FrontierFinance - Coverage & Catalyst Monitoring: leaderboard
The 27 FrontierFinance queries on coverage and catalyst monitoring, 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 2029. 16 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Muse Wonder | 56.22 | #27 |
| 2 | Claude Fable 5.1 (High) | 53.72 | #14 (Claude Fable 5.1) |
| 3 | Muse Spark Open (xHigh) | 51.05 | #79 (Muse Spark Open) |
| 4 | Claude Fable 5 (High) | 49.01 | #26 (Claude Fable 5) |
| 5 | Ling-3.0-flash-fin | 48.24 | #289 |
| 6 | Kimi K3 (Max) | 46.87 | #53 (Kimi K3) |
| 7 | GPT-5.6 Sol (Medium) | 46.73 | #29 (GPT-5.6 Sol) |
| 8 | GLM-5.2 (Max) | 46.36 | #137 (GLM-5.2) |
| 9 | Claude Opus 5.5 (High) | 45.51 | #5 (Claude Opus 5.5) |
| 10 | Gemini 3.8 Flash (Medium) | 44.36 | #36 (Gemini 3.8 Flash) |
| 11 | Claude Opus 4.8 (High) | 43.19 | #56 (Claude Opus 4.8) |
| 12 | GPT-5.5 (Medium) | 41.51 | #48 (GPT-5.5) |
| 13 | DeepSeek V4 Pro (High) | 38.45 | #181 (DeepSeek V4 Pro) |
| 14 | Gemini 3.6 Flash (Medium) | 36.47 | #72 (Gemini 3.6 Flash) |
| 15 | Kimi K2.6 | 28.37 | #173 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #6 GPT-6 Astra.
Interactive version: theaggregate.ai/benchmark?slug=frontierfinance-coverage-catalyst-monitoring · How It Works · Data refreshed daily, snapshot 2026-11-12.