Model comparison
Mistral Small 3.1 vs o3
o3 is the stronger model overall, scoring 47.5 to 31.7 on the Noometry Index. Mistral Small 3.1 costs 8.7× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Last verified . 28 shared benchmarks.
Mistral AISummary
- They share 28 benchmarks with published results for both. Mistral Small 3.1 scores higher in 0 categories and o3 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where o3 leads 50.2 to 14.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 3.9% for Mistral Small 3.1 and 84.4% for o3.
- Mistral Small 3.1 is cheaper at $0.35 / $0.56 per million input/output tokens, against $2 / $8 for o3.
- o3 accepts more context: 200K tokens versus 128K.
- Mistral Small 3.1 has downloadable open weights; the other is API-only.
Side by side
| Mistral Small 3.1 | o3 | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 31.7 | 47.5 |
| Released | 2025-03-17 | 2025-04-16 |
| Weights | Open | Proprietary |
| Context window | 128K | 200K |
| Max output | 102K | 100K |
| Input $ / M tokens | $0.35 | $2 |
| Output $ / M tokens | $0.56 | $8 |
| Results tracked | 28 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3 leads
Mistral Small 3.1: 38.3 (#179), o3: 46.8 (#64)
| Benchmark | Mistral Small 3.1 | o3 |
|---|---|---|
| LMArena Coding | 1309 | 1408 |
| SWE-bench Verified | — | 62.3% |
| SWE-bench Verified (bash only) | — | 58.4% |
| Aider Polyglot | — | 81.3% |
| GSO | — | 8.8% |
| WeirdML | — | 52.4% |
| CadEval | — | 74% |
| ALE-Bench | — | 933.55 |
Agentic & Tool Use Not comparable
Mistral Small 3.1: —, o3: 34.5 (#44)
| Benchmark | Mistral Small 3.1 | o3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 30.8% |
| DeepResearch Bench | — | 45.2% |
| OSWorld | — | 23% |
| LMArena Search | — | 1144 |
| METR Time Horizons | — | 65.4% |
Reasoning o3 leads
Mistral Small 3.1: 19.7 (#254), o3: 32.0 (#78)
| Benchmark | Mistral Small 3.1 | o3 |
|---|---|---|
| Chess Puzzles | 1% | 38% |
| LMArena Hard Prompts | 1278 | 1402 |
| Epoch Capabilities Index | 127.48 | 146.86 |
| ARC-AGI-2 | — | 6.5% |
| SimpleBench | — | 53.1% |
| Kagi LLM Benchmark | — | 67.6% |
| ARC-AGI-1 | — | 60.8% |
| CritPt | — | 1.4% |
| EnigmaEval | — | 13.1% |
| Mystery Game Puzzles | — | 29% |
| DTBench | — | 84.8% |
| LMCA | — | 39.7% |
| ForecastBench | — | 62.5 |
Math o3 leads
Mistral Small 3.1: 14.7 (#301), o3: 50.2 (#58)
| Benchmark | Mistral Small 3.1 | o3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 3.9% | 84.4% |
| Omni-MATH | 24.8% | 71.4% |
| LMArena Math | 1262 | 1426 |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 18.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge o3 leads
Mistral Small 3.1: 22.6 (#271), o3: 54.6 (#52)
| Benchmark | Mistral Small 3.1 | o3 |
|---|---|---|
| GPQA Diamond | 41.9% | 81.8% |
| MMLU-Pro | 61% | 85.9% |
| GPQA (HELM) | 39.2% | 75.3% |
| LMArena Expert | 1257 | 1402 |
| Humanity's Last Exam | — | 20.3% |
| SimpleQA Verified | — | 49.4% |
| Confabulations | — | 14.4% |
Multimodal o3 leads
Mistral Small 3.1: 33.2 (#99), o3: 41.4 (#36)
| Benchmark | Mistral Small 3.1 | o3 |
|---|---|---|
| LMArena Vision | 1136 | 1214 |
| GeoBench | — | 74% |
| VPCT | — | 52% |
Multilingual o3 leads
Mistral Small 3.1: 41.2 (#209), o3: 51.7 (#105)
| Benchmark | Mistral Small 3.1 | o3 |
|---|---|---|
| LMArena Non-English | 1255 | 1401 |
| LMArena Chinese | 1253 | 1437 |
| LMArena French | 1273 | 1430 |
| LMArena German | 1266 | 1420 |
| LMArena Japanese | 1208 | 1403 |
| LMArena Korean | 1206 | 1370 |
| LMArena Russian | 1263 | 1406 |
| LMArena Spanish | 1283 | 1395 |
Instruction Following o3 leads
Mistral Small 3.1: 63.6 (#230), o3: 72.8 (#127)
| Benchmark | Mistral Small 3.1 | o3 |
|---|---|---|
| IFEval | 75% | 86.9% |
| LMArena Instruction Following | 1264 | 1368 |
Long Context o3 leads
Mistral Small 3.1: 39.5 (#178), o3: 53.3 (#6)
| Benchmark | Mistral Small 3.1 | o3 |
|---|---|---|
| LMArena Longer Query | 1299 | 1372 |
| Fiction.LiveBench | — | 88.9% |
| CL-bench | — | 17.8% |
Writing & Preference o3 leads
Mistral Small 3.1: 37.0 (#259), o3: 63.5 (#64)
| Benchmark | Mistral Small 3.1 | o3 |
|---|---|---|
| LMArena Text | 1277 | 1410 |
| LMArena Creative Writing | 1253 | 1359 |
| EQ-Bench Creative Writing | 761 | 1676 |
| WildBench | 78.8% | 86.1% |
| LMArena Multi-Turn | 1270 | 1405 |
| Short-Story Creative Writing | — | 83.9% |
Frequently asked questions
Is Mistral Small 3.1 better than o3?
o3 is the stronger model overall, scoring 47.5 to 31.7 on the Noometry Index. Mistral Small 3.1 costs 8.7× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Which is cheaper, Mistral Small 3.1 or o3?
Mistral Small 3.1 is cheaper. It lists at $0.35 per million input tokens and $0.56 per million output tokens; o3 lists at $2 and $8.
Is Mistral Small 3.1 or o3 better for coding?
o3 scores higher on coding benchmarks: 46.8 versus 38.3 in the Noometry coding category.
Which has the bigger context window?
o3 does, with 200K tokens against 128K.
How many benchmarks do Mistral Small 3.1 and o3 share?
28 benchmarks have published results for both models. Mistral Small 3.1 has 28 scored results on Noometry and o3 has 63.