Model Comparison

Head-to-head benchmark, pricing, and spec comparison between any two AI models.

Provider
Anthropic
Context Window200K tokens
Input Cost$15.00/M tokens
Output Cost$75.00/M tokens
Release2026-05
Modalitiestext, vision, code
Intelligence
97
Speed
72
Provider
OpenAI
Context Window128K tokens
Input Cost$2.50/M tokens
Output Cost$10.00/M tokens
Release2024-05
Modalitiestext, vision, code, audio
Intelligence
88
Speed
82

Benchmark Comparison

MMLUKnowledge
92.0
vs
87.2
HumanEvalCoding
84.9
vs
90.2
MATHReasoning
71.1
vs
76.6
GPQA DiamondScience
74.3
vs
53.6
SWE-bench VerifiedCoding
72.5
vs
33.2
MMMUMultimodal
73.8
vs
69.1
ARC ChallengeReasoning
96.4
vs
96.7
HellaSwagLanguage
95.4
vs
95.3