FrontierFinance - Earnings & Events: leaderboard
The 36 FrontierFinance queries on earnings results and corporate events, answered in the Finance Agent v2 harness. Graded against expert rubric items by a three-judge majority vote; the score is the mean per-query share of rubric items satisfied (%), and higher is better.
Metric: Rubric qualification rate (%, macro average over queries, three-judge majority vote). Source: research.samaya.ai. Saturation forecast: Around March 2028. 16 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Fable 5.1 (High) | 71.22 | #14 (Claude Fable 5.1) |
| 2 | Muse Spark Open (xHigh) | 70.53 | #79 (Muse Spark Open) |
| 3 | Claude Opus 5.5 (High) | 66.37 | #5 (Claude Opus 5.5) |
| 4 | Muse Wonder | 65.95 | #27 |
| 5 | Claude Fable 5 (High) | 63.91 | #26 (Claude Fable 5) |
| 6 | Ling-3.0-flash-fin | 61.33 | #289 |
| 7 | Gemini 3.8 Flash (Medium) | 61.18 | #36 (Gemini 3.8 Flash) |
| 8 | Kimi K3 (Max) | 60.98 | #53 (Kimi K3) |
| 9 | GPT-5.6 Sol (Medium) | 58.03 | #29 (GPT-5.6 Sol) |
| 10 | Claude Opus 4.8 (High) | 57.7 | #56 (Claude Opus 4.8) |
| 11 | DeepSeek V4 Pro (High) | 54.51 | #181 (DeepSeek V4 Pro) |
| 12 | Gemini 3.6 Flash (Medium) | 54.05 | #72 (Gemini 3.6 Flash) |
| 13 | GPT-5.5 (Medium) | 53.7 | #48 (GPT-5.5) |
| 14 | GLM-5.2 (Max) | 51.97 | #137 (GLM-5.2) |
| 15 | Kimi K2.6 | 50.39 | #173 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #6 GPT-6 Astra.
Interactive version: theaggregate.ai/benchmark?slug=frontierfinance-earnings-events · How It Works · Data refreshed daily, snapshot 2026-11-12.