Model comparison
Magistral Small vs o3
o3 is the stronger model overall, scoring 47.5 to 30.2 on the Noometry Index. Magistral Small costs 4.7× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Last verified . 9 shared benchmarks.
Mistral AISummary
- They share 9 benchmarks with published results for both. Magistral Small scores higher in 0 categories and o3 in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where o3 leads 32.0 to 6.8.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 6.3% for Magistral Small and 67.6% for o3.
- Magistral Small is cheaper at $0.50 / $1.50 per million input/output tokens, against $2 / $8 for o3.
- o3 accepts more context: 200K tokens versus 128K.
- Magistral Small has downloadable open weights; the other is API-only.
Side by side
| Magistral Small | o3 | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 30.2 | 47.5 |
| Released | 2025-06-10 | 2025-04-16 |
| Weights | Open | Proprietary |
| Context window | 128K | 200K |
| Max output | 40K | 100K |
| Input $ / M tokens | $0.50 | $2 |
| Output $ / M tokens | $1.50 | $8 |
| Results tracked | 10 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3 leads
Magistral Small: 38.4 (#176), o3: 46.8 (#64)
| Benchmark | Magistral Small | o3 |
|---|---|---|
| SWE-bench Verified | — | 62.3% |
| SWE-bench Verified (bash only) | — | 58.4% |
| Aider Polyglot | — | 81.3% |
| SciCode | 35.2% | — |
| GSO | — | 8.8% |
| WeirdML | — | 52.4% |
| LMArena Coding | — | 1408 |
| CadEval | — | 74% |
| ALE-Bench | — | 933.55 |
Agentic & Tool Use Not comparable
Magistral Small: —, o3: 34.5 (#44)
| Benchmark | Magistral Small | 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
Magistral Small: 6.8 (#350), o3: 32.0 (#78)
| Benchmark | Magistral Small | o3 |
|---|---|---|
| ARC-AGI-2 | 0% | 6.5% |
| Kagi LLM Benchmark | 6.3% | 67.6% |
| ARC-AGI-1 | 5% | 60.8% |
| CritPt | 0.3% | 1.4% |
| Chess Puzzles | 3% | 38% |
| DTBench | 61.3% | 84.8% |
| Epoch Capabilities Index | 133.19 | 146.86 |
| SimpleBench | — | 53.1% |
| EnigmaEval | — | 13.1% |
| LMArena Hard Prompts | — | 1402 |
| Mystery Game Puzzles | — | 29% |
| LMCA | — | 39.7% |
| ForecastBench | — | 62.5 |
Math o3 leads
Magistral Small: 26.2 (#261), o3: 50.2 (#58)
| Benchmark | Magistral Small | o3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 30% | 84.4% |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| Omni-MATH | — | 71.4% |
| LMArena Math | — | 1426 |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 18.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge o3 leads
Magistral Small: 30.9 (#223), o3: 54.6 (#52)
| Benchmark | Magistral Small | o3 |
|---|---|---|
| GPQA Diamond | 56.1% | 81.8% |
| Humanity's Last Exam | — | 20.3% |
| SimpleQA Verified | — | 49.4% |
| MMLU-Pro | — | 85.9% |
| Confabulations | — | 14.4% |
| GPQA (HELM) | — | 75.3% |
| LMArena Expert | — | 1402 |
Multimodal Not comparable
Magistral Small: —, o3: 41.4 (#36)
| Benchmark | Magistral Small | o3 |
|---|---|---|
| LMArena Vision | — | 1214 |
| GeoBench | — | 74% |
| VPCT | — | 52% |
Multilingual Not comparable
Magistral Small: —, o3: 51.7 (#105)
| Benchmark | Magistral Small | 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
Magistral Small: —, o3: 72.8 (#127)
| Benchmark | Magistral Small | o3 |
|---|---|---|
| IFEval | — | 86.9% |
| LMArena Instruction Following | — | 1368 |
Long Context Not comparable
Magistral Small: —, o3: 53.3 (#6)
| Benchmark | Magistral Small | o3 |
|---|---|---|
| Fiction.LiveBench | — | 88.9% |
| CL-bench | — | 17.8% |
| LMArena Longer Query | — | 1372 |
Writing & Preference Not comparable
Magistral Small: —, o3: 63.5 (#64)
| Benchmark | Magistral Small | 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 Magistral Small better than o3?
o3 is the stronger model overall, scoring 47.5 to 30.2 on the Noometry Index. Magistral Small costs 4.7× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Which is cheaper, Magistral Small or o3?
Magistral Small is cheaper. It lists at $0.50 per million input tokens and $1.50 per million output tokens; o3 lists at $2 and $8.
Is Magistral Small or o3 better for coding?
o3 scores higher on coding benchmarks: 46.8 versus 38.4 in the Noometry coding category.
Which has the bigger context window?
o3 does, with 200K tokens against 128K.
How many benchmarks do Magistral Small and o3 share?
9 benchmarks have published results for both models. Magistral Small has 10 scored results on Noometry and o3 has 63.