Skip to content
AI Atlas
BenchmarkActivecategory · general

LiveBench

livebench.ai

contamination-limited, monthly refreshed questions across 6 categories

quality57

Updated 3 h ago · first seen 11 Sept 2026

bench_01M293SPERF0D8QG7TSCGE8GGF

Metric
average score · %
Direction
Higher is better
Results
456
Leader
Claude Fable 5.1 Max Effort 97.01%

Score history · claude-opus-4-5-20251101-thinking-64k-high-effort 8 rows

Not enough history to chart — 8 observations, all dated 25 Jun 2026. Rows under different configurations count separately; the list below shows each one.

  • 62.55%release=2026-06-25 · subtasks=["paraphrase","simplify","story_generation","summarize"] · livebench_model_id=claude-opus-4-5-20251101-thinking-64k-high-effort25 Jun 2026
  • 81.26%release=2026-06-25 · subtasks=["connections","plot_unscrambling","typos"] · livebench_model_id=claude-opus-4-5-20251101-thinking-64k-high-effort25 Jun 2026
  • 74.44%release=2026-06-25 · subtasks=["consecutive_events","tablejoin","tablereformat"] · livebench_model_id=claude-opus-4-5-20251101-thinking-64k-high-effort25 Jun 2026
  • 90.39%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=claude-opus-4-5-20251101-thinking-64k-high-effort25 Jun 2026
  • 39.7%release=2026-06-25 · subtasks=["javascript","typescript","python"] · livebench_model_id=claude-opus-4-5-20251101-thinking-64k-high-effort25 Jun 2026
  • 79.65%release=2026-06-25 · subtasks=["code_generation","code_completion"] · livebench_model_id=claude-opus-4-5-20251101-thinking-64k-high-effort25 Jun 2026
  • 80.09%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=claude-opus-4-5-20251101-thinking-64k-high-effort25 Jun 2026
  • 72.58%release=2026-06-25 · aggregation=mean of category averages; category = mean of its subtasks · livebench_model_id=claude-opus-4-5-20251101-thinking-64k-high-effort25 Jun 2026

Back to the full leaderboard

Leaderboard 456 current results

Select models with +, then open Compare.

