CorpFin v2 - Max Fitting Context
Professional Work · 2025-01-27
The Max Fitting Context split of CorpFin v2. 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 Fable 5 | 77.0 |
| Claude Opus 5 | 76.0 |
| Muse Spark 1.1 | 74.4 |
| Kimi K3 | 72.7 |
| Qwen3 Max Thinking (2026-01-23) | 70.6 |
| Inkling-Small | 70.4 |
| GPT-5.5 | 70.0 |
| Opus 4.8 | 69.8 |
| MiniMax M3 | 69.7 |
| Sonnet 5 | 69.1 |
| Grok 4.3 | 68.8 |
| GLM-5.2 | 68.4 |
| Kimi K2.5 | 68.4 |
| Qwen3.6-Max-Preview | 68.2 |
| Opus 4.7 | 67.8 |
| Inkling | 67.6 |
| Grok 4.5 | 67.5 |
| Kimi K2.6 | 67.2 |
| Qwen3.5 Plus (2026-02-15) | 67.2 |
| Opus 4.6 | 67.1 |
| Nemotron 3 Ultra 550B A55B | 67.1 |
| Gemini 3 Pro Preview | 67.0 |
| Gemini 3.1 Pro Preview | 66.9 |
| Gemini 3.5 Flash | 66.7 |
| GLM-5.1 | 66.3 |
| GPT-5.6 Terra | 66.3 |
| Sonnet 4.6 | 66.1 |
| Qwen3.5-Flash | 65.7 |
| Qwen3.7-Max | 65.7 |
| Opus 4.5 | 65.6 |
| Gemini 3.6 Flash | 65.4 |
| GPT-5.6 Sol | 65.2 |
| GPT-5.4 | 64.9 |
| Qwen3.6 27B | 64.9 |
| Grok 4.1 Fast | 64.8 |
| GPT-5.6 Luna | 64.1 |
| GPT-5.2 | 63.9 |
| Mistral Large 3 675B Instruct 2512 | 63.8 |
| Gemini 3 Flash Preview | 63.5 |
| GPT-5.1 | 63.4 |