LiveBench leaderboard: who is #1

Name: LiveBench rankings
Creator: LiveBench
License: https://creativecommons.org/licenses/by/4.0/

LiveBench · Global average, higher is better · 59 models · published Jun 25, 2026

Top 25 of 59 models, best variant per model as published

#	Model	Score
1	Claude Fable 5.1as “claude-fable-5-1-max-effort”	83.4%
2	Claude Opus 5.5as “claude-opus-5-5-max-effort”	83.2%
3	Claude Fable 5as “claude-fable-5-max-effort”	83.0%
4	GPT-6 Astraas “gpt-6-astra-max”	82.2%
5	Muse Spark 1.3as “muse-spark-1.3-xhigh”	81.6%
6	DeepSeek V4.1 Flashas “deepseek-v4.1-flash-max”	81.1%
7	GPT-5.6 Solas “gpt-5.6-sol-max”	81.0%
8	GPT-5.5as “gpt-5.5-xhigh”	80.2%
9	Claude Opus 5as “claude-opus-5-max-effort”	80.1%
10	Smaug Agenticas “smaug-agentic”	79.5%
11	GPT-6 Solas “gpt-6-sol-max”	79.3%
12	Kimi K3as “kimi-k3”	79.2%
13	Gemini 3.7 Flashas “gemini-3.7-flash-high”	78.8%
14	Qwen 3.8 Maxas “qwen3.8-max”	78.5%
15	Grok 4.6as “grok-4.6”	78.0%
16	GPT-5.4as “gpt-5.4-xhigh”	78.0%
17	Muse Spark 1.2as “muse-spark-1.2-xhigh”	78.0%
18	GPT-5.6 Terraas “gpt-5.6-terra-max”	77.9%
19	DeepSeek V4 Pro 0813as “deepseek-v4-pro-0813”	77.4%
19	Smaug Flashas “smaug-flash”	77.4%
21	Grok 4.7as “grok-4.7-xhigh”	77.4%
22	Gemini 3.1 Pro Previewas “gemini-3.1-pro-preview-high”	77.0%
23	Smaug Minias “smaug-mini”	76.9%
24	DeepSeek V4 Flash Visionas “deepseek-v4-flash-vision-exp”	76.8%
25	Claude Opus 4.7as “claude-opus-4-7-xhigh-effort”	76.5%