Model comparison
Mistral Small vs o4-mini
o4-mini is the stronger model overall, scoring 41.6 to 33.4 on the Noometry Index. Mistral Small costs 7.3× less per token, which makes it the better buy when o4-mini'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 scores higher in 0 categories and o4-mini in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where o4-mini leads 40.8 to 16.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 5.8% for Mistral Small and 81.7% for o4-mini.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $1.10 / $4.40 for o4-mini.
- Mistral Small accepts more context: 262K tokens versus 200K.
- Mistral Small has downloadable open weights; the other is API-only.
Side by side
| Mistral Small | o4-mini | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 33.4 | 41.6 |
| Released | 2024-02-26 | 2025-04-16 |
| Weights | Open | Proprietary |
| Context window | 262K | 200K |
| Max output | 256K | 100K |
| Input $ / M tokens | $0.15 | $1.10 |
| Output $ / M tokens | $0.60 | $4.40 |
| Results tracked | 39 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o4-mini leads
Mistral Small: 34.0 (#247), o4-mini: 40.9 (#127)
| Benchmark | Mistral Small | o4-mini |
|---|---|---|
| LMArena Coding | 1362 | 1368 |
| ALE-Bench | 497.62 | 826.17 |
| SWE-bench Verified (bash only) | — | 45% |
| Aider Polyglot | — | 72% |
| SciCode | 26.5% | — |
| GSO | — | 3.6% |
| WeirdML | — | 52.6% |
| BigCodeBench Instruct | 36.1% | — |
| LiveBench Coding | 36.2% | — |
| BigCodeBench Complete | 46.6% | — |
| CadEval | — | 62% |
| AlgoTune | — | 1.72 |
Agentic & Tool Use o4-mini leads
Mistral Small: 28.1 (#93), o4-mini: 32.6 (#61)
| Benchmark | Mistral Small | o4-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.1% | 53.2% |
| GDPval | — | 25.3% |
| METR Time Horizons | — | 63.9% |
Reasoning o4-mini leads
Mistral Small: 19.8 (#250), o4-mini: 24.6 (#162)
| Benchmark | Mistral Small | o4-mini |
|---|---|---|
| Kagi LLM Benchmark | 37.8% | 67.6% |
| CritPt | 0% | 0.6% |
| LMArena Hard Prompts | 1335 | 1351 |
| DTBench | 70.9% | 77.6% |
| LMCA | 20.6% | 26.5% |
| ARC-AGI-2 | — | 6.1% |
| SimpleBench | — | 38.7% |
| ARC-AGI-1 | — | 58.7% |
| Chess Puzzles | — | 26% |
| EnigmaEval | — | 9.2% |
| LiveBench Reasoning | 44.8% | — |
| Mystery Game Puzzles | — | 5% |
| LiveBench Data Analysis | 53.7% | — |
| Epoch Capabilities Index | — | 145.64 |
| ForecastBench | — | 61.8 |
| LiveBench | 44% | — |
Math o4-mini leads
Mistral Small: 16.4 (#293), o4-mini: 40.8 (#89)
| Benchmark | Mistral Small | o4-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 5.8% | 81.7% |
| LMArena Math | 1341 | 1389 |
| MATH Level 5 | 46.8% | 97.8% |
| FrontierMath (Tiers 1-3) | — | 36.1% |
| FrontierMath Tier 4 | — | 4.9% |
| Omni-MATH | — | 72% |
| LiveBench Math | 39.9% | — |
| FrontierMath (Feb 2025 set) | — | 24.8% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge o4-mini leads
Mistral Small: 31.0 (#222), o4-mini: 43.6 (#91)
| Benchmark | Mistral Small | o4-mini |
|---|---|---|
| GPQA Diamond | 47.5% | 79.6% |
| Vectara Hallucination Rate | 5.1% | 18.6% |
| LMArena Expert | 1291 | 1343 |
| Humanity's Last Exam | — | 18.1% |
| SimpleQA Verified | — | 19.6% |
| MMLU-Pro | — | 82% |
| Confabulations | — | 15.8% |
| GPQA (HELM) | — | 73.5% |
| MMLU | 68.7% | — |
Multimodal o4-mini leads
Mistral Small: 33.5 (#96), o4-mini: 40.2 (#49)
| Benchmark | Mistral Small | o4-mini |
|---|---|---|
| LMArena Vision | 1142 | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
Multilingual o4-mini leads
Mistral Small: 45.5 (#169), o4-mini: 47.0 (#154)
| Benchmark | Mistral Small | o4-mini |
|---|---|---|
| LMArena Non-English | 1315 | 1337 |
| LMArena Chinese | 1340 | 1354 |
| LMArena French | 1337 | 1364 |
| LMArena German | 1340 | 1336 |
| LMArena Japanese | 1275 | 1308 |
| LMArena Korean | 1259 | 1312 |
| LMArena Russian | 1324 | 1334 |
| LMArena Spanish | 1346 | 1347 |
Instruction Following o4-mini leads
Mistral Small: 66.4 (#209), o4-mini: 75.2 (#68)
| Benchmark | Mistral Small | o4-mini |
|---|---|---|
| LMArena Instruction Following | 1310 | 1321 |
| LiveBench Instruction Following | 63.7% | — |
| IFEval | — | 92.8% |
Long Context o4-mini leads
Mistral Small: 40.4 (#156), o4-mini: 45.5 (#33)
| Benchmark | Mistral Small | o4-mini |
|---|---|---|
| LMArena Longer Query | 1327 | 1315 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference o4-mini leads
Mistral Small: 52.5 (#171), o4-mini: 54.0 (#152)
| Benchmark | Mistral Small | o4-mini |
|---|---|---|
| LMArena Text | 1338 | 1353 |
| LMArena Creative Writing | 1305 | 1294 |
| LMArena Multi-Turn | 1344 | 1350 |
| Short-Story Creative Writing | — | 75% |
| WildBench | — | 85.4% |
| LiveBench Language | 30.5% | — |
Frequently asked questions
Is Mistral Small better than o4-mini?
o4-mini is the stronger model overall, scoring 41.6 to 33.4 on the Noometry Index. Mistral Small costs 7.3× less per token, which makes it the better buy when o4-mini's lead doesn't matter for your workload.
Which is cheaper, Mistral Small or o4-mini?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; o4-mini lists at $1.10 and $4.40.
Is Mistral Small or o4-mini better for coding?
o4-mini scores higher on coding benchmarks: 40.9 versus 34.0 in the Noometry coding category.
Which has the bigger context window?
Mistral Small does, with 262K tokens against 200K.
How many benchmarks do Mistral Small and o4-mini share?
28 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and o4-mini has 60.