Code Migration - COBOL
Code · 2026-06-16
The COBOL 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 Haiku 5.5 | 70.0 |
| Opus 4.7 | 70.0 |
| Claude Opus 5 | 70.0 |
| Claude Sonnet 5.5 | 70.0 |
| DeepSeek V4.1 Flash 1017 | 70.0 |
| DeepSeek V4.1 Flash | 70.0 |
| DeepSeek V4 Pro 0813 | 70.0 |
| Gemini 4 Argon | 70.0 |
| GLM-5.2 | 70.0 |
| GLM-5.3 | 70.0 |
| GPT-5.5 | 70.0 |
| GPT-5.6 Luna | 70.0 |
| GPT-5.6 Sol | 70.0 |
| GPT-5.6 Terra | 70.0 |
| GPT-6.1 Sol | 70.0 |
| GPT-6 Sol | 70.0 |
| Grok 4.5 | 70.0 |
| Grok 4.7 | 70.0 |
| Hy4 Preview | 70.0 |
| MiMo-V2.6-Flash | 70.0 |
| MiMo-V2.6-Pro | 70.0 |
| Mistral Large 4 Preview | 70.0 |
| Muse Wonder Full | 70.0 |
| Muse Wonder | 70.0 |
| Opus 4.8 | 68.6 |
| Sonnet 4.6 | 68.6 |
| Sonnet 5 | 68.6 |
| Gemini 3.7 Flash | 68.6 |
| Gemini 3.8 Flash | 68.6 |
| GPT-5.4 | 68.6 |
| GPT-6 Astra | 68.6 |
| Muse Spark 1.1 | 68.6 |
| Muse Spark 1.2 | 68.6 |
| Muse Spark 1.3 | 68.6 |
| Gemini 3.6 Flash | 65.7 |
| Kimi K2.7 Code | 61.3 |
| Ember-1 | 60.0 |
| GLM-5.3 Flash | 60.0 |
| Grok 4.6 | 60.0 |
| Kimi K3 | 60.0 |