Gert Labs Rankings: leaderboard
Gert Labs global model ranking across game environments that evaluate agentic coding, one-shot coding, and decision-making performance.
Metric: GScore (%). Source: gertlabs.com. Source: gertlabs.com. Saturation forecast: Around January 2027. 100 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra | 83.62 | #6 |
| 2 | GPT-6.1 Sol | 81.61 | #7 |
| 3 | Claude Opus 5.5 | 76.56 | #3 |
| 4 | GPT-6 Sol | 72.95 | #14 |
| 5 | Gemini 4 Argon | 72.73 | #8 |
| 6 | Claude Opus 5 | 71.28 | #12 |
| 7 | Claude Fable 5.1 | 70.98 | #9 |
| 8 | Claude Sonnet 5.5 | 69.12 | #11 |
| 9 | Claude Fable 5 | 67.58 | #16 |
| 10 | Muse Wonder | 65.06 | #15 |
| 11 | GPT-5.6 Sol | 64.5 | #19 |
| 12 | Grok 4.7 | 63.27 | #25 |
| 13 | GPT-5.5 | 63.09 | #31 |
| 14 | Grok 4.6 | 62.6 | #26 |
| 15 | Gemini 3.7 Flash | 61.53 | #23 |
No result here: #10 Muse Wonder Full.
Interactive version: theaggregate.ai/benchmark?slug=gert-labs-rankings · How It Works · Data refreshed daily, snapshot 2026-10-20.