FinFIRST: leaderboard
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 December 2026. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 5 | 87.61 |
| 2 | GPT-5.6 Sol | 85.92 |
| 3 | Qwen 3.8 Flash | 81.23 |
| 4 | Kimi K3 | 80.83 |
| 5 | GLM-5.3 | 80.61 |
| 6 | Qwen 3.8 Max | 77.4 |
| 7 | Qwen 3.8 27B | 77.28 |
| 8 | Gemini 3.7 Flash | 76.75 |
| 9 | GLM-5.3 Flash | 76.64 |
| 10 | DeepSeek V4 Pro (0813) | 75.41 |
| 11 | Ling-3.0-flash-fin | 75.07 |
| 12 | DeepSeek V4 Flash (0731) | 71.37 |
| 13 | GLM-5.2 | 65.89 |
| 14 | MiniMax-M3 | 60.7 |
Interactive version: theaggregate.ai/benchmark?slug=finfirst · How It Works · Data refreshed daily, snapshot 2026-09-26.