Mistral Medium 3.5vsGPT-5.3-Codex

Mistral Medium 3.5
GPT-5.3-Codex
Specifications
Parameters
128B
Context window
256k
Benchmarks
Nonsense detection
BullshitBench v2
24%
Coding
SWE-Bench Verified
77.6%
Next.js coding
Next.js Evals
83%
Community preference (code)
Arena Elo (Code)
1267
1406Best
Overview
CompanyMistralOpenAI
Release dateApr 29 2026Feb 5 2026
AccessOpen WeightProprietary

Which is better: Mistral Medium 3.5 or GPT-5.3-Codex?

GPT-5.3-Codex leads Mistral Medium 3.5 on 1 of the 1 benchmark they both report (Arena Elo (Code)). GPT-5.3-Codex shipped 83 days before Mistral Medium 3.5, so benchmark comparisons should account for the intervening progress.

Mistral Medium 3.5 is open weight, while GPT-5.3-Codex is proprietary.

On Arena Elo (Code), GPT-5.3-Codex leads at 1406 vs Mistral Medium 3.5 at 1267.

Frequently asked questions

Mistral Medium 3.5 was released by Mistral on Apr 29 2026.

GPT-5.3-Codex was released by OpenAI on Feb 5 2026.

Mistral Medium 3.5 is an open weight model released by Mistral. GPT-5.3-Codex is a proprietary model released by OpenAI.

Other comparisons