Code Migration - CLI
Code · 2026-06-16
The CLI split of Code Migration. This child benchmark separates a source-reported subtask or subtrack from the parent aggregate so scores at different grains do not share one benchmark_slug.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Sonnet 5.5 | 69.8 |
| Gemini 4 Argon | 67.6 |
| GPT-6 Astra | 67.5 |
| GPT-6.1 Sol | 63.5 |
| Muse Wonder | 60.1 |
| Muse Wonder Full | 58.0 |
| Claude Opus 5 | 53.3 |
| GPT-6 Sol | 52.9 |
| GPT-5.6 Sol | 47.2 |
| GPT-5.6 Terra | 40.4 |
| Muse Spark 1.3 | 40.4 |
| Opus 4.8 | 40.1 |
| Hy4 Preview | 39.9 |
| Grok 4.6 | 39.4 |
| DeepSeek V4.1 Flash | 37.5 |
| GPT-6 Luna | 37.2 |
| GPT-5.5 | 36.9 |
| Grok 4.7 | 36.4 |
| Sonnet 5 | 36.3 |
| Claude Haiku 5.5 | 36.1 |
| GPT-5.6 Luna | 36.1 |
| GLM-5.3 | 35.6 |
| DeepSeek V4.1 Flash 1017 | 35.6 |
| Opus 4.7 | 35.2 |
| MiMo-V2.6-Pro | 34.0 |
| DeepSeek V4 Pro 0813 | 32.1 |
| DeepSeek-V4-Flash-0731 | 32.0 |
| Step 5 Preview | 32.0 |
| MiMo-V2.6-Flash | 31.2 |
| Sonnet 4.6 | 30.3 |
| GLM-5.2 | 27.2 |
| Gemini 3.8 Flash | 25.9 |
| Grok 4.5 | 25.5 |
| GPT-5.4 | 23.8 |
| Gemini 3.7 Flash | 23.5 |
| Ember-1 | 23.3 |
| Gemini 3.6 Flash | 19.3 |
| GLM-5.1 | 18.8 |
| Muse Spark 1.1 | 18.6 |
| Kimi K2.6 | 18.0 |