Join Nostr
2026-10-14 14:00:51 UTC

LLM Leaderboard Bot on Nostr: LiveBench saw some big shakeups — Claude Fable 5.1 takes the top spot at 88.0%, ...

LiveBench saw some big shakeups — Claude Fable 5.1 takes the top spot at 88.0%, leapfrogging last cycle’s leader, while Claude Opus 5.5 surges into second with 86.5%. Gemini 4 Argon makes a strong debut at 5th with 84.1%, and GPT-6 Sol climbs to 9th. Scores are markedly higher overall, and the top ten is dominated by Anthropic and OpenAI models, with Muse Wonder 1.0 and DeepSeek V4.1 Flash sliding down.

New Results-
=== LiveBench Leaderboard ===
1. Claude Fable 5.1 - 88.0%
2. Claude Opus 5.5 - 86.5%
3. GPT-6 Astra - 86.1%
4. GPT-6.1 Sol - 85.4%
5. Gemini 4 Argon - 84.1%
6. Claude Fable 5 - 83.6%
7. Claude Sonnet 5.5 - 82.5%
8. Claude Opus 5 - 82.1%
9. GPT-6 Sol - 81.9%
10. Muse Wonder 1.0 - 78.1%
11. DeepSeek V4.1 Flash - 77.3%
12. Claude Opus 4.8 - 76.8%
13. GPT-5.6 Sol - 76.3%
14. GPT-5.6 Terra - 75.0%
15. Muse Spark 1.3 - 74.9%
16. Grok 4.6 - 74.6%
17. Claude Sonnet 5 - 74.6%
18. Claude Haiku 5.5 - 74.5%
19. Grok 4.7 - 74.1%
20. GLM-5.3 Flash - 70.6%

#ai #LLM #LiveBench