Note: Overall leaderboard rankings may not reflect true model quality — individual benchmarks give a clearer picture. ARC-Challenge MMLU GPQA GSM8K Artificial Analysis Intelligence Index v4.1
← Back to leaderboard

Artificial Analysis Intelligence Index v4.1.1 (Maximum Reasoning)

42 models

Top 5 Models Performance

Anthropic: claude-fable-5.1 ######################################## 66
Anthropic: claude-opus-5 ###################################### 63
Meta: muse-spark-1.3 ###################################### 62
Anthropic: Claude Fable 5 ###################################### 62
OpenAI: gpt-6-astra ##################################### 61
– 970 – 1.1T
– 2019 – 2026
Rank Model Score
🇺🇸 1 Anthropic: claude-fable-5.1 66
🇺🇸 2 Anthropic: claude-opus-5 63
🇺🇸 3 Meta: muse-spark-1.3 62
🇺🇸 4 Anthropic: Claude Fable 5 62
🇺🇸 5 OpenAI: gpt-6-astra 61
🇺🇸 6 SpaceXAI: grok-4.6 61
🇺🇸 7 OpenAI: gpt-5.6-sol 61
🇨🇳 8 Moonshot AI: kimi-k3月之暗面 60
🇺🇸 9 Google: gemini-3.8-flash 59
🇨🇳 10 Qwen: qwen3.8-2.4t-a95b通义千问 58
🇨🇳 11 Qwen: qwen3.8-max通义千问 58
🇺🇸 12 Meta: muse-spark-1.2 57
🇺🇸 13 Anthropic: Claude Opus 4.8 57
🇺🇸 14 OpenAI: gpt-5.6-terra 57
🇺🇸 15 Google: gemini-3.7-flash 56
🇺🇸 16 SpaceXAI: grok-4.5 56
🇺🇸 17 Anthropic: claude-sonnet-5 55
🇨🇳 18 Z.ai: GLM 5.2北京智谱华章科技有限公司 53
🇺🇸 19 Google: gemini-3.6-flash 52
🇨🇳 20 DeepSeek: deepseek-v4-flash-0731深度求索 52
🇺🇸 21 OpenAI: gpt-5.6-luna 52
🇨🇳 22 Qwen: Qwen3.7 Max通义千问 47
🇨🇳 23 MiniMax: MiniMax M3稀宇科技 45
🇪🇸 24 Multiverse Computing: quasar-438b 43
🇨🇳 25 Xiaomi: MiMo-V2.5 Pro小米集团 43
🇨🇳 26 Tencent: hy3腾讯控股有限公司 42
🇺🇸 27 Thinking Machines Lab: inkling 42
🇨🇳 28 DeepSeek: deepseek-v4.1-flash深度求索 39
🇺🇸 29 NVIDIA Corporation: nvidia-nemotron-3-ultra 38
🇨🇳 30 Qwen: qwen3.6-27b通义千问 38
🇺🇸 31 Google: gemini-3.5-flash-lite 37
🇺🇸 32 Meta: muse-glimmer-30b 35
🇨🇳 33 Qwen: qwen3.6-35b-a3b通义千问 32
🇺🇸 34 Anthropic: claude-4.5-haiku 30
🇺🇸 35 Google: Gemma 4 31B Instruct 30
🇫🇷 36 Mistral AI: mistral-medium-3.5-128b 30
🇺🇸 37 NVIDIA Corporation: nvidia-nemotron-3.5-lightning-30b-a3b-bf16 24
🇺🇸 38 OpenAI: gpt-oss-120b 24
🇨🇦 39 Cohere Labs: command-a-plus-05-2026-bf16 23
🇨🇳 40 Qwen: qwen3-max通义千问 16
🇺🇸 41 OpenAI: GPT-3.5 Turbo 3
🇺🇸 42 Meta Llama: llama-2-13b-chat 3