FinChain — leaderboard
Financial chain-of-thought benchmark reporting ChainEval and lexical/semantic similarity metrics for general and finance-specific models.
Metric: ChainEval (self-reported). Source: benchmarklist.com. Status: saturation imminent. 25 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 58.65 |
| 2 | Claude Sonnet 4.5 | 58.22 |
| 3 | Claude Sonnet 4 | 58.18 |
| 4 | Gemini 2.5 Flash | 58.01 |
| 5 | Claude 3.7 Sonnet | 57.89 |
| 6 | GPT-5 Mini | 57.38 |
| 7 | GPT-4.1 Mini | 57.24 |
| 8 | GPT-5 | 57.07 |
| 9 | GPT-4.1 | 56.92 |
| 10 | DeepSeek V3.1 | 56.76 |
| 11 | Grok 4 Fast | 56.73 |
| 12 | DeepSeek V3.2 | 56.71 |
Interactive version: theaggregate.ai/benchmark?slug=finchain · How the rankings work · Data refreshed daily, snapshot 2026-07-22.