FinFIRST: leaderboard
FinFIRST (Wang et al., 2026) evaluates financial search agents on 123 expert-authored Chinese and English research questions that need time-valid facts from authoritative sources plus calculations, scored with expert-weighted atomic rubric criteria. The score is the percentage of rubric points satisfied. Every model runs in the same ReAct harness with web search, page visit and Python tools, and a GLM-5.1 judge checks each criterion; higher is better.
Metric: Weighted rubric score (%; Loose Pass, share of the 12,300 expert-weighted rubric points satisfied; 123 expert-authored bilingual financial research tasks, each scored against expert atomic rubric criteria (701 in all, weights summing to 100 per task) by a GLM-5.1 judge validated against finance experts (Cohen kappa 0.816); all models run in the same ReAct harness with web search, page visit and Python tools, temperature 1.0, one run; missing outputs count as failed). Source: arxiv.org. Saturation forecast: Around February 2027. 15 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5 | 87.61 | #20 |
| 2 | GPT-5.6 Sol | 85.92 | #29 |
| 3 | Qwen 3.8 Flash | 81.23 | #109 |
| 4 | Kimi K3 | 80.83 | #53 |
| 5 | GLM-5.3 | 80.61 | #62 |
| 6 | Qwen 3.8 Max | 77.4 | #55 |
| 7 | Qwen 3.8 27B | 77.28 | #199 |
| 8 | Gemini 3.7 Flash | 76.75 | #32 |
| 9 | GLM-5.3 Flash | 76.64 | #119 |
| 10 | DeepSeek V4 Pro (0813) | 75.41 | #81 |
| 11 | Ling-3.0-flash-fin | 75.07 | #289 |
| 12 | DeepSeek V4 Flash (0731) | 71.37 | #136 |
| 13 | GLM-5.2 | 65.89 | #137 |
| 14 | MiniMax-M3 | 60.7 | #265 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=finfirst · How It Works · Data refreshed daily, snapshot 2026-11-12.