgVisual":80,"avgQuality":80,"avgSecurity":100,"avgCost":70,"avgSpeed":80,"totalTokens":647747,"inputTokens":194324,"outputTokens":453423,"totalCostUSD":12.31,"avgTimeMs":43958,"pricingInput":5,"pricingOutput":25,"lastUpdated":"2026-01-19T19:25:00.000Z"},{"rank":2,"agentName":"Claude Haiku","agentVersion":"Haiku-4.5","modelName":"Claude Haiku 4.5","tasksCompleted":180,"passedTasks":179,"failedTasks":1,"avgScore":88.97,"avgFunctional":84.53,"avgVisual":80,"avgQuality":79.56,"avgSecurity":100,"avgCost":88,"avgSpeed":95,"totalTokens":798291,"inputTokens":239487,"outputTokens":558804,"totalCostUSD":3.03,"avgTimeMs":21570,"pricingInput":1,"pricingOutput":5,"lastUpdated":"2026-01-20T15:21:00.000Z"},{"rank":3,"agentName":"Grok","agentVersion":"4-Fast","modelName":"Grok 4 Fast","tasksCompleted":180,"passedTasks":178,"failedTasks":2,"avgScore":88.8,"avgFunctional":84.1,"avgVisual":80,"avgQuality":80,"avgSecurity":100,"avgCost":94,"avgSpeed":72,"totalTokens":520000,"inputTokens":156000,"outputTokens":364000,"totalCostUSD":0.21,"avgTimeMs":70000,"pricingInput":0.2,"pricingOutput":0.5,"lastUpdated":"2026-01-20T18:30:00.000Z"},{"rank":4,"agentName":"OpenAI","agentVersion":"GPT-5.2","modelName":"OpenAI GPT-5.2","tasksCompleted":180,"passedTasks":177,"failedTasks":3,"avgScore":88.75,"avgFunctional":83.58,"avgVisual":80,"avgQuality":79.56,"avgSecurity":100,"avgCost":98,"avgSpeed":92,"totalTokens":485000,"inputTokens":145500,"outputTokens":339500,"totalCostUSD":5.01,"avgTimeMs":28000,"pricingInput":1.75,"pricingOutput":14,"lastUpdated":"2026-01-20T16:35:00.000Z"},{"rank":5,"agentName":"Qwen","agentVersion":"3-Max","modelName":"Qwen3 Max","tasksCompleted":180,"passedTasks":180,"failedTasks":0,"avgScore":88.6,"avgFunctional":85,"avgVisual":80,"avgQuality":80,"avgSecurity":100,"avgCost":90,"avgSpeed":75,"totalTokens":949212,"inputTokens":57101,"outputTokens":892111,"totalCostUSD":5.42,"avgTimeMs":45000,"pricingInput":1.2,"pricingOutput":6,"lastUpdated":"2026-01-21T19:30:00.000Z"},{"rank":6,"agentName":"Claude","agentVersion":"Sonnet-4.5","modelName":"Claude Sonnet 4.5","tasksCompleted":180,"passedTasks":177,"failedTasks":3,"avgScore":88.56,"avgFunctional":83.58,"avgVisual":80,"avgQuality":80,"avgSecurity":100,"avgCost":85,"avgSpeed":80,"totalTokens":612000,"inputTokens":183600,"outputTokens":428400,"totalCostUSD":6.98,"avgTimeMs":42000,"pricingInput":3,"pricingOutput":15,"lastUpdated":"2026-01-20T16:46:00.000Z"},{"rank":7,"agentName":"GLM-4","agentVersion":"GLM-4-Plus","modelName":"GLM 4-Plus","tasksCompleted":180,"passedTasks":178,"failedTasks":2,"avgScore":88.2,"avgFunctional":84.06,"avgVisual":80,"avgQuality":80,"avgSecurity":100,"avgCost":92,"avgSpeed":75,"totalTokens":794105,"inputTokens":238232,"outputTokens":555873,"totalCostUSD":0.93,"avgTimeMs":96210,"pricingInput":0.4,"pricingOutput":1.5,"lastUpdated":"2026-01-20T10:20:00.000Z"},{"rank":8,"agentName":"DeepSeek","agentVersion":"v3.2","modelName":"DeepSeek v3.2","tasksCompleted":180,"passedTasks":177,"failedTasks":3,"avgScore":88.19,"avgFunctional":83.58,"avgVisual":80,"avgQuality":80,"avgSecurity":100,"avgCost":96,"avgSpeed":65,"totalTokens":542685,"inputTokens":162806,"outputTokens":379879,"totalCostUSD":0.5,"avgTimeMs":89633,"pricingInput":0.3,"pricingOutput":1.2,"lastUpdated":"2026-01-19T19:44:00.000Z"},{"rank":9,"agentName":"Grok","agentVersion":"4","modelName":"Grok 