PostTrainBench
Can the model complete substantial programming work under this benchmark's agent setup?
Top rankings
One row per model, using its best reported score across effort settings.
| Rank | Model | Best score | Best reported setting |
|---|---|---|---|
| 1 | Claude Opus 4.7Anthropic | 0.42 | Reported configurationMiniMax report1 value · 1 reportJun 1, 2026 · source |
| 2 | GPT-5.5OpenAI | 0.39 | Reported configurationMiniMax report1 value · 1 reportJun 1, 2026 · source |
| 3 | MiniMax M3MiniMax | 0.37 | Reported configurationMiniMax report1 value · 1 reportJun 1, 2026 · source |
Effort curve
Every sourced cost-linked effort value for this exact version. Lines connect complete sweeps only.
Definition and comparison boundarypublic methodology
Can the model complete substantial programming work under this benchmark's agent setup?
Software implementation, debugging, or repository work under the published evaluation protocol. Higher is better. The value is a ratio on a 0–1 scale reported in this lab's table.
Harness, tools, prompts, attempt count, and benchmark version can materially change the result. Compare within one reporting context.
12-hour autonomous data-synthesis, training, evaluation, and iteration process across four base models and five component benchmarks.
Method / source