XpertBench - Finance: leaderboard
The finance tasks of XpertBench (2026), open-ended professional assignments written by domain experts and graded against typically 15 to 40 weighted expert rubric checkpoints per task. Weighted rubric score in percent on the finance part of the XpertBench-Gold subset, judged by Gemini 2.5 Pro; higher is better.
Metric: Weighted rubric score (%) on the XpertBench-Gold subset (245 expert-written open-ended professional tasks, 15-40 weighted binary checkpoints each); ShotJudge: Gemini 2.5 Pro judges every checkpoint with an expert-graded GPT-5 response as one-shot exemplar; finance tasks; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 14 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GPT-5.4 | High | 84.65 | #135 |
| 2 | Doubao-2.0-pro | 73.82 | #149 | |
| 3 | Claude Opus 4.6 | Thinking | 73.25 | #113 |
| 4 | GPT-5.2 | High | 71.22 | #185 |
| 5 | GPT-5 | High | 64.5 | #178 |
| 6 | Gemini 3 Pro | 62.96 | #145 | |
| 7 | Gemini 3.1 Pro (Preview) | 62.43 | #99 | |
| 8 | Gemini 3 Flash | 57.45 | #175 | |
| 9 | Kimi K2 (Thinking) | 55 | ||
| 10 | GLM-4.6 | 52.7 | #498 | |
| 11 | DeepSeek V3.1 Terminus | Thinking | 46.1 | #437 |
| 12 | Claude Sonnet 4.5 | Thinking | 44.5 | #261 |
| 13 | Doubao-Seed-1.6 | Thinking | 40.8 | |
| 14 | Gemini 2.5 Pro | 30.3 | #276 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=xpertbench-finance · How It Works · Data refreshed daily, snapshot 2026-11-21.