Mistral Medium 3.5vsGPT-5.3-Codex-Spark
Mistral Medium 3.5 | GPT-5.3-Codex-Spark | |
|---|---|---|
| Specifications | ||
Parameters | 128B | — |
Context window | 256k | 128k |
| Benchmarks | ||
Coding SWE-Bench VerifiedReal coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 77.6% | — |
Community preference (code) Arena Elo (Code)Like the text arena, but people vote on which AI writes better code. The votes become a chess-style Elo rating on arena.ai. Higher is better. | 1267 | — |
| Overview | ||
| Company | Mistral | OpenAI |
| Release date | Apr 29 2026 | Feb 12 2026 |
| Access | Open Weight | Proprietary |
Which is better: Mistral Medium 3.5 or GPT-5.3-Codex-Spark?
Mistral Medium 3.5 and GPT-5.3-Codex-Spark don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. GPT-5.3-Codex-Spark shipped 76 days before Mistral Medium 3.5, so benchmark comparisons should account for the intervening progress.
Context windows are 256k (Mistral Medium 3.5) vs 128k (GPT-5.3-Codex-Spark). Mistral Medium 3.5 is open weight, while GPT-5.3-Codex-Spark is proprietary.
Direct benchmark comparisons are unavailable — Mistral Medium 3.5 and GPT-5.3-Codex-Spark don't publish scores on any of the same benchmarks.
Frequently asked questions
Mistral Medium 3.5 was released by Mistral on Apr 29 2026.
GPT-5.3-Codex-Spark was released by OpenAI on Feb 12 2026.
Mistral Medium 3.5 has a 256k context window; GPT-5.3-Codex-Spark has 128k.
Mistral Medium 3.5 is an open weight model released by Mistral. GPT-5.3-Codex-Spark is a proprietary model released by OpenAI.