CorpFin v2: leaderboard
A private benchmark evaluating understanding of long-context credit agreements.
Metric: Accuracy (%). Source: www.vals.ai. Status: years away from saturation. 134 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 5 | 73.19 |
| 2 | Claude Fable 5 (Max) | 71.83 |
| 3 | Kimi K3 | 71.56 |
| 4 | Muse Spark 1.1 (xHigh) | 71.29 |
| 5 | Muse Spark 1.2 (xHigh) | 70.94 |
| 6 | Inkling Small | 69.62 |
| 7 | Inkling | 68.57 |
| 8 | Grok 4.3 | 68.53 |
| 9 | GPT-5.5 (xHigh) | 68.42 |
| 10 | Kimi K2.5 (Thinking) | 68.26 |
| 11 | MiniMax-M3 | 68.1 |
| 12 | Qwen 3 Max (2026-01-23) | 68.03 |
| 13 | Grok 4.5 (High) | 67.41 |
| 14 | Claude Opus 4.6 (Adaptive Reasoning, Max Effort) | 67.02 |
| 15 | Claude Sonnet 5 (Max) | 66.98 |
Interactive version: theaggregate.ai/benchmark?slug=corpfin-v2 · How It Works · Data refreshed daily, snapshot 2026-09-05.