Model comparison
Mistral Small vs o3-mini
o3-mini is the stronger model overall, scoring 36.7 to 33.1 on the Noometry Index. Mistral Small costs 7.3× less per token, which makes it the better buy when o3-mini's lead doesn't matter for your workload.
Last verified . 31 shared benchmarks.
Mistral AISummary
- They share 31 benchmarks with published results for both. Mistral Small scores higher in 3 categories and o3-mini in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where o3-mini leads 27.6 to 15.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 5.8% for Mistral Small and 76.9% for o3-mini.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $1.10 / $4.40 for o3-mini.
- Mistral Small accepts more context: 256K tokens versus 200K.
- Mistral Small has downloadable open weights; the other is API-only.
Side by side
| Mistral Small | o3-mini | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 33.1 | 36.7 |
| Released | 2024-02-26 | 2024-12-20 |
| Weights | Open | Proprietary |
| Context window | 256K | 200K |
| Max output | 256K | 100K |
| Input $ / M tokens | $0.15 | $1.10 |
| Output $ / M tokens | $0.60 | $4.40 |
| Results tracked | 39 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
Mistral Small: 33.5 (#242), o3-mini: 41.4 (#116)
| Benchmark | Mistral Small | o3-mini |
|---|---|---|
| SciCode | 26.5% | 39.8% |
| LiveBench Coding | 36.2% | 82.7% |
| LMArena Coding | 1363 | 1378 |
| Aider Polyglot | — | 60.4% |
| GSO | — | 1.3% |
| WeirdML | — | 43.7% |
| BigCodeBench Instruct | 36.1% | — |
| BigCodeBench Complete | 46.6% | — |
| CadEval | — | 54% |
| ALE-Bench | 497.62 | — |
Agentic & Tool Use o3-mini leads
Mistral Small: 27.9 (#87), o3-mini: 29.3 (#79)
| Benchmark | Mistral Small | o3-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.1% | — |
| Cybench | — | 22.5% |
Reasoning Mistral Small leads
Mistral Small: 19.3 (#238), o3-mini: 16.3 (#295)
| Benchmark | Mistral Small | o3-mini |
|---|---|---|
| CritPt | 0% | 0.3% |
| LiveBench Reasoning | 44.8% | 89.6% |
| LMArena Hard Prompts | 1336 | 1366 |
| DTBench | 70.9% | 68.8% |
| LiveBench Data Analysis | 53.7% | 70.6% |
| LMCA | 20.6% | 19% |
| LiveBench | 44% | 75.9% |
| ARC-AGI-2 | — | 3% |
| SimpleBench | — | 22.8% |
| Kagi LLM Benchmark | 37.8% | — |
| ARC-AGI-1 | — | 34.5% |
| Chess Puzzles | — | 17% |
| Mystery Game Puzzles | — | 7% |
| Epoch Capabilities Index | — | 140.35 |
| ForecastBench | — | 59.6 |
Math o3-mini leads
Mistral Small: 15.4 (#287), o3-mini: 27.6 (#236)
| Benchmark | Mistral Small | o3-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 5.8% | 76.9% |
| LiveBench Math | 39.9% | 77.3% |
| LMArena Math | 1341 | 1396 |
| MATH Level 5 | 46.8% | 96.5% |
| FrontierMath (Tiers 1-3) | — | 18.6% |
| FrontierMath Tier 4 | — | 0% |
| FrontierMath (Feb 2025 set) | — | 12.4% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge o3-mini leads
Mistral Small: 30.9 (#214), o3-mini: 38.3 (#135)
| Benchmark | Mistral Small | o3-mini |
|---|---|---|
| GPQA Diamond | 47.5% | 77% |
| LMArena Expert | 1293 | 1364 |
| SimpleQA Verified | — | 15.3% |
| Confabulations | — | 17.9% |
| Vectara Hallucination Rate | 5.1% | — |
| MMLU | 68.7% | — |
Multimodal Not comparable
Mistral Small: 32.9 (#91), o3-mini: —
| Benchmark | Mistral Small | o3-mini |
|---|---|---|
| LMArena Vision | 1142 | — |
Multilingual Too close to call
Mistral Small: 45.7 (#164), o3-mini: 45.9 (#159)
| Benchmark | Mistral Small | o3-mini |
|---|---|---|
| LMArena Non-English | 1315 | 1319 |
| LMArena Chinese | 1342 | 1379 |
| LMArena French | 1337 | 1333 |
| LMArena German | 1341 | 1303 |
| LMArena Japanese | 1275 | 1286 |
| LMArena Korean | 1260 | 1314 |
| LMArena Russian | 1324 | 1304 |
| LMArena Spanish | 1346 | 1321 |
Instruction Following o3-mini leads
Mistral Small: 66.6 (#204), o3-mini: 75.3 (#67)
| Benchmark | Mistral Small | o3-mini |
|---|---|---|
| LiveBench Instruction Following | 63.7% | 84.4% |
| LMArena Instruction Following | 1310 | 1338 |
Long Context Mistral Small leads
Mistral Small: 40.4 (#151), o3-mini: 33.8 (#251)
| Benchmark | Mistral Small | o3-mini |
|---|---|---|
| LMArena Longer Query | 1327 | 1343 |
| Fiction.LiveBench | — | 50% |
Writing & Preference Mistral Small leads
Mistral Small: 52.6 (#165), o3-mini: 50.4 (#177)
| Benchmark | Mistral Small | o3-mini |
|---|---|---|
| LMArena Text | 1338 | 1337 |
| LMArena Creative Writing | 1304 | 1286 |
| LMArena Multi-Turn | 1344 | 1320 |
| LiveBench Language | 30.5% | 50.7% |
| Short-Story Creative Writing | — | 61.7% |
Frequently asked questions
Is Mistral Small better than o3-mini?
o3-mini is the stronger model overall, scoring 36.7 to 33.1 on the Noometry Index. Mistral Small costs 7.3× less per token, which makes it the better buy when o3-mini's lead doesn't matter for your workload.
Which is cheaper, Mistral Small or o3-mini?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; o3-mini lists at $1.10 and $4.40.
Is Mistral Small or o3-mini better for coding?
o3-mini scores higher on coding benchmarks: 41.4 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
Mistral Small does, with 256K tokens against 200K.
How many benchmarks do Mistral Small and o3-mini share?
31 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and o3-mini has 51.