DAYJOB: Data Science: leaderboard
Long-horizon data-science assignments from a brief request and a workspace of files, graded by an agent judge against an expert rubric; the score is the share of attempts meeting at least 95% of criteria. Surge AI supplied these results before publishing the board and has not stated the task count.
Metric: Attempts meeting at least 95% of rubric criteria (%). Source: fireworks.ai. Saturation forecast: Around October 2027. 16 models tracked. Updated 16 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Opus 5.5 | Max | 37.3 | #5 |
| 2 | Claude Sonnet 5.5 | Max | 35.3 | #19 |
| 3 | Claude Fable 5.1 | Max | 26 | #15 |
| 4 | Gemini 4 Argon | High | 23.3 | #12 |
| 5 | GPT-6 Astra | Max | 21.3 | #6 |
| 6 | GPT-6.1 Sol | Max | 18.7 | #10 |
| 7 | Muse Wonder | Max | 16.7 | #28 |
| 8 | Qwen 3.8 Max | xHigh | 7.3 | #59 |
| 9 | Grok 4.7 | xHigh | 6.7 | #47 |
| 10 | Muse Spark 1.3 | Max | 6 | #43 |
| 11 | Kimi K3.1 Pro | 4.7 | #29 | |
| 12 | GLM-5.3 | Max | 4 | #68 |
| 13 | DeepSeek V4.1 Flash (1017) | Max | 3.3 | #41 |
| 14 | Hy4 preview | High | 3.3 | #71 |
| 15 | Kimi K3 | Max | 1.3 | #56 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon.
Interactive version: theaggregate.ai/benchmark?slug=dayjob-data-science · How It Works · Data refreshed daily, snapshot 2026-11-16.