free-coding-models 0.1.40 → 0.1.42

package/README.md

@@ -199,23 +199,23 @@ free-coding-models
 
 ## 🤖 Coding Models
 
-**44 coding models** across 8 tiers, ranked by [Aider Polyglot benchmark](https://aider.chat/docs/leaderboards) (225 coding exercises across C++/Go/Java/JS/Python/Rust). Models without a confirmed Aider score are estimated from model family, size, and published release benchmarks.
-
-| Tier | Score | Count | Models |
-|------|-------|-------|--------|
-| **S+** | 75%+ | 7 | DeepSeek V3.1/Terminus, DeepSeek V3.2, Kimi K2.5, Devstral 2, Nemotron Ultra 253B, Mistral Large 675B |
-| **S**  | 62–74% | 7 | Qwen2.5 Coder 32B, GLM 5, Qwen3.5 400B VLM, Qwen3 Coder 480B, Qwen3 80B Thinking, Llama 3.1 405B, MiniMax M2.1 |
-| **A+** | 54–62% | 6 | Kimi K2 Thinking/Instruct, Qwen3 235B, Llama 3.3 70B, GLM 4.7, Qwen3 80B Instruct |
-| **A**  | 44–54% | 5 | MiniMax M2, Mistral Medium 3, Magistral Small, Nemotron Nano 30B, R1 Distill 32B |
-| **A-** | 36–44% | 5 | GPT OSS 120B, Nemotron Super 49B, Llama 4 Scout, R1 Distill 14B, Colosseum 355B |
-| **B+** | 25–36% | 5 | QwQ 32B, GPT OSS 20B, Stockmark 100B, Seed OSS 36B, Step 3.5 Flash |
-| **B**  | 14–25% | 5 | Llama 4 Maverick, Mixtral 8x22B, Ministral 14B, Granite 34B Code, R1 Distill 8B |
-| **C**  | <14%  | 4 | R1 Distill 7B, Gemma 2 9B, Phi 3.5 Mini, Phi 4 Mini |
+**44 coding models** across 8 tiers, ranked by [SWE-bench Verified](https://www.swebench.com) — the industry-standard benchmark measuring real GitHub issue resolution. Scores are self-reported by providers unless noted.
+
+| Tier | SWE-bench | Models |
+|------|-----------|--------|
+| **S+** ≥70% | GLM 5 (77.8%), Kimi K2.5 (76.8%), Step 3.5 Flash (74.4%), MiniMax M2.1 (74.0%), GLM 4.7 (73.8%), DeepSeek V3.2 (73.1%), Devstral 2 (72.2%), Kimi K2 Thinking (71.3%), Qwen3 Coder 480B (70.6%), Qwen3 235B (70.0%) |
+| **S** 60–70% | MiniMax M2 (69.4%), DeepSeek V3.1 Terminus (68.4%), Qwen3 80B Thinking (68.0%), Qwen3.5 400B (68.0%), Kimi K2 Instruct (65.8%), Qwen3 80B Instruct (65.0%), DeepSeek V3.1 (62.0%), Llama 4 Maverick (62.0%), GPT OSS 120B (60.0%) |
+| **A+** 50–60% | Mistral Large 675B (58.0%), Nemotron Ultra 253B (56.0%), Colosseum 355B (52.0%), QwQ 32B (50.0%) |
+| **A** 40–50% | Nemotron Super 49B (49.0%), Mistral Medium 3 (48.0%), Qwen2.5 Coder 32B (46.0%), Magistral Small (45.0%), Llama 4 Scout (44.0%), Llama 3.1 405B (44.0%), Nemotron Nano 30B (43.0%), R1 Distill 32B (43.9%), GPT OSS 20B (42.0%) |
+| **A-** 35–40% | Llama 3.3 70B (39.5%), Seed OSS 36B (38.0%), R1 Distill 14B (37.7%), Stockmark 100B (36.0%) |
+| **B+** 30–35% | Ministral 14B (34.0%), Mixtral 8x22B (32.0%), Granite 34B Code (30.0%) |
+| **B** 20–30% | R1 Distill 8B (28.2%), R1 Distill 7B (22.6%) |
+| **C** <20% | Gemma 2 9B (18.0%), Phi 4 Mini (14.0%), Phi 3.5 Mini (12.0%) |
 
