AA-AnalystAgent: leaderboard
Artificial Analysis evaluates agents on data-analysis work. The published headline score, pass-at-one and pass-at-k rates are retained as separate measurements of task success.
Metric: Score (%). Source: artificialanalysis.ai. Saturation forecast: Around December 2027. 51 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.7 Flash (High) | 60 | #24 (Gemini 3.7 Flash) |
| 2 | Grok 4.7 (High) | 55 | #26 (Grok 4.7) |
| 3 | Claude Opus 5 (Max) | 53.75 | #16 (Claude Opus 5) |
| 4 | Claude Haiku 5.5 (Max) | 53.75 | #43 (Claude Haiku 5.5) |
| 5 | Grok 4.7 (xHigh) | 52.5 | #26 (Grok 4.7) |
| 6 | GPT-6 Astra (Max) | 51.25 | #6 (GPT-6 Astra) |
| 7 | GPT-5.5 (xHigh) | 50 | #33 (GPT-5.5) |
| 8 | GPT-6.1 Sol (Max) | 50 | #7 (GPT-6.1 Sol) |
| 9 | Gemini 4 Argon (High) | 48.75 | #9 (Gemini 4 Argon) |
| 10 | GPT-5.6 Sol (Max) | 47.5 | #22 (GPT-5.6 Sol) |
| 11 | Gemini 3.8 Flash (High) | 46.25 | #30 (Gemini 3.8 Flash) |
| 12 | Claude Sonnet 5 (Max) | 46.25 | #65 (Claude Sonnet 5) |
| 13 | Gemini 3.5 Flash (High) | 45 | #66 (Gemini 3.5 Flash) |
| 14 | Claude Opus 4.8 (Max) | 45 | #39 (Claude Opus 4.8) |
| 15 | Qwen 3.8 Max (0902) | 45 | #36 |
No result here: #3 Claude Opus 5.5, #10 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=aa-analystagent · How It Works · Data refreshed daily, snapshot 2026-11-05.