Lynchmark: leaderboard
Lynchmark — long-horizon coding/debugging tasks with verification; pass rate.
Metric: Pass Rate (%). Source: lynchmark.com. Saturation forecast: Estimated already saturated. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 100 | #58 |
| 2 | Gemini 3.5 Flash | 100 | #60 |
| 3 | Claude Fable 5 | 100 | #16 |
| 4 | Gemini 3 Flash (Preview) | 83.33 | #82 |
| 5 | Grok 4.5 | 83.33 | #48 |
| 6 | Kimi K2.6 | 75 | #104 |
| 7 | GLM-5.2 | 75 | #73 |
| 8 | Gemini 3.1 Flash Lite | 66.67 | #191 |
| 9 | DeepSeek V3.2 | 58.33 | #205 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=lynchmark · How It Works · Data refreshed daily, snapshot 2026-10-20.