Skip to content

Artificial Analysis index

Ranked by the Artificial Analysis Intelligence Index, as published via OpenRouter. Covers many new models before Epoch evaluates them.

All90d30d
Open weights
All typesTextImageAudio
98 models

Ranked by the Artificial Analysis Intelligence Index, as published via OpenRouter. Covers many new models before Epoch evaluates them. Source: Artificial Analysis (via OpenRouter). Variants (reasoning effort, batch) are folded into one row.

#ModelCapabilityReasoningCodingContext$/M
1Claude Opus 5.5NEWAnthropic · +1 variant—90.6—1M$8.00
2Claude Sonnet 5.5NEWAnthropic · +1 variant—95.6—1M$4.00
3Claude Fable 5.1NEWAnthropic · +1 variant165.0——1M$20.00
4GPT-6 AstraNEWbatchOpenAI · +1 variant———1.05M$10.00
5GPT-6.1 SolNEWOpenAI · +1 variant———1.05M$4.00
6Claude Opus 5Anthropic · +1 variant162.793.973.61M$10.00
7Claude Fable 5Anthropic · +1 variant163.685.969.71M$20.00
8GPT-6 SolNEWOpenAI · +1 variant———1.05M$4.00
9GPT-5.6 SolOpenAI · +1 variant162.093.572.71.05M$4.00
10Grok 4.7NEWxAI———500K$3.00
11MiMo-V2.6-ProNEWXiaomi———1.05M$0.54
12Qwen3.8 Max (0902)NEWAlibaba (Qwen)155.3——1M$3.00
13GLM 5.3batchZ.ai (Zhipu AI) · +1 variant———1.05M$0.84
14Grok 4.6xAI156.594.065.2500K$3.00
15Kimi K3Moonshot AI · +1 variant157.793.168.51.05M$6.00
16GPT-5.6 TerraOpenAI · +1 variant159.393.369.61.05M$4.50
17Claude Opus 4.8Anthropic · +1 variant158.391.059.01M$10.00
18GLM 5.3 FlashbatchZ.ai (Zhipu AI) · +1 variant———1.05M$0.095
19Gemini 3.8 FlashNEWGoogle · +1 variant157.195.473.81.05M$1.50
20Qwen3.8 2.4T A95BAlibaba (Qwen)———1.05M$3.00
21Muse Spark 1.2Meta155.2——1.05M$2.00
22DeepSeek V4.1 FlashNEWbatchDeepSeek · +1 variant———1.05M$0.17
23Gemini 3.7 FlashGoogle · +1 variant157.794.865.31.05M$1.50
24Grok 4.5xAI154.093.453.8500K$3.00
25GPT-5.5batchOpenAI · +1 variant———1.05M$5.63
26Claude Sonnet 5Anthropic · +1 variant156.380.353.81M$4.00
27MiMo-V2.6-FlashNEWXiaomi———1.05M$0.17
28GPT-5.6 LunaOpenAI · +1 variant156.391.667.21.05M$0.45
29GPT-6 LunaNEWOpenAI · +1 variant———1.05M$0.20
30DeepSeek V4 Pro 0813DeepSeek155.491.7—1.05M$0.99
31DeepSeek V4 Flash 0731DeepSeek154.591.0—1.05M$0.33
32Gemini 3.6 FlashGoogle · +1 variant154.494.146.71.05M$1.50
33Muse Spark 1.1Meta154.3—53.31.05M$2.00
34GLM 5.2Z.ai (Zhipu AI)151.891.943.81.05M$1.30
35Qwen3.8 27BAlibaba (Qwen)———1M$1.11
36Gemini 3.5 FlashGoogle · +1 variant154.692.837.41.05M$3.38
37DeepSeek V4 Pro 0423DeepSeek149.1——1.05M$0.98
38Claude Sonnet 4.6Anthropic · +1 variant152.383.329.91M$6.00
39Gemini 3.1 Pro PreviewGoogle · +1 variant—94.411.71.05M$4.50
40Qwen3.7 MaxAlibaba (Qwen)153.790.9—1M$2.21
41MiniMax M3MiniMax147.090.9—1.05M$0.53
42Kimi K2.6Moonshot AI151.090.8—262K$1.34
43GLM 5.1Z.ai (Zhipu AI)149.989.9—205K$1.48
44MiMo-V2.5-ProXiaomi———1.05M$0.54
45Kimi K2.7 CodeMoonshot AI150.087.930.5262K$1.34
46Inkling SmallThinking Machines Lab150.1——524K$0.64
47Hy3 previewTencent———262K$0.28
48Qwen3.7 PlusAlibaba (Qwen)147.487.9—1M$0.56
49InklingThinking Machines Lab148.6——524K$1.76
50Grok 4.3xAI · +1 variant———1M$1.56
— means no published score from that source yet · click a model for every benchmark with its source

New - awaiting independent evaluation

All new models →

Not ranked until an independent evaluator (Epoch AI) publishes scores. We don't use vendor-reported benchmark claims for rankings.

Best AI for coding →
Models ranked on DeepSWE
Best AI for reasoning →
Ranked on GPQA Diamond
Best AI for math →
Ranked on competition math
Best open-weight models →
Weights you can run yourself
Cheapest capable models →
Lowest blended API price
Best AI coding tools →
Apps & agents by popularity
Best AI image generators →
Apps & models
Best AI for research →
Answer engines & deep research