FinFIRST - Raw-Information Acquisition: leaderboard
The raw-information acquisition rubric of FinFIRST (Wang et al., 2026): the percentage of rubric points for retrieving the correct values for the required entity, period, unit, definition and data version in expert-authored financial research questions. 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 (%; the 7,322 rubric points for retrieving the correct values for the required entity, period, unit, definition and data version; 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: Estimated already saturated. 15 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5 | 88.98 | #20 |
| 2 | GPT-5.6 Sol | 86.85 | #29 |
| 3 | Kimi K3 | 84.84 | #53 |
| 4 | Qwen 3.8 Flash | 84.29 | #109 |
| 5 | GLM-5.3 | 83.11 | #62 |
| 6 | Qwen 3.8 27B | 81.49 | #199 |
| 7 | Gemini 3.7 Flash | 81.19 | #32 |
| 8 | Qwen 3.8 Max | 80.33 | #55 |
| 9 | DeepSeek V4 Pro (0813) | 80.09 | #81 |
| 10 | GLM-5.3 Flash | 79.5 | #119 |
| 11 | Ling-3.0-flash-fin | 78.43 | #289 |
| 12 | DeepSeek V4 Flash (0731) | 77.49 | #136 |
| 13 | GLM-5.2 | 69.75 | #137 |
| 14 | MiniMax-M3 | 65.51 | #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-raw-information-acquisition · How It Works · Data refreshed daily, snapshot 2026-11-12.