BenchLM: leaderboard
Composite LLM leaderboard aggregating current model performance across agentic, coding, reasoning, grounded multimodal, knowledge, multilingual, instruction-following, and math categories.
Metric: Overall Score. Source: benchlm.ai. Saturation forecast: Around January 2027. 200 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5.5 | 86.7 | #3 |
| 2 | GPT-6.1 Sol | 84.2 | #7 |
| 3 | GPT-6 Astra | 84 | #6 |
| 4 | Claude Fable 5.1 | 83.2 | #9 |
| 5 | Gemini 4 Argon | 82.9 | #8 |
| 6 | Claude Sonnet 5.5 | 82.2 | #11 |
| 7 | Claude Fable 5 | 81.3 | #16 |
| 8 | Claude Opus 5 | 80.1 | #12 |
| 9 | GPT-6 Sol | 78.6 | #14 |
| 10 | GPT-5.6 Sol | 75.3 | #19 |
| 11 | Muse Wonder Full | 74.8 | #10 |
| 12 | MiMo-V2.6-Pro | 73.7 | #42 |
| 13 | GPT-5.5 Pro | 73.5 | #17 |
| 14 | Muse Wonder | 71.5 | #15 |
| 15 | GPT-5.6 Terra | 70.2 | #41 |
Interactive version: theaggregate.ai/benchmark?slug=benchlm · How It Works · Data refreshed daily, snapshot 2026-10-20.