CompareLLM
CompareLLM.ai
Live
LeaderboardModelsCompareStacksBest ofGuidesNewsMethod
…
CompareLLM
CompareLLM.ai
Precision Benchmarks

Programmatic, dated AI model benchmarks, head-to-head comparisons, and Stack Engine presets.

Daily ingest · 06:00 UTC

Analytics & Benchmarks

  • AI Model Leaderboard
  • Head-to-Head Compare Hub
  • Models Directory
  • Stack Engine Presets
  • Frontier Models
  • Open Weights Catalog

Guides & Intent Lists

  • Best LLM Lists (2026)
  • Best Coding LLM
  • Best Cheap LLM
  • Fastest Low-Latency LLM
  • Claude vs GPT Benchmark
  • What is Elo?
  • Methodology Guides
  • News & Dispatches

Transparency & API

  • Evaluation Methodology
  • Benchmark Changelog
  • Public JSON API
  • llms.txt Specification
  • Privacy Policy
  • Sign In / Account

© 2026 CompareLLM. Public benchmark data aggregated from Arena Elo, LiveBench, SWE-bench & OpenRouter.

Every score has a dated snapshot.

  1. Home
  2. Leaderboards
  3. GPQA Diamond
Benchmark Domain · %
▲ Higher is better

GPQA Diamond Leaderboard

All active models in our catalog ranked by verified GPQA Diamond snapshots. Showing 70 validated models.

Switch Leaderboard Metric:
All Metrics:EloCode EloLiveBenchSWE-benchGPQATTFTSpeedIn $Out $Context
Current #1 Leader for GPQA
88.4%