 ### Tier scale
 
-- **S+/S** — Frontier coders, top Aider polyglot scores, best for complex refactors
-- **A+/A** — Excellent alternatives, strong at most coding tasks
+- **S+/S** — Elite frontier coders (≥60% SWE-bench), best for complex real-world tasks and refactors
+- **A+/A** — Great alternatives, strong at most coding tasks
 - **A-/B+** — Solid performers, good for targeted programming tasks
 - **B/C** — Lightweight or older models, good for code completion on constrained infra
 

package/bin/free-coding-models.js

@@ -411,11 +411,11 @@ function renderTable(results, pendingPings, frame, cursor = null, sortColumn = '
   // 📖 Add mode toggle hint
   const modeHint = chalk.dim.yellow(' (Z to toggle)')
 
-  // 📖 Tier filter badge shown when filtering is active
+  // 📖 Tier filter badge shown when filtering is active (shows exact tier name)
+  const TIER_CYCLE_NAMES = [null, 'S+', 'S', 'A+', 'A', 'A-', 'B+', 'B', 'C']
   let tierBadge = ''
   if (tierFilterMode > 0) {
-    const tierNames = ['All', 'S+/S', 'A+/A/A-', 'B+/B', 'C']
-    tierBadge = chalk.bold.rgb(255, 200, 0)(` [${tierNames[tierFilterMode]}]`)
+    tierBadge = chalk.bold.rgb(255, 200, 0)(` [${TIER_CYCLE_NAMES[tierFilterMode]}]`)
   }
 
   // 📖 Column widths (generous spacing with margins)
@@ -665,7 +665,7 @@ function renderTable(results, pendingPings, frame, cursor = null, sortColumn = '
       : chalk.rgb(0, 200, 255)('Enter→OpenCode')
   lines.push(chalk.dim(`  ↑↓ Navigate  •  `) + actionHint + chalk.dim(`  •  R/T/O/M/L/A/S/C/H/V/U Sort  •  W↓/X↑ Interval (${intervalSec}s)  •  T Tier  •  Z Mode  •  Ctrl+C Exit`))
   lines.push('')
-  lines.push(chalk.dim('  Made with ') + '💖 & ☕' + chalk.dim(' by ') + '\x1b]8;;https://github.com/vava-nessa\x1b\\vava-nessa\x1b]8;;\x1b\\' + chalk.dim('  •  ') + '💬 ' + chalk.cyanBright('\x1b]8;;https://discord.gg/WKA3TwYVuZ\x1b\\Join Free-Coding-Models Discord!\x1b]8;;\x1b\\') + chalk.dim('  •  ') + '⭐ ' + '\x1b]8;;https://github.com/vava-nessa/free-coding-models\x1b\\Read the docs on GitHub\x1b]8;;\x1b\\')
+  lines.push(chalk.dim('  Made with ') + '💖 & ☕' + chalk.dim(' by ') + '\x1b]8;;https://github.com/vava-nessa\x1b\\vava-nessa\x1b]8;;\x1b\\' + chalk.dim('  •  ') + '🫂 ' + chalk.cyanBright('\x1b]8;;https://discord.gg/WKA3TwYVuZ\x1b\\Join our Discord!\x1b]8;;\x1b\\') + chalk.dim('  •  ') + '⭐ ' + '\x1b]8;;https://github.com/vava-nessa/free-coding-models\x1b\\Read the docs on GitHub\x1b]8;;\x1b\\')
   lines.push('')
   // 📖 Append \x1b[K (erase to EOL) to each line so leftover chars from previous
   // 📖 frames are cleared. Then pad with blank cleared lines to fill the terminal,
@@ -1296,29 +1296,15 @@ async function main() {
   process.on('SIGINT',  () => exit(0))
   process.on('SIGTERM', () => exit(0))
 
