BenchGecko Score: leaderboard
BenchGecko's own composite index over the public boards it tracks, mirrored here the way LLM Stats Score and BenchmarkList ECI are. Coverage per model is uneven — between 3 and 14 boards feed each score — so it reads as one aggregator's view rather than an independent measurement.
Metric: Composite Score. Source: benchgecko.ai. Saturation forecast: Around January 2027. 20 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Mythos Preview | 99.7 | #4 |
| 2 | GPT-5.5 Pro | 99.6 | #17 |
| 3 | GPT-6 Astra | 95.6 | #6 |
| 4 | DeepSeek V3.2 Speciale | 95.2 | #128 |
| 5 | GPT-6.1 Sol | 93.5 | #7 |
| 6 | Claude Opus 5.5 | 91.9 | #3 |
| 7 | Step 3.5 Flash | 89.5 | #270 |
| 8 | GPT-5 Chat | 89 | #241 |
| 9 | Gemini 4 Argon | 88.6 | #8 |
| 10 | Claude Opus 5 | 86 | #12 |
| 11 | DeepSeek V2 | 85.9 | #549 |
| 12 | GPT-5.1 Codex Max | 85.6 | #100 |
| 13 | Claude Fable 5.1 | 84.5 | #9 |
| 14 | Claude Fable 5 | 83.6 | #16 |
| 15 | MiMo-V2-Flash | 81.7 | #372 |
No result here: #10 Muse Wonder Full.
Interactive version: theaggregate.ai/benchmark?slug=benchgecko-score · How It Works · Data refreshed daily, snapshot 2026-10-20.