Kimi K3

Moonshot · Proprietary · Frontier tier

seed-bootstrap · Aug 1, 2026View full model fact sheet

Complete Ranked Roster

#1
Kimi K3Moonshot
seed-bootstrap · Aug 1, 2026
88.4%Current Leader
#2
MoonshotAI: Kimi K2.5Moonshot
seed-bootstrap · Aug 1, 2026
87.6%vs #1
#3
Claude Fable 5Anthropic
seed-bootstrap · Aug 16, 2026
87.6%vs #1
#4
OpenAI: o3 MiniOpenAI
seed-bootstrap · Aug 1, 2026
87.2%vs #1
#5
Claude Opus 5Anthropic
seed-bootstrap · Aug 16, 2026
87.1%vs #1
#6
GPT-5.6 SolOpenAI
seed-bootstrap · Aug 16, 2026
86.8%vs #1
#7
Claude Opus 4.8Anthropic
seed-bootstrap · Aug 16, 2026
86.2%vs #1
#8
GPT-5OpenAI
seed-bootstrap · Aug 1, 2026
85.2%vs #1
#9
Claude Opus 4.6Anthropic
seed-bootstrap · Aug 1, 2026
84.8%vs #1
#10
Grok 4.6xAI
seed-bootstrap · Aug 16, 2026
84.6%vs #1
#11
Gemini 3.6 ProGoogle
seed-bootstrap · Aug 16, 2026
84.4%vs #1
#12
Claude Opus 4.5Anthropic
seed-bootstrap · Aug 1, 2026
84.1%vs #1
#13
DeepSeek V4 ProDeepSeekOpen
seed-bootstrap · Aug 1, 2026
84%vs #1
#14
GPT-4.5 OrionOpenAI
seed-bootstrap · Aug 1, 2026
84%vs #1
#15
Gemini 3 ProGoogle
seed-bootstrap · Aug 1, 2026
83.6%vs #1
#16
Qwen QwQ 32BAlibabaOpen
seed-bootstrap · Aug 1, 2026
83.2%vs #1
#17
GLM-5.3Zhipu
seed-bootstrap · Aug 16, 2026
83.2%vs #1
#18
Qwen 3 MaxAlibaba
seed-bootstrap · Aug 1, 2026
83.1%vs #1
#19
Claude Sonnet 5Anthropic
seed-bootstrap · Aug 16, 2026
82.8%vs #1
#20
GPT-5.6 TerraOpenAI
seed-bootstrap · Aug 16, 2026
82%vs #1
#21
DeepSeek V4 FlashDeepSeekOpen
seed-bootstrap · Aug 16, 2026
81.6%vs #1
#22
Gemini 3.7 FlashGoogle
seed-bootstrap · Aug 16, 2026
81.2%vs #1
#23
Gemini 2.0 Flash ThinkingGoogle
seed-bootstrap · Aug 1, 2026
81%vs #1
#24
Claude Opus 4Anthropic
seed-bootstrap · Aug 1, 2026
80.4%vs #1
#25
Claude Sonnet 4.5Anthropic
seed-bootstrap · Aug 1, 2026
80.2%vs #1
#26
DeepSeek R1DeepSeekOpen
seed-bootstrap · Aug 1, 2026
79.8%vs #1
#27
Gemini 3.6 FlashGoogle
seed-bootstrap · Aug 16, 2026
79.6%vs #1
#28
GLM-5.2ZhipuOpen
seed-bootstrap · Aug 1, 2026
79.5%vs #1
#29
Grok 4xAI
seed-bootstrap · Aug 1, 2026
79%vs #1
#30
Claude 3.7 SonnetAnthropic
seed-bootstrap · Aug 1, 2026
78.5%vs #1
#31
Gemini 3 FlashGoogle
seed-bootstrap · Aug 1, 2026
78.4%vs #1
#32
Yi-Lightning01.AI
seed-bootstrap · Aug 1, 2026
78%vs #1
#33
OpenAI: o1OpenAI
seed-bootstrap · Aug 1, 2026
78%vs #1
#34
Doubao Pro 1.5ByteDance
seed-bootstrap · Aug 1, 2026
77.5%vs #1
#35
Qwen3 235BAlibabaOpen
seed-bootstrap · Aug 1, 2026
76.8%vs #1
#36
Seed 2.1 TurboByteDance
seed-bootstrap · Aug 16, 2026
76.8%vs #1
#37
OpenAI o1-miniOpenAI
seed-bootstrap · Aug 1, 2026
76.8%vs #1
#38
MoonshotAI: Kimi K2 0711Moonshot
seed-bootstrap · Aug 1, 2026
76.5%vs #1
#39
Gemini 2.5 ProGoogle
seed-bootstrap · Aug 1, 2026
76.4%vs #1
#40
Claude Sonnet 4Anthropic
seed-bootstrap · Aug 1, 2026
76.4%vs #1
#41
MiniMax M2.5MiniMaxOpen
seed-bootstrap · Aug 1, 2026
76.2%vs #1
#42
Qwen 2.5 PlusAlibaba
seed-bootstrap · Aug 1, 2026
75.8%vs #1
#43
GPT-5.6 LunaOpenAI
seed-bootstrap · Aug 16, 2026
75.4%vs #1
#44
Llama 3.1 405BMetaOpen
seed-bootstrap · Aug 1, 2026
75.2%vs #1
#45
Llama 4 MaverickMetaOpen
seed-bootstrap · Aug 1, 2026
74.6%vs #1
#46
Ernie 4.5 TurboBaidu
seed-bootstrap · Aug 1, 2026
74.5%vs #1
#47
Grok 3xAI
seed-bootstrap · Aug 1, 2026
74.2%vs #1
#48
Mistral Large 3Mistral
seed-bootstrap · Aug 1, 2026
74.1%vs #1
#49
Claude Haiku 4.5Anthropic
seed-bootstrap · Aug 16, 2026
74%vs #1
#50
Qwen 2.5 Coder 32BAlibabaOpen
seed-bootstrap · Aug 1, 2026
74%vs #1
#51
Qwen3.8 27BAlibabaOpen
seed-bootstrap · Aug 16, 2026
73.4%vs #1
#52
GPT-4oOpenAI
seed-bootstrap · Aug 1, 2026
73.2%vs #1
#53
Yi-Large01.AI
seed-bootstrap · Aug 1, 2026
72.4%vs #1
#54
GPT-5 miniOpenAI
seed-bootstrap · Aug 1, 2026
72%vs #1
#55
Kimi Chat 1.5Moonshot
seed-bootstrap · Aug 1, 2026
71.5%vs #1
#56
Llama 4 ScoutMetaOpen
seed-bootstrap · Aug 16, 2026
71.2%vs #1
#57
DeepSeek Coder V2DeepSeekOpen
seed-bootstrap · Aug 1, 2026
70.2%vs #1
#58
Gemini 2.5 FlashGoogle
seed-bootstrap · Aug 1, 2026
68.2%vs #1
#59
Command ACohere
seed-bootstrap · Aug 1, 2026
66%vs #1
#60
Llama 3.3 70BMetaOpen
seed-bootstrap · Aug 1, 2026
65.7%vs #1
#61
Claude 3.5 SonnetAnthropic
seed-bootstrap · Aug 1, 2026
65%vs #1
#62
Doubao Lite 1.5ByteDance
seed-bootstrap · Aug 1, 2026
64.2%vs #1
#63
GPT-4o miniOpenAI
seed-bootstrap · Aug 1, 2026
60.1%vs #1
#64
DeepSeek V3DeepSeekOpen
seed-bootstrap · Aug 1, 2026
59.1%vs #1
#65
Codestral 25.01Mistral
seed-bootstrap · Aug 1, 2026
58.4%vs #1
#66
Gemini 1.5 ProGoogle
seed-bootstrap · Aug 1, 2026
58%vs #1
#67
Claude 3.5 HaikuAnthropic
seed-bootstrap · Aug 1, 2026
54.1%vs #1
#68
Claude 3 OpusAnthropic
seed-bootstrap · Aug 1, 2026
50.4%vs #1
#69
GPT-4 TurboOpenAI
seed-bootstrap · Aug 1, 2026
48%vs #1
#70
Llama 3.1 70BMetaOpen
seed-bootstrap · Aug 1, 2026
48%vs #1