AutoBench — leaderboard
Automated multi-metric LLM evaluation ranking models by cost, latency, and domain performance. Models ranked by aggregate score across practical business tasks.
Metric: AutoBench Rank. Source: autobench.org. Status: saturation imminent. 32 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.1 | 4.49 |
| 2 | GPT-5 | 4.45 |
| 3 | Gemini 3 Pro (Preview) | 4.39 |
| 4 | Gemini 2.5 Pro | 4.37 |
| 5 | GPT-OSS-120B | 4.37 |
| 6 | Kimi K2 (Thinking) | 4.34 |
| 7 | Grok 4.1 Fast | 4.34 |
| 8 | GPT-5 Nano | 4.32 |
| 9 | Claude Sonnet 4.5 | 4.31 |
| 10 | Gemini 2.5 Flash | 4.3 |
| 11 | Qwen 3 235B A22B (Thinking) | 4.28 |
| 12 | Claude Haiku 4.5 | 4.27 |
| 13 | Claude Opus 4.1 | 4.27 |
| 14 | GLM-4.6 | 4.25 |
| 15 | Qwen 3 235B A22B 2507 | 4.24 |
Interactive version: theaggregate.ai/benchmark?slug=autobench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.