Model comparison
Codestral vs GPT-5 Pro
GPT-5 Pro is the stronger model overall, scoring 46.4 to 30.6 on the Noometry Index. Codestral costs 92× less per token, which makes it the better buy when GPT-5 Pro'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 Pro in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5 Pro leads 38.9 to 19.8.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 32.5% for Codestral and 76.8% for GPT-5 Pro.
- Codestral is cheaper at $0.30 / $0.90 per million input/output tokens, against $15 / $120 for GPT-5 Pro.
- GPT-5 Pro accepts more context: 400K tokens versus 256K.
Side by side
| Codestral | GPT-5 Pro | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 30.6 | 46.4 |
| Released | 2024-05-29 | 2025-10-06 |
| Weights | Proprietary | Proprietary |
| Context window | 256K | 400K |
| Max output | 8K | 272K |
| Input $ / M tokens | $0.30 | $15 |
| Output $ / M tokens | $0.90 | $120 |
| Results tracked | 7 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Pro leads
Codestral: 27.3 (#321), GPT-5 Pro: 44.0 (#80)
| Benchmark | Codestral | GPT-5 Pro |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| WeirdML | — | 60.4% |
| BigCodeBench Instruct | 41.8% | — |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| AlgoTune | — | 1.31 |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning GPT-5 Pro leads
Codestral: 19.8 (#251), GPT-5 Pro: 38.9 (#62)
| Benchmark | Codestral | GPT-5 Pro |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | 76.8% |
| ARC-AGI-2 | — | 18.3% |
| SimpleBench | — | 61.6% |
| ARC-AGI-1 | — | 70.2% |
| EnigmaEval | — | 18.8% |
| Epoch Capabilities Index | — | 150.28 |
Math Not comparable
Codestral: —, GPT-5 Pro: 48.5 (#63)
| Benchmark | Codestral | GPT-5 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 55.8% |
| FrontierMath Tier 4 | — | 19.5% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Not comparable
Codestral: —, GPT-5 Pro: 56.7 (#42)
| Benchmark | Codestral | GPT-5 Pro |
|---|---|---|
| Humanity's Last Exam | — | 31.6% |
Frequently asked questions
Is Codestral better than GPT-5 Pro?
GPT-5 Pro is the stronger model overall, scoring 46.4 to 30.6 on the Noometry Index. Codestral costs 92× less per token, which makes it the better buy when GPT-5 Pro's lead doesn't matter for your workload.
Which is cheaper, Codestral or GPT-5 Pro?
Codestral is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; GPT-5 Pro lists at $15 and $120.
Is Codestral or GPT-5 Pro better for coding?
GPT-5 Pro scores higher on coding benchmarks: 44.0 versus 27.3 in the Noometry coding category.
Which has the bigger context window?
GPT-5 Pro does, with 400K tokens against 256K.
How many benchmarks do Codestral and GPT-5 Pro share?
1 benchmark has published results for both models. Codestral has 7 scored results on Noometry and GPT-5 Pro has 12.