Model comparison
Codestral vs GPT-5.2 Codex
GPT-5.2 Codex is the stronger model overall, scoring 42.6 to 30.6 on the Noometry Index. Codestral costs 11× less per token, which makes it the better buy when GPT-5.2 Codex's lead doesn't matter for your workload.
Last verified . 1 shared benchmarks.
Mistral AISummary
- They share 1 benchmark with published results for both. Codestral scores higher in 0 categories and GPT-5.2 Codex in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where GPT-5.2 Codex leads 45.5 to 27.3.
- Codestral is cheaper at $0.30 / $0.90 per million input/output tokens, against $1.75 / $14 for GPT-5.2 Codex.
- GPT-5.2 Codex accepts more context: 400K tokens versus 256K.
Side by side
| Codestral | GPT-5.2 Codex | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 30.6 | 42.6 |
| Released | 2024-05-29 | 2025-12-18 |
| Weights | Proprietary | Proprietary |
| Context window | 256K | 400K |
| Max output | 8K | 128K |
| Input $ / M tokens | $0.30 | $1.75 |
| Output $ / M tokens | $0.90 | $14 |
| Results tracked | 7 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.2 Codex leads
Codestral: 27.3 (#321), GPT-5.2 Codex: 45.5 (#71)
| Benchmark | Codestral | GPT-5.2 Codex |
|---|---|---|
| ALE-Bench | 137.78 | 1,300 |
| SWE-bench Verified (bash only) | — | 72.8% |
| Aider Polyglot | 11.1% | — |
| LMArena WebDev | — | 1339 |
| SWE-bench Multilingual | — | 66.3% |
| BigCodeBench Instruct | 41.8% | — |
| BigCodeBench Complete | 52.5% | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Agentic & Tool Use Not comparable
Codestral: —, GPT-5.2 Codex: 41.0 (#22)
| Benchmark | Codestral | GPT-5.2 Codex |
|---|---|---|
| Terminal-Bench | — | 66.5% |
Reasoning Not comparable
Codestral: 19.8 (#251), GPT-5.2 Codex: —
| Benchmark | Codestral | GPT-5.2 Codex |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
Frequently asked questions
Is Codestral better than GPT-5.2 Codex?
GPT-5.2 Codex is the stronger model overall, scoring 42.6 to 30.6 on the Noometry Index. Codestral costs 11× less per token, which makes it the better buy when GPT-5.2 Codex's lead doesn't matter for your workload.
Which is cheaper, Codestral or GPT-5.2 Codex?
Codestral is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; GPT-5.2 Codex lists at $1.75 and $14.
Is Codestral or GPT-5.2 Codex better for coding?
GPT-5.2 Codex scores higher on coding benchmarks: 45.5 versus 27.3 in the Noometry coding category.
Which has the bigger context window?
GPT-5.2 Codex does, with 400K tokens against 256K.
How many benchmarks do Codestral and GPT-5.2 Codex share?
1 benchmark has published results for both models. Codestral has 7 scored results on Noometry and GPT-5.2 Codex has 5.