AA-AnalystAgent - Pass@1: leaderboard
Metric: Pass@1 (%). Source: artificialanalysis.ai. 33 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.7 Flash (High) | 70.5 |
| 2 | GPT-5.5 (xHigh) | 66.25 |
| 3 | Gemini 3.1 Pro (Preview) | 64 |
| 4 | Claude Opus 5 (Adaptive Reasoning, Max Effort) | 63.75 |
| 5 | Claude Opus 4.8 (Adaptive Reasoning, Max Effort) | 63.5 |
| 6 | Claude Sonnet 5 (Adaptive Reasoning, Max Effort) | 61.5 |
| 7 | GPT-5.6 Sol (Max) | 61.25 |
| 8 | Grok 4.6 (High) | 60.75 |
| 9 | GPT-6 (Max) | 60 |
| 10 | Claude Opus 4.7 (Adaptive Reasoning, Max Effort) | 59.5 |
| 11 | Gemini 3.5 Flash (High) | 58.5 |
| 12 | Kimi K3 (Max) | 57.75 |
| 13 | Inkling Small | 57 |
| 14 | Grok 4.5 (High) | 54 |
| 15 | Inkling (xHigh) | 52.25 |
Interactive version: theaggregate.ai/benchmark?slug=aa-analystagent-pass-1 · How It Works · Data refreshed daily, snapshot 2026-09-19.