Decision workspace
Compare AI Models
Pick two models to compare head-to-head across 107 benchmarks.
Step 1: Pick Model AStep 2: Pick Model B
Popular Comparisons
GPT-5.6 SolvsClaude Sonnet 5
81.96 vs 65.32
Kimi K3vsGPT-5.6 Sol
80.96 vs 81.96
GPT-5.6 SolvsClaude Opus 4.8
81.96 vs 78.34
GPT-5.6 TerravsGemini 3.5 Flash
72.57 vs 64.75
GPT-5.6 LunavsGemini 3.5 Flash
67.17 vs 64.75
Claude Sonnet 5vsClaude Opus 4.8
65.32 vs 78.34
Claude Opus 4.8vsGPT-5.5
78.34 vs 73.51
Claude Opus 4.8vsClaude Opus 4.7 (Adaptive)
78.34 vs 66.27
Gemini 3.5 FlashvsGPT-5.5
64.75 vs 73.51
Gemini 3.5 FlashvsClaude Opus 4.7
64.75 vs 71.94
Gemini 3.5 FlashvsGemini 3.1 Pro
64.75 vs 55.3
GPT-5.5vsClaude Opus 4.7
73.51 vs 71.94
GPT-5.5vsClaude Opus 4.7 (Adaptive)
73.51 vs 66.27
GPT-5.5vsClaude Fable 5
73.51 vs 83.68
GPT-5.5vsClaude Mythos 5
73.51 vs 83.93
GPT-5.5vsGemini 3.1 Pro
73.51 vs 55.3
GPT-5.5vsGemini 3.1 Flash-Lite
73.51 vs 50.83
GPT-5.5vsGLM-5.2
73.51 vs 63.96
GPT-5.5vsGLM-5.1
73.51 vs 67.74
GPT-5.5vsKimi K2.7 Code
73.51 vs 55
GPT-5.5 ProvsClaude Opus 4.7
63.69 vs 71.94
Claude Opus 4.7vsGemini 3.1 Pro
71.94 vs 55.3
GLM-5 (Reasoning)vsGPT-5.5
59.77 vs 73.51
GLM-5.2vsKimi K2.7 Code
63.96 vs 55
GLM-5.1vsKimi K2.7 Code
67.74 vs 55
Ling 2.6 FlashvsKimi K2.7 Code
43.87 vs 55
Ling 2.6 FlashvsGPT-5.5
43.87 vs 73.51
Ling 2.6 FlashvsGLM-5.1
43.87 vs 67.74
Ling 2.6 FlashvsClaude Opus 4.7
43.87 vs 71.94
Qwen3.6-27BvsQwen3.6-35B-A3B
53.82 vs 51.47
Qwen3.6-27BvsQwen3.5-27B
53.82 vs 60.7
Qwen3.6-27BvsGemma 4 31B
53.82 vs 61.08
Claude Mythos 5vsGPT-5.5 Pro
83.93 vs 63.69
Claude Mythos 5vsClaude Opus 4.7
83.93 vs 71.94
Claude Fable 5vsClaude Opus 4.8
83.68 vs 78.34
Claude 3.5 SonnetvsGrok 4
47.74 vs 60.42
GPT-4ovsGrok 4.1
41.49 vs 59.97
Gemini 2.5 Provso3
57.25 vs 47.89
Kimi K2.7 CodevsKimi K2.6
55 vs 56.79
Claude Opus 4.7vsGrok 4.20
71.94 vs 54.68
GPT-4ovsGrok 4
41.49 vs 60.42
Claude 4.1 Opus ThinkingvsGrok 4
36.55 vs 60.42
Claude Opus 4.7vsGrok 4.1 Fast
71.94 vs 51.25
Gemini 3.1 ProvsGrok 3 [Beta]
55.3 vs 40.43
Claude 4 SonnetvsGrok 4
42.79 vs 60.42
Claude Opus 4.7vsGPT-4o
71.94 vs 41.49