Leaderboard
#ModelScoreConfigEvaluatedSourceActions
1#1Claude Fable 5.1 Max EffortAnthropic97.01%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=claude-fable-5-1-max-effort25 Jun 2026livebench.aiT2 History
2#2gpt-6-astraOpenAI96.81%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=gpt-6-astra-max25 Jun 2026livebench.aiT2 History
3#3gpt-5-6-solOpenAI96.2%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=gpt-5.6-sol-max25 Jun 2026livebench.aiT2 History
4#4Claude Fable 5 xHigh EffortAnthropic95.99%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=claude-fable-5-max-effort25 Jun 2026livebench.aiT2 History
5#5muse-spark-1-3-xhighMeta AI95.95%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=muse-spark-1.3-xhigh25 Jun 2026livebench.aiT2 History
6#6gpt-5.5OpenAI95.86%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=gpt-5.5-xhigh25 Jun 2026livebench.aiT2 History
7#7claude-opus-5-max-effort95.73%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=claude-opus-5-max-effort25 Jun 2026livebench.aiT2 History
8#8DeepSeek-V4-Pro-0813DeepSeek95.09%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=deepseek-v4-pro-081325 Jun 2026livebench.aiT2 History
9#9gpt-5.6-terraOpenAI94.91%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=gpt-5.6-terra-max25 Jun 2026livebench.aiT2 History
10#10Claude 4.8 Opus Thinking Max EffortAnthropic94.32%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=claude-opus-4-8-max-effort25 Jun 2026livebench.aiT2 History
11#11gpt-5.4OpenAI94.15%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=gpt-5.4-xhigh25 Jun 2026livebench.aiT2 History
12#12Gemini 3.7 FlashGoogle93.47%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=gemini-3.7-flash-high25 Jun 2026livebench.aiT2 History
13#13DeepSeek-V4.1-FlashDeepSeek93.29%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=deepseek-v4.1-flash-max25 Jun 2026livebench.aiT2 History
14#14gpt-5.2-2025-12-11-high93.17%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=gpt-5.2-2025-12-11-high25 Jun 2026livebench.aiT2 History
15#15Claude Sonnet 5 xHigh EffortAnthropic92.94%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=claude-sonnet-5-xhigh-effort25 Jun 2026livebench.aiT2 History
16#16claude-opus-4-7-xhigh-effort92.85%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=claude-opus-4-7-xhigh-effort25 Jun 2026livebench.aiT2 History
17#17gpt-6-astraOpenAI92.65%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=gpt-6-astra-max25 Jun 2026livebench.aiT2 History
18#18Grok 4.6xAI92.57%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=grok-4.625 Jun 2026livebench.aiT2 History
19#19Claude Fable 5.1 Max EffortAnthropic91.69%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=claude-fable-5-1-max-effort25 Jun 2026livebench.aiT2 History
20#20gpt-5-6-solOpenAI91.65%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=gpt-5.6-sol-max25 Jun 2026livebench.aiT2 History
21#21Gemini 3.8 FlashGoogle91.56%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=gemini-3.8-flash-high25 Jun 2026livebench.aiT2 History
22#22Qwen 3.8 MaxQwen91.31%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=qwen3.8-max25 Jun 2026livebench.aiT2 History
23#23claude-opus-5-max-effort91.21%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=claude-opus-5-max-effort25 Jun 2026livebench.aiT2 History
24#24Muse Spark 1.2Meta AI91.2%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=muse-spark-1.2-xhigh25 Jun 2026livebench.aiT2 History
25#25Gemini 3.1 Pro Preview HighGoogle91.05%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=gemini-3.1-pro-preview-high25 Jun 2026livebench.aiT2 History
26#26gpt-5.4-nanoOpenAI90.98%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=gpt-5.4-nano-xhigh25 Jun 2026livebench.aiT2 History
27#27Grok 4.5xAI90.83%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=grok-4.525 Jun 2026livebench.aiT2 History
28#28Claude Fable 5 xHigh EffortAnthropic90.68%release=2026-06-25 · subtasks=["connections","plot_unscrambling","typos"] · livebench_model_id=claude-fable-5-max-effort25 Jun 2026livebench.aiT2 History
29#29deepseek-v4-proDeepSeek90.68%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=deepseek-v4-pro25 Jun 2026livebench.aiT2 History
30#30Kimi K3Moonshot AI90.67%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=kimi-k325 Jun 2026livebench.aiT2 History
31#31gpt-5.6-terraOpenAI90.64%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=gpt-5.6-terra-max25 Jun 2026livebench.aiT2 History
32#32Grok 4.6xAI90.51%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=grok-4.625 Jun 2026livebench.aiT2 History
33#33claude-opus-4-5-20251101-thinking-64k-high-effort90.39%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=claude-opus-4-5-20251101-thinking-64k-high-effort25 Jun 2026livebench.aiT2 History
34#34Smaug Agentic90.27%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=smaug-agentic25 Jun 2026livebench.aiT2 History
35#35Smaug Flash90.06%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=smaug-flash25 Jun 2026livebench.aiT2 History
36#36Muse Spark 1.2Meta AI90.01%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=muse-spark-1.2-xhigh25 Jun 2026livebench.aiT2 History
