nex-code 0.3.59 → 0.3.61
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/README.md +5 -1
- package/dist/nex-code.js +150 -150
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -118,7 +118,11 @@ Rankings are based on nex-code's own `/benchmark` — 15 tool-calling tasks agai
|
|
|
118
118
|
|
|
119
119
|
| Rank | Model | Score | Avg Latency | Context | Best For |
|
|
120
120
|
|---|---|---|---|---|---|
|
|
121
|
-
|
|
121
|
+
| 🥇 | `devstral-2:123b` | **84** | 1.5s | 131K | Default — fastest + most reliable tool selection |
|
|
122
|
+
| 🥈 | `qwen3-coder:480b` | 79 | 2.9s | 131K | Coding-heavy sessions, heavy sub-agents |
|
|
123
|
+
| 🥉 | `kimi-k2:1t` | 79 | 2.7s | 256K | Large repos (>100K tokens) |
|
|
124
|
+
| — | `minimax-m2.7:cloud` | 73 | 3.5s | 200K | Complex swarm / multi-agent sessions (Toolathon SOTA) |
|
|
125
|
+
| — | `devstral-small-2:24b` | 73 | 1.0s | 131K | Fast sub-agents, simple lookups |
|
|
122
126
|
|
|
123
127
|
> Rankings are nex-code-specific: tool name accuracy, argument validity, schema compliance.
|
|
124
128
|
> Toolathon (Minimax SOTA) measures different task types — run `/benchmark --discover` after model releases.
|