Model comparison
Codestral vs o1
o1 is the stronger model overall, scoring 40.9 to 30.6 on the Noometry Index. Codestral costs 58× less per token, which makes it the better buy when o1's lead doesn't matter for your workload.
Last verified . 3 shared benchmarks.
Mistral AISummary
- They share 3 benchmarks with published results for both. Codestral scores higher in 0 categories and o1 in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where o1 leads 46.1 to 27.3.
- The biggest single-benchmark swing is Aider Polyglot: 11.1% for Codestral and 61.7% for o1.
- Codestral is cheaper at $0.30 / $0.90 per million input/output tokens, against $15 / $60 for o1.
- Codestral accepts more context: 256K tokens versus 200K.
Side by side
| Codestral | o1 | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 30.6 | 40.9 |
| Released | 2024-05-29 | 2024-09-12 |
| Weights | Proprietary | Proprietary |
| Context window | 256K | 200K |
| Max output | 8K | 100K |
| Input $ / M tokens | $0.30 | $15 |
| Output $ / M tokens | $0.90 | $60 |
| Results tracked | 7 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1 leads
Codestral: 27.3 (#321), o1: 46.1 (#70)
| Benchmark | Codestral | o1 |
|---|---|---|
| Aider Polyglot | 11.1% | 61.7% |
| HumanEval+ | 73.8% | 89% |
| MBPP+ | 61.9% | 80.2% |
| WeirdML | — | 47.6% |
| BigCodeBench Instruct | 41.8% | — |
| LiveBench Coding | — | 69.7% |
| LMArena Coding | — | 1367 |
| BigCodeBench Complete | 52.5% | — |
| CadEval | — | 56% |
| ALE-Bench | 137.78 | — |
Agentic & Tool Use Not comparable
Codestral: —, o1: 24.6 (#117)
| Benchmark | Codestral | o1 |
|---|---|---|
| Cybench | — | 10% |
| METR Time Horizons | — | 51.1% |
Reasoning o1 leads
Codestral: 19.8 (#251), o1: 27.9 (#111)
| Benchmark | Codestral | o1 |
|---|---|---|
| SimpleBench | — | 41.7% |
| Kagi LLM Benchmark | 32.5% | — |
| ARC-AGI-1 | — | 30.7% |
| Chess Puzzles | — | 15% |
| EnigmaEval | — | 5.7% |
| LiveBench Reasoning | — | 91.6% |
| LMArena Hard Prompts | — | 1371 |
| DTBench | — | 74.7% |
| LiveBench Data Analysis | — | 65.5% |
| LMCA | — | 22.3% |
| Epoch Capabilities Index | — | 141.91 |
| LiveBench | — | 75.7% |
Math Not comparable
Codestral: —, o1: 36.1 (#175)
| Benchmark | Codestral | o1 |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 14.7% |
| OTIS Mock AIME 2024-2025 | — | 73.3% |
| LiveBench Math | — | 80.3% |
| LMArena Math | — | 1388 |
| MATH Level 5 | — | 94.7% |
| FrontierMath (Feb 2025 set) | — | 9.3% |
Knowledge Not comparable
Codestral: —, o1: 41.5 (#110)
| Benchmark | Codestral | o1 |
|---|---|---|
| GPQA Diamond | — | 76.8% |
| Humanity's Last Exam | — | 8% |
| SimpleQA Verified | — | 41.1% |
| Confabulations | — | 11.7% |
| LMArena Expert | — | 1361 |
Multimodal Not comparable
Codestral: —, o1: 34.2 (#93)
| Benchmark | Codestral | o1 |
|---|---|---|
| LMArena Vision | — | 1168 |
| GeoBench | — | 80% |
| VPCT | — | 37% |
| SpatialViz-Bench | — | 41.4% |
Multilingual Not comparable
Codestral: —, o1: 48.6 (#142)
| Benchmark | Codestral | o1 |
|---|---|---|
| LMArena Non-English | — | 1358 |
| LMArena Chinese | — | 1394 |
| LMArena French | — | 1344 |
| LMArena German | — | 1337 |
| LMArena Japanese | — | 1346 |
| LMArena Korean | — | 1396 |
| LMArena Russian | — | 1356 |
| LMArena Spanish | — | 1345 |
Instruction Following Not comparable
Codestral: —, o1: 74.8 (#86)
| Benchmark | Codestral | o1 |
|---|---|---|
| LiveBench Instruction Following | — | 81.5% |
| LMArena Instruction Following | — | 1367 |
Long Context Not comparable
Codestral: —, o1: 50.3 (#9)
| Benchmark | Codestral | o1 |
|---|---|---|
| Fiction.LiveBench | — | 83.3% |
| LMArena Longer Query | — | 1378 |
Writing & Preference Not comparable
Codestral: —, o1: 55.6 (#144)
| Benchmark | Codestral | o1 |
|---|---|---|
| LMArena Text | — | 1366 |
| LMArena Creative Writing | — | 1348 |
| Short-Story Creative Writing | — | 70.2% |
| LMArena Multi-Turn | — | 1369 |
| LiveBench Language | — | 65.4% |
Frequently asked questions
Is Codestral better than o1?
o1 is the stronger model overall, scoring 40.9 to 30.6 on the Noometry Index. Codestral costs 58× less per token, which makes it the better buy when o1's lead doesn't matter for your workload.
Which is cheaper, Codestral or o1?
Codestral is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; o1 lists at $15 and $60.
Is Codestral or o1 better for coding?
o1 scores higher on coding benchmarks: 46.1 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 o1 share?
3 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and o1 has 52.