Model Comparisons

Head-to-head comparisons of the models on the AI leaderboard: benchmark scores and API pricing side by side, refreshed weekly. Each page answers the two questions that matter: which is better, and which is cheaper for your workload.

18 matchups · refreshed weekly
Claude Fable 5 92
vs
o3 95.1
Compare in depth →
Claude Fable 5 92
vs
Gemini 2.5 Pro 89.7
Compare in depth →
o3 95.1
vs
Gemini 2.5 Pro 89.7
Compare in depth →
Claude Opus 4.8 89.3
vs
o3 95.1
Compare in depth →
Claude Opus 4.8 89.3
vs
GPT-4.1 88.4
Compare in depth →
Claude Opus 4.8 89.3
vs
Gemini 2.5 Pro 89.7
Compare in depth →
Claude Opus 4.8 89.3
vs
Claude Sonnet 4.6 86.5
Compare in depth →
Claude Sonnet 4.6 86.5
vs
GPT-4o 85.2
Compare in depth →
Claude Sonnet 4.6 86.5
vs
Gemini 2.5 Flash 85.9
Compare in depth →
DeepSeek R1 88.2
vs
o3 95.1
Compare in depth →
DeepSeek R1 88.2
vs
Claude Opus 4.8 89.3
Compare in depth →
DeepSeek R1 88.2
vs
DeepSeek V3 83.9
Compare in depth →
Llama 4 Maverick 87.3
vs
GPT-4o 85.2
Compare in depth →
Gemini 2.5 Pro 89.7
vs
Gemini 2.5 Flash 85.9
Compare in depth →
GPT-4.1 88.4
vs
GPT-4o 85.2
Compare in depth →
Claude Haiku 4.5 79.8
vs
GPT-4o mini 79.8
Compare in depth →
Gemini 2.5 Flash 85.9
vs
GPT-4o mini 79.8
Compare in depth →
Grok 3 84.2
vs
GPT-4.1 88.4
Compare in depth →