Compare
Codestral vs GPT-5.5
Codestral (Mistral AI) and GPT-5.5 (OpenAI) compared on benchmarks, pricing, context window, and use-case rankings.
Scores
Intelligence (ECI)—159
Coding—91
Math—97
Reasoning & Knowledge—92
Agentic & Tools—87
Specifications
DeveloperMistral AIOpenAI
Family—GPT
ReleasedJul 30, 2025Apr 23, 2026
Parameters——
AvailabilityOpen weights (non-commercial)API access
Context window—1.1M
Price — $/M input—$5.00
Price — $/M output—$30.00
Inputs—file, image, text
Outputs—text
Benchmarks
AIME 2024/2025—100%
APEX—38%
ARC-AGI—95%
ARC-AGI-2—85%
FrontierMath—52%
FrontierMath Tier 4—35%
GPQA Diamond—94%
GSO (code optimization)—40%
Humanity's Last Exam—44%
SciCode—56%
SimpleBench—69%
SimpleQA Verified—63%
SWE-bench Verified—81%
Terminal-Bench—85%
WebDev Arena—1505
WeirdML—85%
τ²-bench—94%
Use-case scores are 0–100 percentile composites across each area’s benchmarks, ranked against every model from the past year. Highlighted cells lead each row. Open a model for the full picture.
Want a different match-up? Open the compare tool to add or swap models.
More comparisons
Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.