Model comparison
Codestral vs o3-pro
o3-pro is the stronger model overall, scoring 42.9 to 30.6 on the Noometry Index. Codestral costs 78× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.
Last verified . 2 shared benchmarks.
Mistral AISummary
- They share 2 benchmarks with published results for both. Codestral scores higher in 0 categories and o3-pro in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where o3-pro leads 55.5 to 27.3.
- The biggest single-benchmark swing is Aider Polyglot: 11.1% for Codestral and 84.9% for o3-pro.
- Codestral is cheaper at $0.30 / $0.90 per million input/output tokens, against $20 / $80 for o3-pro.
- Codestral accepts more context: 256K tokens versus 200K.
Side by side
| Codestral | o3-pro | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 30.6 | 42.9 |
| Released | 2024-05-29 | 2025-06-10 |
| Weights | Proprietary | Proprietary |
| Context window | 256K | 200K |
| Max output | 8K | 100K |
| Input $ / M tokens | $0.30 | $20 |
| Output $ / M tokens | $0.90 | $80 |
| Results tracked | 7 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
Codestral: 27.3 (#321), o3-pro: 55.5 (#24)
| Benchmark | Codestral | o3-pro |
|---|---|---|
| Aider Polyglot | 11.1% | 84.9% |
| WeirdML | — | 58.2% |
| BigCodeBench Instruct | 41.8% | — |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning o3-pro leads
Codestral: 19.8 (#251), o3-pro: 23.8 (#171)
| Benchmark | Codestral | o3-pro |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | 72.1% |
| ARC-AGI-2 | — | 4.9% |
| ARC-AGI-1 | — | 59.3% |
| DTBench | — | 86.9% |
| LMCA | — | 38.5% |
| Epoch Capabilities Index | — | 147.42 |
Knowledge Not comparable
Codestral: —, o3-pro: 29.5 (#238)
| Benchmark | Codestral | o3-pro |
|---|---|---|
| Confabulations | — | 14.2% |
| Vectara Hallucination Rate | — | 23.3% |
Long Context Not comparable
Codestral: —, o3-pro: 72.2 (#1)
| Benchmark | Codestral | o3-pro |
|---|---|---|
| Fiction.LiveBench | — | 97.2% |
Writing & Preference Not comparable
Codestral: —, o3-pro: 57.1 (#133)
| Benchmark | Codestral | o3-pro |
|---|---|---|
| Short-Story Creative Writing | — | 84.4% |
Frequently asked questions
Is Codestral better than o3-pro?
o3-pro is the stronger model overall, scoring 42.9 to 30.6 on the Noometry Index. Codestral costs 78× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.
Which is cheaper, Codestral or o3-pro?
Codestral is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; o3-pro lists at $20 and $80.
Is Codestral or o3-pro better for coding?
o3-pro scores higher on coding benchmarks: 55.5 versus 27.3 in the Noometry coding category.
Which has the bigger context window?
Codestral does, with 256K tokens against 200K.
How many benchmarks do Codestral and o3-pro share?
2 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and o3-pro has 12.