Model comparison
Mistral Small 3 vs o3-pro
o3-pro is the stronger model overall, scoring 42.9 to 31.2 on the Noometry Index. Mistral Small 3 costs 609× 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. Mistral Small 3 scores higher in 0 categories and o3-pro in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in long context, where o3-pro leads 72.2 to 37.8.
- The biggest single-benchmark swing is Confabulations: 25.2% for Mistral Small 3 and 14.2% for o3-pro.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $20 / $80 for o3-pro.
- o3-pro accepts more context: 200K tokens versus 33K.
- Mistral Small 3 has downloadable open weights; the other is API-only.
Side by side
| Mistral Small 3 | o3-pro | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 31.2 | 42.9 |
| Released | 2025-01-30 | 2025-06-10 |
| Weights | Open | Proprietary |
| Context window | 33K | 200K |
| Max output | 16K | 100K |
| Input $ / M tokens | $0.05 | $20 |
| Output $ / M tokens | $0.08 | $80 |
| Results tracked | 24 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
Mistral Small 3: 36.5 (#207), o3-pro: 55.5 (#24)
| Benchmark | Mistral Small 3 | o3-pro |
|---|---|---|
| Aider Polyglot | — | 84.9% |
| WeirdML | — | 58.2% |
| BigCodeBench Instruct | 45.3% | — |
| LMArena Coding | 1246 | — |
| BigCodeBench Complete | 50.4% | — |
Reasoning o3-pro leads
Mistral Small 3: 18.9 (#273), o3-pro: 23.8 (#171)
| Benchmark | Mistral Small 3 | o3-pro |
|---|---|---|
| Epoch Capabilities Index | 127.07 | 147.42 |
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 72.1% |
| ARC-AGI-1 | — | 59.3% |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1233 | — |
| DTBench | — | 86.9% |
| LMCA | — | 38.5% |
Math Not comparable
Mistral Small 3: 16.3 (#295), o3-pro: —
| Benchmark | Mistral Small 3 | o3-pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.7% | — |
| LMArena Math | 1240 | — |
Knowledge o3-pro leads
Mistral Small 3: 25.1 (#263), o3-pro: 29.5 (#238)
| Benchmark | Mistral Small 3 | o3-pro |
|---|---|---|
| Confabulations | 25.2% | 14.2% |
| GPQA Diamond | 47.3% | — |
| Vectara Hallucination Rate | — | 23.3% |
| LMArena Expert | 1202 | — |
Multilingual Not comparable
Mistral Small 3: 37.3 (#236), o3-pro: —
| Benchmark | Mistral Small 3 | o3-pro |
|---|---|---|
| LMArena Non-English | 1198 | — |
| LMArena Chinese | 1204 | — |
| LMArena French | 1203 | — |
| LMArena German | 1211 | — |
| LMArena Japanese | 1111 | — |
| LMArena Korean | 1188 | — |
| LMArena Russian | 1216 | — |
Instruction Following Not comparable
Mistral Small 3: 63.7 (#229), o3-pro: —
| Benchmark | Mistral Small 3 | o3-pro |
|---|---|---|
| LMArena Instruction Following | 1214 | — |
Long Context o3-pro leads
Mistral Small 3: 37.8 (#211), o3-pro: 72.2 (#1)
| Benchmark | Mistral Small 3 | o3-pro |
|---|---|---|
| Fiction.LiveBench | — | 97.2% |
| LMArena Longer Query | 1246 | — |
Writing & Preference o3-pro leads
Mistral Small 3: 32.2 (#280), o3-pro: 57.1 (#133)
| Benchmark | Mistral Small 3 | o3-pro |
|---|---|---|
| LMArena Text | 1234 | — |
| LMArena Creative Writing | 1195 | — |
| Short-Story Creative Writing | — | 84.4% |
| EQ-Bench Creative Writing | 707 | — |
| LMArena Multi-Turn | 1217 | — |
Frequently asked questions
Is Mistral Small 3 better than o3-pro?
o3-pro is the stronger model overall, scoring 42.9 to 31.2 on the Noometry Index. Mistral Small 3 costs 609× 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 3 or o3-pro?
Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; o3-pro lists at $20 and $80.
Is Mistral Small 3 or o3-pro better for coding?
o3-pro scores higher on coding benchmarks: 55.5 versus 36.5 in the Noometry coding category.
Which has the bigger context window?
o3-pro does, with 200K tokens against 33K.
How many benchmarks do Mistral Small 3 and o3-pro share?
2 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and o3-pro has 12.