-  // 📖 Tier filtering system - cycles through filter modes
-  let tierFilterMode = 0 // 0=all, 1=S+/S, 2=A+/A/A-, 3=B+/B, 4=C
+  // 📖 Tier filtering system - cycles through each individual tier one by one
+  // 📖 0=All, 1=S+, 2=S, 3=A+, 4=A, 5=A-, 6=B+, 7=B, 8=C
+  const TIER_CYCLE = [null, 'S+', 'S', 'A+', 'A', 'A-', 'B+', 'B', 'C']
+  let tierFilterMode = 0
   function applyTierFilter() {
+    const activeTier = TIER_CYCLE[tierFilterMode]
     state.results.forEach(r => {
-      switch (tierFilterMode) {
-        case 0: // All tiers visible
-          r.hidden = false
-          break
-        case 1: // S+ and S only
-          r.hidden = !(r.tier === 'S+' || r.tier === 'S')
-          break
-        case 2: // A+, A, A- only
-          r.hidden = !(r.tier === 'A+' || r.tier === 'A' || r.tier === 'A-')
-          break
-        case 3: // B+ and B only
-          r.hidden = !(r.tier === 'B+' || r.tier === 'B')
-          break
-        case 4: // C only
-          r.hidden = r.tier !== 'C'
-          break
-      }
+      r.hidden = activeTier !== null && r.tier !== activeTier
     })
-    
     return state.results
   }
 
@@ -1359,9 +1345,9 @@ async function main() {
       state.pingInterval = Math.min(60000, state.pingInterval + 1000)
     }
 
-    // 📖 Tier toggle key: T = cycle through tier filters (all → S+/S → A+/A/A- → B+/B → C → all)
+    // 📖 Tier toggle key: T = cycle through each individual tier (All → S+ → S → A+ → A → A- → B+ → B → C → All)
     if (key.name === 't') {
-      tierFilterMode = (tierFilterMode + 1) % 5
+      tierFilterMode = (tierFilterMode + 1) % TIER_CYCLE.length
       applyTierFilter()
       adjustScrollOffset(state)
       return

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "free-coding-models",
-  "version": "0.1.40",
+  "version": "0.1.42",
   "description": "Find the fastest coding LLM models in seconds — ping free models from multiple providers, pick the best one for OpenCode, Cursor, or any AI coding assistant.",
   "keywords": [
     "nvidia",

