Skip to content
Leaders Board.
Boards/Reasoning

LiveBench

Contamination-limited questions refreshed regularly: math, reasoning, coding, data analysis, language, instruction following.
LiveBench
Claude Fable 5.1
#1 right now
83.4%
Global average
59
Models ranked
Jun 25, 2026
Board published

Ranking

Best variant per model, as published. Higher is better.

  1. 1
    Claude Fable 5.1
    as “claude-fable-5-1-max-effort”
    83.4%
  2. 2
    Claude Opus 5.5
    as “claude-opus-5-5-max-effort”
    83.2%
  3. 3
    Claude Fable 5
    as “claude-fable-5-max-effort”
    83.0%
  4. 4
    GPT-6 Astra
    as “gpt-6-astra-max”
    82.2%
  5. 5
    Muse Spark 1.3
    as “muse-spark-1.3-xhigh”
    81.6%
  6. 6
    DeepSeek V4.1 Flash
    as “deepseek-v4.1-flash-max”
    81.1%
  7. 7
    GPT-5.6 Sol
    as “gpt-5.6-sol-max”
    81.0%
  8. 8
    GPT-5.5
    as “gpt-5.5-xhigh”
    80.2%
  9. 9
    Claude Opus 5
    as “claude-opus-5-max-effort”
    80.1%
  10. 10
    Smaug Agentic
    as “smaug-agentic”
    79.5%
  11. 11
    GPT-6 Sol
    as “gpt-6-sol-max”
    79.3%
  12. 12
    Kimi K3
    as “kimi-k3”
    79.2%
  13. 13
    Gemini 3.7 Flash
    as “gemini-3.7-flash-high”
    78.8%
  14. 14
    Qwen 3.8 Max
    as “qwen3.8-max”
    78.5%
  15. 15
    Grok 4.6
    as “grok-4.6”
    78.0%
  16. 16
    GPT-5.4
    as “gpt-5.4-xhigh”
    78.0%
  17. 17
    Muse Spark 1.2
    as “muse-spark-1.2-xhigh”
    78.0%
  18. 18
    GPT-5.6 Terra
    as “gpt-5.6-terra-max”
    77.9%
  19. 19
    DeepSeek V4 Pro 0813
    as “deepseek-v4-pro-0813”
    77.4%
  20. 19
    Smaug Flash
    as “smaug-flash”
    77.4%
  21. 21
    Grok 4.7
    as “grok-4.7-xhigh”
    77.4%
  22. 22
    Gemini 3.1 Pro Preview
    as “gemini-3.1-pro-preview-high”
    77.0%
  23. 23
    Smaug Mini
    as “smaug-mini”
    76.9%
  24. 24
    DeepSeek V4 Flash Vision
    as “deepseek-v4-flash-vision-exp”
    76.8%
  25. 25
    Claude Opus 4.7
    as “claude-opus-4-7-xhigh-effort”
    76.5%

Rank over time

Rank at each month’s end, from snapshots this board published or we captured.

12345678910NovDecJan 26FebMarAprNow1Claude Fable 5.12Claude Opus 5.53Claude Fable 54GPT-6 Astra5Muse Spark 1.36DeepSeek V4.1 Flash728GPT-5.52
Claude Fable 5.1Claude Opus 5.5Claude Fable 5GPT-6 AstraMuse Spark 1.3DeepSeek V4.1 FlashClaude Opus 4.5gpt-5-1-codexGPT-5.5GPT-5.4

Other reasoning boards

AA Intelligence
#1 Claude Opus 5.5
HLE
#1 GPT-6 Astra
GPQA Diamond
#1 GPT-6 Astra
Epoch ECI
#1 GPT-6 Astra
ARC-AGI-2
#1 GPT-6 Astra
MMLU-Pro
#1 Gemini 3.1 Pro Preview
Open LLM LB
#1 none

Scores as published by LiveBench on the capture date (2026-09-24). Source: livebench.ai release tables.

livebench.ai/

Weekly: the AI leaderboards with a new #1, Saturday mornings.