37#37Z.ai GLM 5.2Z.ai (Zhipu AI)89.78%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=glm-5.225 Jun 2026livebench.aiT2 History
38#38Smaug Mini89.74%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=smaug-mini25 Jun 2026livebench.aiT2 History
39#39Claude Fable 5 xHigh EffortAnthropic89.65%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=claude-fable-5-max-effort25 Jun 2026livebench.aiT2 History
40#40gpt-5.5OpenAI89.65%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=gpt-5.5-xhigh25 Jun 2026livebench.aiT2 History
41#41muse-spark-1-3-xhighMeta AI89.65%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=muse-spark-1.3-xhigh25 Jun 2026livebench.aiT2 History
42#42Claude Fable 5.1 Max EffortAnthropic89.5%release=2026-06-25 · subtasks=["connections","plot_unscrambling","typos"] · livebench_model_id=claude-fable-5-1-max-effort25 Jun 2026livebench.aiT2 History
43#43gpt-6-astraOpenAI89.43%release=2026-06-25 · subtasks=["connections","plot_unscrambling","typos"] · livebench_model_id=gpt-6-astra-max25 Jun 2026livebench.aiT2 History
44#44Claude 4.6 Opus Thinking High EffortAnthropic89.32%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=claude-opus-4-6-thinking-auto-high-effort25 Jun 2026livebench.aiT2 History
45#45Gemini 3.8 FlashGoogle89.29%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=gemini-3.8-flash-high25 Jun 2026livebench.aiT2 History
46#46Claude 4.8 Opus Thinking Max EffortAnthropic89.19%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=claude-opus-4-8-max-effort25 Jun 2026livebench.aiT2 History
47#47GPT-5.2-CodexOpenAI88.77%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=gpt-5.2-codex25 Jun 2026livebench.aiT2 History
48#48Claude Sonnet 5 xHigh EffortAnthropic88.69%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=claude-sonnet-5-xhigh-effort25 Jun 2026livebench.aiT2 History
49#49claude-opus-5-max-effort88.69%release=2026-06-25 · subtasks=["connections","plot_unscrambling","typos"] · livebench_model_id=claude-opus-5-max-effort25 Jun 2026livebench.aiT2 History
50#50Claude 4.6 Opus Thinking High EffortAnthropic88.67%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=claude-opus-4-6-thinking-auto-high-effort25 Jun 2026livebench.aiT2 History
51#51Nemotron 3 UltraNVIDIA88.66%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=nemotron-3-ultra-550b-a55b25 Jun 2026livebench.aiT2 History
52#52Inkling xHigh Effort88.37%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=inkling-xhigh25 Jun 2026livebench.aiT2 History
53#53gemini-3.5-flash-high88.24%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=gemini-3.5-flash-high25 Jun 2026livebench.aiT2 History
54#54Qwen 3.8 MaxQwen88.21%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=qwen3.8-max25 Jun 2026livebench.aiT2 History
55#55gpt-5.4OpenAI88.12%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=gpt-5.4-xhigh25 Jun 2026livebench.aiT2 History
56#56GLM 5.3Z.ai (Zhipu AI)87.9%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=glm-5.325 Jun 2026livebench.aiT2 History
57#57DeepSeek V4 Flash Vision ExpDeepSeek87.81%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=deepseek-v4-flash-vision-exp25 Jun 2026livebench.aiT2 History
58#58Gemini 3.7 FlashGoogle87.8%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=gemini-3.7-flash-high25 Jun 2026livebench.aiT2 History
59#59Gemini 3.8 FlashGoogle87.79%release=2026-06-25 · subtasks=["connections","plot_unscrambling","typos"] · livebench_model_id=gemini-3.8-flash-high25 Jun 2026livebench.aiT2 History
60#60Muse Spark 1.1Meta AI87.73%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=muse-spark-1.1-xhigh25 Jun 2026livebench.aiT2 History
61#61gpt-5-6-solOpenAI87.68%release=2026-06-25 · subtasks=["connections","plot_unscrambling","typos"] · livebench_model_id=gpt-5.6-sol-max25 Jun 2026livebench.aiT2 History
62#62Qwen3.8 FlashQwen87.38%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=qwen3.8-flash-next25 Jun 2026livebench.aiT2 History
63#63gpt-5.5OpenAI87.36%release=2026-06-25 · subtasks=["connections","plot_unscrambling","typos"] · livebench_model_id=gpt-5.5-xhigh25 Jun 2026livebench.aiT2 History
64#64gpt-5.6-lunaOpenAI87.2%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=gpt-5.6-luna-max25 Jun 2026livebench.aiT2 History
65#65claude-opus-4-7-xhigh-effort87.19%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=claude-opus-4-7-xhigh-effort25 Jun 2026livebench.aiT2 History
66#66Grok 4.5xAI87.17%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=grok-4.525 Jun 2026livebench.aiT2 History
67#67Muse Spark 1.1Meta AI87.15%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=muse-spark-1.1-xhigh25 Jun 2026livebench.aiT2 History
68#68claude-sonnet-4-6-thinking-auto-medium-effort86.99%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=claude-sonnet-4-6-thinking-auto-medium-effort25 Jun 2026livebench.aiT2 History
69#69DeepSeek V4 Flash (0731)DeepSeek86.79%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=deepseek-v4-flash-073125 Jun 2026livebench.aiT2 History
70#70DeepSeek-V4.1-FlashDeepSeek86.69%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=deepseek-v4.1-flash-max25 Jun 2026livebench.aiT2 History
