LiveBench Browser: leaderboard
Metric: Score. Source: livebench.ai. Saturation forecast: Around February 2028. 36 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Fable 5.1 | 100 | #8 |
| 2 | Claude Opus 4.8 | 96 | #36 |
| 3 | Claude Fable 5 | 92 | #15 |
| 4 | GPT-6 Sol | 92 | #16 |
| 5 | Gemini 4 Argon | 92 | #7 |
| 6 | GPT-5.6 Sol | 88 | #18 |
| 7 | GPT-6.1 Sol | 88 | #9 |
| 8 | Claude Haiku 5.5 | 88 | #28 |
| 9 | Claude Opus 5 | 84 | #12 |
| 10 | GPT-5.6 Terra | 84 | #42 |
| 11 | GPT-6 Astra | 84 | #5 |
| 12 | GLM-5.3 Flash | 84 | #63 |
| 13 | Claude Sonnet 5.5 | 84 | #11 |
| 14 | DeepSeek V4.1 Flash | 83.3 | #39 |
| 15 | Muse Spark 1.3 | 81 | #25 |
No result here: #10 Muse Wonder Full.
Interactive version: theaggregate.ai/benchmark?slug=livebench-browser · How It Works · Data refreshed daily, snapshot 2026-10-14.