package/sources.js

@@ -8,9 +8,9 @@
  *   - model_id: The model identifier for API calls
  *   - display_label: Human-friendly name for display
  *   - tier: Performance tier (S+, S, A+, A, A-, B+, B, C)
- *   - swe_score: SWE-bench Verified score percentage
+ *   - swe_score: SWE-bench Verified score percentage (self-reported by model provider)
  *   - ctx: Context window size in tokens (e.g., "128k", "32k")
- *   
+ *
  *   Add new sources here to support additional providers beyond NIM.
  *
  *   🎯 Tier scale (based on SWE-bench Verified):
@@ -18,12 +18,14 @@
  *   - S:  60-70% (excellent)
  *   - A+: 50-60% (great)
  *   - A:  40-50% (good)
- *   - A-: 35-45% (decent)
- *   - B+: 30-40% (average)
+ *   - A-: 35-40% (decent)
+ *   - B+: 30-35% (average)
  *   - B:  20-30% (below average)
  *   - C:  <20% (lightweight/edge)
  *
- *   📖 Source: https://www.swebench.com
+ *   📖 Source: https://www.swebench.com — scores are self-reported unless noted
+ *   📖 Secondary: https://swe-rebench.com (independent evals, scores are lower)
+ *   📖 Leaderboard tracker: https://www.marc0.dev/en/leaderboard
  *
  *   @exports Object containing all sources and their models
  */
@@ -31,57 +33,57 @@
 // 📖 NIM source - https://build.nvidia.com
 export const nvidiaNim = [
   // ── S+ tier — SWE-bench Verified ≥70% ──
-  ['deepseek-ai/deepseek-v3.1',                    'DeepSeek V3.1',       'S+', '49.2%', '128k'],
-  ['deepseek-ai/deepseek-v3.1-terminus',           'DeepSeek V3.1 Term',  'S+', '49.2%', '128k'],
   ['deepseek-ai/deepseek-v3.2',                    'DeepSeek V3.2',       'S+', '73.1%', '128k'],
   ['moonshotai/kimi-k2.5',                         'Kimi K2.5',           'S+', '76.8%', '128k'],
-  ['mistralai/devstral-2-123b-instruct-2512',      'Devstral 2 123B',     'S+', '62.0%', '128k'],
-  ['nvidia/llama-3.1-nemotron-ultra-253b-v1',      'Nemotron Ultra 253B', 'S+', '56.0%', '128k'],
-  ['mistralai/mistral-large-3-675b-instruct-2512', 'Mistral Large 675B',  'S+', '58.0%', '128k'],
-  // ── S tier — SWE-bench Verified 50–70% ──
-  ['qwen/qwen2.5-coder-32b-instruct',              'Qwen2.5 Coder 32B',   'S', '46.0%', '32k'],
-  ['z-ai/glm5',                                    'GLM 5',               'S', '77.8%', '128k'],
-  ['qwen/qwen3.5-397b-a17b',                       'Qwen3.5 400B VLM',    'S', '68.0%', '128k'],
-  ['qwen/qwen3-coder-480b-a35b-instruct',          'Qwen3 Coder 480B',    'S', '72.0%', '128k'],
-  ['qwen/qwen3-next-80b-a3b-thinking',             'Qwen3 80B Thinking',  'S', '68.0%', '128k'],
-  ['meta/llama-3.1-405b-instruct',                 'Llama 3.1 405B',      'S', '44.0%', '128k'],
-  ['minimaxai/minimax-m2.1',                       'MiniMax M2.1',        'S', '70.0%', '128k'],
-  // ── A+ tier — SWE-bench Verified 60–70% ──
-  ['moonshotai/kimi-k2-thinking',                  'Kimi K2 Thinking',    'A+', '67.0%', '128k'],
-  ['moonshotai/kimi-k2-instruct',                  'Kimi K2 Instruct',    'A+', '65.8%', '128k'],
-  ['qwen/qwen3-235b-a22b',                         'Qwen3 235B',          'A+', '70.0%', '128k'],
-  ['meta/llama-3.3-70b-instruct',                  'Llama 3.3 70B',       'A+', '39.5%', '128k'],
-  ['z-ai/glm4.7',                                  'GLM 4.7',             'A+', '73.8%', '128k'],
-  ['qwen/qwen3-next-80b-a3b-instruct',             'Qwen3 80B Instruct',  'A+', '65.0%', '128k'],
-  // ── A tier — SWE-bench Verified 45–60% ──
-  ['minimaxai/minimax-m2',                         'MiniMax M2',          'A', '56.5%', '128k'],