71#71DeepSeek V4 Flash (0731)DeepSeek86.64%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=deepseek-v4-flash-073125 Jun 2026livebench.aiT2 History
72#72Gemini 3.6 Flash HighGoogle86.4%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=gemini-3.6-flash-high25 Jun 2026livebench.aiT2 History
73#73Claude Fable 5.1 Max EffortAnthropic86.38%release=2026-06-25 · subtasks=["code_generation","code_completion"] · livebench_model_id=claude-fable-5-1-max-effort25 Jun 2026livebench.aiT2 History
74#74Smaug Flash86.23%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=smaug-flash25 Jun 2026livebench.aiT2 History
75#75qwen3-8-27b-non-reasoningAlibaba Group86.21%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=qwen3.8-27b25 Jun 2026livebench.aiT2 History
76#76Claude Fable 5 xHigh EffortAnthropic85.99%release=2026-06-25 · subtasks=["code_generation","code_completion"] · livebench_model_id=claude-fable-5-max-effort25 Jun 2026livebench.aiT2 History
77#77DeepSeek-V4-Pro-0813DeepSeek85.84%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=deepseek-v4-pro-081325 Jun 2026livebench.aiT2 History
78#78Qwen3.8 FlashQwen85.82%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=qwen3.8-flash-next25 Jun 2026livebench.aiT2 History
79#79GLM 5.3Z.ai (Zhipu AI)85.8%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=glm-5.325 Jun 2026livebench.aiT2 History
80#80gpt-5.6-lunaOpenAI85.64%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=gpt-5.6-luna-max25 Jun 2026livebench.aiT2 History
81#81Kimi K3Moonshot AI85.53%release=2026-06-25 · subtasks=["connections","plot_unscrambling","typos"] · livebench_model_id=kimi-k325 Jun 2026livebench.aiT2 History
82#82Gemini 3.7 FlashGoogle85.46%release=2026-06-25 · subtasks=["connections","plot_unscrambling","typos"] · livebench_model_id=gemini-3.7-flash-high25 Jun 2026livebench.aiT2 History
83#83DeepSeek V4 Flash Vision ExpDeepSeek85.4%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=deepseek-v4-flash-vision-exp25 Jun 2026livebench.aiT2 History
84#84Gemini 3.1 Pro Preview HighGoogle85.38%release=2026-06-25 · subtasks=["connections","plot_unscrambling","typos"] · livebench_model_id=gemini-3.1-pro-preview-high25 Jun 2026livebench.aiT2 History
85#85Qwen3.7 MaxQwen85.25%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=qwen3.7-max25 Jun 2026livebench.aiT2 History
86#86Gemini 3.6 Flash HighGoogle85.15%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=gemini-3.6-flash-high25 Jun 2026livebench.aiT2 History
87#87claude-sonnet-4-6-thinking-auto-medium-effort84.77%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=claude-sonnet-4-6-thinking-auto-medium-effort25 Jun 2026livebench.aiT2 History
88#88gemini-3.5-flash-high84.58%release=2026-06-25 · subtasks=["connections","plot_unscrambling","typos"] · livebench_model_id=gemini-3.5-flash-high25 Jun 2026livebench.aiT2 History
89#89Kimi K3Moonshot AI84.44%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=kimi-k325 Jun 2026livebench.aiT2 History
90#90Smaug Agentic84.36%release=2026-06-25 · subtasks=["connections","plot_unscrambling","typos"] · livebench_model_id=smaug-agentic25 Jun 2026livebench.aiT2 History
91#91Grok 4.3xAI84.34%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=grok-4.325 Jun 2026livebench.aiT2 History
92#92Kimi K2.6 ThinkingMoonshot AI84.28%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=kimi-k2.6-thinking25 Jun 2026livebench.aiT2 History
93#93Gemini 3.1 Pro Preview HighGoogle84.01%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=gemini-3.1-pro-preview-high25 Jun 2026livebench.aiT2 History
94#94gpt-5-6-solOpenAI83.94%release=2026-06-25 · subtasks=["code_generation","code_completion"] · livebench_model_id=gpt-5.6-sol-max25 Jun 2026livebench.aiT2 History
95#95Smaug Agentic83.92%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=smaug-agentic25 Jun 2026livebench.aiT2 History
96#96Gemini 3.6 Flash HighGoogle83.9%release=2026-06-25 · subtasks=["connections","plot_unscrambling","typos"] · livebench_model_id=gemini-3.6-flash-high25 Jun 2026livebench.aiT2 History
97#97Qwen3.6 PlusQwen83.73%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=qwen3.6-plus25 Jun 2026livebench.aiT2 History
98#98Grok 4.6xAI83.7%release=2026-06-25 · subtasks=["connections","plot_unscrambling","typos"] · livebench_model_id=grok-4.625 Jun 2026livebench.aiT2 History
99#99GPT-5.2-CodexOpenAI83.62%release=2026-06-25 · subtasks=["code_generation","code_completion"] · livebench_model_id=gpt-5.2-codex25 Jun 2026livebench.aiT2 History
100#100Claude Fable 5.1 Max EffortAnthropic83.41%release=2026-06-25 · aggregation=mean of category averages; category = mean of its subtasks · livebench_model_id=claude-fable-5-1-max-effort25 Jun 2026livebench.aiT2 History

Scores are reported as published, with their evaluation configuration (harness, prompting, judge). The bar is relative to the best score on this page. Results with different configs are not directly comparable — see methodology.

The config filter matches a value inside each result's configuration (server-side, `config=` on the API). Chips are the values shared by several rows on the first page; per-model identifiers are not offered.