FinFIRST - Source Verification: leaderboard
Metric: Weighted rubric score (%; the 2,085 rubric points for using authoritative, relevant and time-valid sources; 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 | 89.59 |
| 2 | GPT-5.6 Sol | 88.68 |
| 3 | Qwen 3.8 Flash | 83.36 |
| 4 | Ling-3.0-flash-fin | 82.45 |
| 5 | GLM-5.3 Flash | 80.77 |
| 6 | GLM-5.3 | 78.56 |
| 7 | Qwen 3.8 Max | 77.75 |
| 8 | Qwen 3.8 27B | 76.83 |
| 9 | DeepSeek V4 Pro (0813) | 73.57 |
| 10 | DeepSeek V4 Flash (0731) | 71.65 |
| 11 | Kimi K3 | 70.7 |
| 12 | GLM-5.2 | 68.3 |
| 13 | Gemini 3.7 Flash | 66.62 |
| 14 | MiniMax-M3 | 62.97 |
Interactive version: theaggregate.ai/benchmark?slug=finfirst-source-verification · How It Works · Data refreshed daily, snapshot 2026-09-26.