-  ['mistralai/mistral-medium-3-instruct',          'Mistral Medium 3',    'A', '48.0%', '128k'],
-  ['mistralai/magistral-small-2506',               'Magistral Small',     'A', '45.0%', '32k'],
-  ['nvidia/nemotron-3-nano-30b-a3b',               'Nemotron Nano 30B',   'A', '43.0%', '128k'],
-  ['deepseek-ai/deepseek-r1-distill-qwen-32b',     'R1 Distill 32B',      'A', '43.9%', '128k'],
-  // ── A- tier — SWE-bench Verified 35–45% ──
-  ['openai/gpt-oss-120b',                          'GPT OSS 120B',        'A-', '60.0%', '128k'],
-  ['nvidia/llama-3.3-nemotron-super-49b-v1.5',     'Nemotron Super 49B',  'A-', '49.0%', '128k'],
-  ['meta/llama-4-scout-17b-16e-instruct',          'Llama 4 Scout',       'A-', '44.0%', '128k'],
+  ['z-ai/glm5',                                    'GLM 5',               'S+', '77.8%', '128k'],
+  ['z-ai/glm4.7',                                  'GLM 4.7',             'S+', '73.8%', '200k'],
+  ['moonshotai/kimi-k2-thinking',                  'Kimi K2 Thinking',    'S+', '71.3%', '256k'],
+  ['minimaxai/minimax-m2.1',                       'MiniMax M2.1',        'S+', '74.0%', '200k'],
+  ['stepfun-ai/step-3.5-flash',                    'Step 3.5 Flash',      'S+', '74.4%', '256k'],
+  ['qwen/qwen3-coder-480b-a35b-instruct',          'Qwen3 Coder 480B',    'S+', '70.6%', '256k'],
+  ['qwen/qwen3-235b-a22b',                         'Qwen3 235B',          'S+', '70.0%', '128k'],
+  ['mistralai/devstral-2-123b-instruct-2512',      'Devstral 2 123B',     'S+', '72.2%', '256k'],
+  // ── S tier — SWE-bench Verified 60–70% ──
+  ['deepseek-ai/deepseek-v3.1-terminus',           'DeepSeek V3.1 Term',  'S',  '68.4%', '128k'],
+  ['moonshotai/kimi-k2-instruct',                  'Kimi K2 Instruct',    'S',  '65.8%', '128k'],
+  ['minimaxai/minimax-m2',                         'MiniMax M2',          'S',  '69.4%', '128k'],
+  ['qwen/qwen3-next-80b-a3b-thinking',             'Qwen3 80B Thinking',  'S',  '68.0%', '128k'],
+  ['qwen/qwen3-next-80b-a3b-instruct',             'Qwen3 80B Instruct',  'S',  '65.0%', '128k'],
+  ['qwen/qwen3.5-397b-a17b',                       'Qwen3.5 400B VLM',    'S',  '68.0%', '128k'],
+  ['openai/gpt-oss-120b',                          'GPT OSS 120B',        'S',  '60.0%', '128k'],
+  ['meta/llama-4-maverick-17b-128e-instruct',      'Llama 4 Maverick',    'S',  '62.0%', '1M'],
+  ['deepseek-ai/deepseek-v3.1',                    'DeepSeek V3.1',       'S',  '62.0%', '128k'],
+  // ── A+ tier — SWE-bench Verified 50–60% ──
+  ['nvidia/llama-3.1-nemotron-ultra-253b-v1',      'Nemotron Ultra 253B', 'A+', '56.0%', '128k'],
+  ['mistralai/mistral-large-3-675b-instruct-2512', 'Mistral Large 675B',  'A+', '58.0%', '256k'],
+  ['qwen/qwq-32b',                                 'QwQ 32B',             'A+', '50.0%', '131k'],
+  ['igenius/colosseum_355b_instruct_16k',          'Colosseum 355B',      'A+', '52.0%', '16k'],
+  // ── A tier — SWE-bench Verified 40–50% ──
+  ['mistralai/mistral-medium-3-instruct',          'Mistral Medium 3',    'A',  '48.0%', '128k'],
+  ['mistralai/magistral-small-2506',               'Magistral Small',     'A',  '45.0%', '32k'],
+  ['nvidia/llama-3.3-nemotron-super-49b-v1.5',     'Nemotron Super 49B',  'A',  '49.0%', '128k'],
+  ['meta/llama-4-scout-17b-16e-instruct',          'Llama 4 Scout',       'A',  '44.0%', '10M'],
+  ['nvidia/nemotron-3-nano-30b-a3b',               'Nemotron Nano 30B',   'A',  '43.0%', '128k'],