4","tasksCompleted":180,"passedTasks":176,"failedTasks":4,"avgScore":88,"avgFunctional":83.6,"avgVisual":80,"avgQuality":80,"avgSecurity":100,"avgCost":94,"avgSpeed":70,"totalTokens":480000,"inputTokens":144000,"outputTokens":336000,"totalCostUSD":5.47,"avgTimeMs":75000,"pricingInput":3,"pricingOutput":15,"lastUpdated":"2026-01-20T18:37:00.000Z"},{"rank":10,"agentName":"MiniMax","agentVersion":"M2.1","modelName":"MiniMax M2.1","tasksCompleted":180,"passedTasks":179,"failedTasks":1,"avgScore":87.42,"avgFunctional":84.53,"avgVisual":80,"avgQuality":80,"avgSecurity":100,"avgCost":85,"avgSpeed":60,"totalTokens":2778476,"inputTokens":833543,"outputTokens":1944933,"totalCostUSD":2.4,"avgTimeMs":164907,"pricingInput":0.27,"pricingOutput":1.12,"lastUpdated":"2026-01-20T11:26:00.000Z"},{"rank":11,"agentName":"Grok","agentVersion":"4.1-Fast","modelName":"Grok 4.1 Fast","tasksCompleted":180,"passedTasks":175,"failedTasks":5,"avgScore":86.8,"avgFunctional":82.6,"avgVisual":80,"avgQuality":78.7,"avgSecurity":100,"avgCost":90,"avgSpeed":68,"totalTokens":580000,"inputTokens":174000,"outputTokens":406000,"totalCostUSD":0.24,"avgTimeMs":88500,"pricingInput":0.2,"pricingOutput":0.5,"lastUpdated":"2026-01-20T18:35:00.000Z"},{"rank":12,"agentName":"Gemini","agentVersion":"3-Pro-Preview","modelName":"Gemini 3 Pro Preview","tasksCompleted":180,"passedTasks":171,"failedTasks":9,"avgScore":85.8,"avgFunctional":80.8,"avgVisual":80,"avgQuality":77.3,"avgSecurity":100,"avgCost":94,"avgSpeed":88,"totalTokens":737849,"inputTokens":221566,"outputTokens":516283,"totalCostUSD":10.34,"avgTimeMs":32000,"pricingInput":2,"pricingOutput":12,"lastUpdated":"2026-01-21T18:45:00.000Z"},{"rank":13,"agentName":"GLM-4","agentVersion":"GLM-4.7","modelName":"GLM-4.7","tasksCompleted":180,"passedTasks":154,"failedTasks":26,"avgScore":83.9,"avgFunctional":72.72,"avgVisual":80,"avgQuality":79.56,"avgSecurity":100,"avgCost":94,"avgSpeed":82,"totalTokens":623474,"inputTokens":187042,"outputTokens":436432,"totalCostUSD":0.73,"avgTimeMs":56805,"pricingInput":0.4,"pricingOutput":1.5,"lastUpdated":"2026-01-20T10:20:00.000Z"},{"rank":14,"agentName":"GLM","agentVersion":"4.7-Flash","modelName":"GLM 4.7 Flash","tasksCompleted":180,"passedTasks":167,"failedTasks":13,"avgScore":83.83,"avgFunctional":78.86,"avgVisual":80,"avgQuality":79.56,"avgSecurity":100,"avgCost":92,"avgSpeed":75,"totalTokens":650000,"inputTokens":195000,"outputTokens":455000,"totalCostUSD":1.11,"avgTimeMs":45000,"pricingInput":0.07,"pricingOutput":0.4,"lastUpdated":"2026-01-21T17:30:00.000Z"},{"rank":15,"agentName":"Gemini","agentVersion":"3-Flash-Preview","modelName":"Gemini 3 Flash","tasksCompleted":180,"passedTasks":166,"failedTasks":14,"avgScore":83.44,"avgFunctional":78.39,"avgVisual":80,"avgQuality":75.11,"avgSecurity":100,"avgCost":95,"avgSpeed":90,"totalTokens":383991,"inputTokens":115197,"outputTokens":268794,"totalCostUSD":0.86,"avgTimeMs":27822,"pricingInput":0.5,"pricingOutput":3,"lastUpdated":"2026-01-20T07:29:00.000Z"}],"totalAgents":15,"lastUpdated":"2026-01-21T19:30:00.000Z","source":"mock"}
|