Model comparison
Ministral 3B vs o3
o3 is the stronger model overall, scoring 47.5 to 26.2 on the Noometry Index. Ministral 3B costs 35× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Last verified . 5 shared benchmarks.
Mistral AISummary
- They share 5 benchmarks with published results for both. Ministral 3B scores higher in 0 categories and o3 in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o3 leads 54.6 to 10.4.
- The biggest single-benchmark swing is MATH Level 5: 14.4% for Ministral 3B and 97.8% for o3.
- Ministral 3B is cheaper at $0.10 / $0.10 per million input/output tokens, against $2 / $8 for o3.
- o3 accepts more context: 200K tokens versus 131K.
- Ministral 3B has downloadable open weights; the other is API-only.
Side by side
| Ministral 3B | o3 | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 26.2 | 47.5 |
| Released | 2024-10-01 | 2025-04-16 |
| Weights | Open | Proprietary |
| Context window | 131K | 200K |
| Max output | 262K | 100K |
| Input $ / M tokens | $0.10 | $2 |
| Output $ / M tokens | $0.10 | $8 |
| Results tracked | 6 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Ministral 3B: —, o3: 46.8 (#64)
| Benchmark | Ministral 3B | o3 |
|---|---|---|
| SWE-bench Verified | — | 62.3% |
| SWE-bench Verified (bash only) | — | 58.4% |
| Aider Polyglot | — | 81.3% |
| GSO | — | 8.8% |
| WeirdML | — | 52.4% |
| LMArena Coding | — | 1408 |
| CadEval | — | 74% |
| ALE-Bench | — | 933.55 |
Agentic & Tool Use Not comparable
Ministral 3B: —, o3: 34.5 (#44)
| Benchmark | Ministral 3B | 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
Ministral 3B: 18.4 (#282), o3: 32.0 (#78)
| Benchmark | Ministral 3B | o3 |
|---|---|---|
| DTBench | 51.7% | 84.8% |
| LMCA | 5.5% | 39.7% |
| Epoch Capabilities Index | 118.1 | 146.86 |
| ARC-AGI-2 | — | 6.5% |
| SimpleBench | — | 53.1% |
| Kagi LLM Benchmark | — | 67.6% |
| ARC-AGI-1 | — | 60.8% |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 38% |
| EnigmaEval | — | 13.1% |
| LMArena Hard Prompts | — | 1402 |
| Mystery Game Puzzles | — | 29% |
| ForecastBench | — | 62.5 |
Math o3 leads
Ministral 3B: 26.6 (#258), o3: 50.2 (#58)
| Benchmark | Ministral 3B | o3 |
|---|---|---|
| MATH Level 5 | 14.4% | 97.8% |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| OTIS Mock AIME 2024-2025 | — | 84.4% |
| Omni-MATH | — | 71.4% |
| LMArena Math | — | 1426 |
| FrontierMath (Feb 2025 set) | — | 18.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge o3 leads
Ministral 3B: 10.4 (#302), o3: 54.6 (#52)
| Benchmark | Ministral 3B | o3 |
|---|---|---|
| GPQA Diamond | 25.3% | 81.8% |
| Humanity's Last Exam | — | 20.3% |
| SimpleQA Verified | — | 49.4% |
| MMLU-Pro | — | 85.9% |
| Confabulations | — | 14.4% |
| Vectara Hallucination Rate | 7.3% | — |
| GPQA (HELM) | — | 75.3% |
| LMArena Expert | — | 1402 |
Multimodal Not comparable
Ministral 3B: —, o3: 41.4 (#36)
| Benchmark | Ministral 3B | o3 |
|---|---|---|
| LMArena Vision | — | 1214 |
| GeoBench | — | 74% |
| VPCT | — | 52% |
Multilingual Not comparable
Ministral 3B: —, o3: 51.7 (#105)
| Benchmark | Ministral 3B | o3 |
|---|---|---|
| LMArena Non-English | — | 1401 |
| LMArena Chinese | — | 1437 |
| LMArena French | — | 1430 |
| LMArena German | — | 1420 |
| LMArena Japanese | — | 1403 |
| LMArena Korean | — | 1370 |
| LMArena Russian | — | 1406 |
| LMArena Spanish | — | 1395 |
Instruction Following Not comparable
Ministral 3B: —, o3: 72.8 (#127)
| Benchmark | Ministral 3B | o3 |
|---|---|---|
| IFEval | — | 86.9% |
| LMArena Instruction Following | — | 1368 |
Long Context Not comparable
Ministral 3B: —, o3: 53.3 (#6)
| Benchmark | Ministral 3B | o3 |
|---|---|---|
| Fiction.LiveBench | — | 88.9% |
| CL-bench | — | 17.8% |
| LMArena Longer Query | — | 1372 |
Writing & Preference Not comparable
Ministral 3B: —, o3: 63.5 (#64)
| Benchmark | Ministral 3B | o3 |
|---|---|---|
| LMArena Text | — | 1410 |
| LMArena Creative Writing | — | 1359 |
| Short-Story Creative Writing | — | 83.9% |
| EQ-Bench Creative Writing | — | 1676 |
| WildBench | — | 86.1% |
| LMArena Multi-Turn | — | 1405 |
Frequently asked questions
Is Ministral 3B better than o3?
o3 is the stronger model overall, scoring 47.5 to 26.2 on the Noometry Index. Ministral 3B costs 35× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Which is cheaper, Ministral 3B or o3?
Ministral 3B is cheaper. It lists at $0.10 per million input tokens and $0.10 per million output tokens; o3 lists at $2 and $8.
Which has the bigger context window?
o3 does, with 200K tokens against 131K.
How many benchmarks do Ministral 3B and o3 share?
5 benchmarks have published results for both models. Ministral 3B has 6 scored results on Noometry and o3 has 63.