+  ['deepseek-ai/deepseek-r1-distill-qwen-32b',     'R1 Distill 32B',      'A',  '43.9%', '128k'],
+  ['openai/gpt-oss-20b',                           'GPT OSS 20B',         'A',  '42.0%', '128k'],
+  ['qwen/qwen2.5-coder-32b-instruct',              'Qwen2.5 Coder 32B',   'A',  '46.0%', '32k'],
+  ['meta/llama-3.1-405b-instruct',                 'Llama 3.1 405B',      'A',  '44.0%', '128k'],
+  // ── A- tier — SWE-bench Verified 35–40% ──
+  ['meta/llama-3.3-70b-instruct',                  'Llama 3.3 70B',       'A-', '39.5%', '128k'],
   ['deepseek-ai/deepseek-r1-distill-qwen-14b',     'R1 Distill 14B',      'A-', '37.7%', '64k'],
-  ['igenius/colosseum_355b_instruct_16k',          'Colosseum 355B',      'A-', '52.0%', '16k'],
-  // ── B+ tier — SWE-bench Verified 30–40% ──
-  ['qwen/qwq-32b',                                 'QwQ 32B',            'B+', '50.0%', '32k'],
-  ['openai/gpt-oss-20b',                           'GPT OSS 20B',        'B+', '42.0%', '32k'],
-  ['stockmark/stockmark-2-100b-instruct',          'Stockmark 100B',     'B+', '36.0%', '32k'],
-  ['bytedance/seed-oss-36b-instruct',              'Seed OSS 36B',       'B+', '38.0%', '32k'],
-  ['stepfun-ai/step-3.5-flash',                    'Step 3.5 Flash',      'B+', '74.4%', '32k'],
-  // ── B tier — SWE-bench Verified 20–35% ──
-  ['meta/llama-4-maverick-17b-128e-instruct',      'Llama 4 Maverick',    'B', '62.0%', '128k'],
-  ['mistralai/mixtral-8x22b-instruct-v0.1',        'Mixtral 8x22B',       'B', '32.0%', '64k'],
-  ['mistralai/ministral-14b-instruct-2512',        'Ministral 14B',       'B', '34.0%', '32k'],
-  ['ibm/granite-34b-code-instruct',                'Granite 34B Code',    'B', '30.0%', '32k'],
-  ['deepseek-ai/deepseek-r1-distill-llama-8b',     'R1 Distill 8B',       'B', '28.2%', '32k'],
-  // ── C tier — SWE-bench Verified <25% or lightweight edge models ──
-  ['deepseek-ai/deepseek-r1-distill-qwen-7b',      'R1 Distill 7B',       'C', '22.6%', '32k'],
-  ['google/gemma-2-9b-it',                         'Gemma 2 9B',          'C', '18.0%', '8k'],
-  ['microsoft/phi-3.5-mini-instruct',              'Phi 3.5 Mini',        'C', '12.0%', '128k'],
-  ['microsoft/phi-4-mini-instruct',                'Phi 4 Mini',          'C', '14.0%', '128k'],
+  ['bytedance/seed-oss-36b-instruct',              'Seed OSS 36B',        'A-', '38.0%', '32k'],
+  ['stockmark/stockmark-2-100b-instruct',          'Stockmark 100B',      'A-', '36.0%', '32k'],
+  // ── B+ tier — SWE-bench Verified 30–35% ──
+  ['mistralai/mixtral-8x22b-instruct-v0.1',        'Mixtral 8x22B',       'B+', '32.0%', '64k'],
+  ['mistralai/ministral-14b-instruct-2512',        'Ministral 14B',       'B+', '34.0%', '32k'],
+  ['ibm/granite-34b-code-instruct',                'Granite 34B Code',    'B+', '30.0%', '32k'],
+  // ── B tier — SWE-bench Verified 20–30% ──
+  ['deepseek-ai/deepseek-r1-distill-llama-8b',     'R1 Distill 8B',       'B',  '28.2%', '32k'],
+  ['deepseek-ai/deepseek-r1-distill-qwen-7b',      'R1 Distill 7B',       'B',  '22.6%', '32k'],
+  // ── C tier — SWE-bench Verified <20% or lightweight edge models ──
+  ['google/gemma-2-9b-it',                         'Gemma 2 9B',          'C',  '18.0%', '8k'],
+  ['microsoft/phi-3.5-mini-instruct',              'Phi 3.5 Mini',        'C',  '12.0%', '128k'],
+  ['microsoft/phi-4-mini-instruct',                'Phi 4 Mini',          'C',  '14.0%', '128k'],
 ]
 
 // 📖 All sources combined - used by the main script