Tuesday Work Index: leaderboard
Surge AI’s published index compares models on professional work. Native scores and reasoning settings remain attached to each model; individual component results are separate.
Metric: Published work index (0–100). Source: surgehq.ai. Saturation forecast: Around February 2027. 44 models tracked. Updated 17 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Opus 5.5 | Max | 76.3 | #7 |
| 2 | Claude Sonnet 5.5 | Max | 75.8 | #21 |
| 3 | Claude Fable 5.1 | Max | 72.4 | #17 |
| 4 | GPT-6 Astra | Max | 72.3 | #8 |
| 5 | GPT-6.1 Sol | Max | 70.6 | #12 |
| 6 | Muse Wonder | Max | 69.7 | #31 |
| 7 | Gemini 4 Argon | High | 67.2 | #14 |
| 8 | Claude Opus 5 | Max | 65 | #23 |
| 9 | Grok 4.7 | xHigh | 64.7 | #48 |
| 10 | Muse Spark 1.3 | Max | 63.9 | #45 |
| 11 | Claude Fable 5 | Max | 61.5 | #28 |
| 12 | GPT-5.6 Sol | Max | 61.1 | #33 |
| 13 | Grok 4.6 | xHigh | 60.8 | #47 |
| 14 | Kimi K3.1 Pro | Max | 60.2 | #32 |
| 15 | GPT-6 Sol | Max | 58.9 | #29 |
No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.
Interactive version: theaggregate.ai/benchmark?slug=tuesday-work-index · How It Works · Data refreshed daily, snapshot 2026-11-17.