Model comparison
Mistral Small vs o3-pro
o3-pro is the stronger model overall, scoring 42.9 to 33.4 on the Noometry Index. Mistral Small costs 133× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.
Last verified . 4 shared benchmarks.
Mistral AISummary
- They share 4 benchmarks with published results for both. Mistral Small scores higher in 1 category and o3-pro in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in long context, where o3-pro leads 72.2 to 40.4.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 37.8% for Mistral Small and 72.1% for o3-pro.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $20 / $80 for o3-pro.
- Mistral Small accepts more context: 262K tokens versus 200K.
- Mistral Small has downloadable open weights; the other is API-only.
Side by side
| Mistral Small | o3-pro | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 33.4 | 42.9 |
| Released | 2024-02-26 | 2025-06-10 |
| Weights | Open | Proprietary |
| Context window | 262K | 200K |
| Max output | 256K | 100K |
| Input $ / M tokens | $0.15 | $20 |
| Output $ / M tokens | $0.60 | $80 |
| Results tracked | 39 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
Mistral Small: 34.0 (#247), o3-pro: 55.5 (#24)
| Benchmark | Mistral Small | o3-pro |
|---|---|---|
| Aider Polyglot | — | 84.9% |
| SciCode | 26.5% | — |
| WeirdML | — | 58.2% |
| BigCodeBench Instruct | 36.1% | — |
| LiveBench Coding | 36.2% | — |
| LMArena Coding | 1362 | — |
| BigCodeBench Complete | 46.6% | — |
| ALE-Bench | 497.62 | — |
Agentic & Tool Use Not comparable
Mistral Small: 28.1 (#93), o3-pro: —
| Benchmark | Mistral Small | o3-pro |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.1% | — |
Reasoning o3-pro leads
Mistral Small: 19.8 (#250), o3-pro: 23.8 (#171)
| Benchmark | Mistral Small | o3-pro |
|---|---|---|
| Kagi LLM Benchmark | 37.8% | 72.1% |
| DTBench | 70.9% | 86.9% |
| LMCA | 20.6% | 38.5% |
| ARC-AGI-2 | — | 4.9% |
| ARC-AGI-1 | — | 59.3% |
| CritPt | 0% | — |
| LiveBench Reasoning | 44.8% | — |
| LMArena Hard Prompts | 1335 | — |
| LiveBench Data Analysis | 53.7% | — |
| Epoch Capabilities Index | — | 147.42 |
| LiveBench | 44% | — |
Math Not comparable
Mistral Small: 16.4 (#293), o3-pro: —
| Benchmark | Mistral Small | o3-pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 5.8% | — |
| LiveBench Math | 39.9% | — |
| LMArena Math | 1341 | — |
| MATH Level 5 | 46.8% | — |
Knowledge Mistral Small leads
Mistral Small: 31.0 (#222), o3-pro: 29.5 (#238)
| Benchmark | Mistral Small | o3-pro |
|---|---|---|
| Vectara Hallucination Rate | 5.1% | 23.3% |
| GPQA Diamond | 47.5% | — |
| Confabulations | — | 14.2% |
| LMArena Expert | 1291 | — |
| MMLU | 68.7% | — |
Multimodal Not comparable
Mistral Small: 33.5 (#96), o3-pro: —
| Benchmark | Mistral Small | o3-pro |
|---|---|---|
| LMArena Vision | 1142 | — |
Multilingual Not comparable
Mistral Small: 45.5 (#169), o3-pro: —
| Benchmark | Mistral Small | o3-pro |
|---|---|---|
| LMArena Non-English | 1315 | — |
| LMArena Chinese | 1340 | — |
| LMArena French | 1337 | — |
| LMArena German | 1340 | — |
| LMArena Japanese | 1275 | — |
| LMArena Korean | 1259 | — |
| LMArena Russian | 1324 | — |
| LMArena Spanish | 1346 | — |
Instruction Following Not comparable
Mistral Small: 66.4 (#209), o3-pro: —
| Benchmark | Mistral Small | o3-pro |
|---|---|---|
| LiveBench Instruction Following | 63.7% | — |
| LMArena Instruction Following | 1310 | — |
Long Context o3-pro leads
Mistral Small: 40.4 (#156), o3-pro: 72.2 (#1)
| Benchmark | Mistral Small | o3-pro |
|---|---|---|
| Fiction.LiveBench | — | 97.2% |
| LMArena Longer Query | 1327 | — |
Writing & Preference o3-pro leads
Mistral Small: 52.5 (#171), o3-pro: 57.1 (#133)
| Benchmark | Mistral Small | o3-pro |
|---|---|---|
| LMArena Text | 1338 | — |
| LMArena Creative Writing | 1305 | — |
| Short-Story Creative Writing | — | 84.4% |
| LMArena Multi-Turn | 1344 | — |
| LiveBench Language | 30.5% | — |
Frequently asked questions
Is Mistral Small better than o3-pro?
o3-pro is the stronger model overall, scoring 42.9 to 33.4 on the Noometry Index. Mistral Small costs 133× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.
Which is cheaper, Mistral Small or o3-pro?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; o3-pro lists at $20 and $80.
Is Mistral Small or o3-pro better for coding?
o3-pro scores higher on coding benchmarks: 55.5 versus 34.0 in the Noometry coding category.
Which has the bigger context window?
Mistral Small does, with 262K tokens against 200K.
How many benchmarks do Mistral Small and o3-pro share?
4 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and o3-pro has 12.