Model comparison
Mistral Large 3 vs o4-mini
o4-mini is the stronger model overall, scoring 41.6 to 39.1 on the Noometry Index. Mistral Large 3 costs 5.1× less per token, which makes it the better buy when o4-mini's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
Mistral AISummary
- They share 20 benchmarks with published results for both. Mistral Large 3 scores higher in 2 categories and o4-mini in 7 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where o4-mini leads 24.6 to 15.2.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 50.9% for Mistral Large 3 and 67.6% for o4-mini.
- Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $1.10 / $4.40 for o4-mini.
- Mistral Large 3 accepts more context: 262K tokens versus 200K.
- Mistral Large 3 has downloadable open weights; the other is API-only.
Side by side
| Mistral Large 3 | o4-mini | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 39.1 | 41.6 |
| Released | 2025-12-02 | 2025-04-16 |
| Weights | Open | Proprietary |
| Context window | 262K | 200K |
| Max output | 8K | 100K |
| Input $ / M tokens | $0.25 | $1.10 |
| Output $ / M tokens | $0.75 | $4.40 |
| Results tracked | 24 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o4-mini leads
Mistral Large 3: 34.4 (#237), o4-mini: 40.9 (#127)
| Benchmark | Mistral Large 3 | o4-mini |
|---|---|---|
| LMArena Coding | 1448 | 1368 |
| SWE-bench Verified (bash only) | — | 45% |
| Aider Polyglot | — | 72% |
| LMArena WebDev | 1230 | — |
| GSO | — | 3.6% |
| WeirdML | — | 52.6% |
| CadEval | — | 62% |
| ALE-Bench | — | 826.17 |
| AlgoTune | — | 1.72 |
Agentic & Tool Use Not comparable
Mistral Large 3: —, o4-mini: 32.6 (#61)
| Benchmark | Mistral Large 3 | o4-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 53.2% |
| GDPval | — | 25.3% |
| METR Time Horizons | — | 63.9% |
Reasoning o4-mini leads
Mistral Large 3: 15.2 (#319), o4-mini: 24.6 (#162)
| Benchmark | Mistral Large 3 | o4-mini |
|---|---|---|
| Kagi LLM Benchmark | 50.9% | 67.6% |
| LMArena Hard Prompts | 1429 | 1351 |
| ARC-AGI-2 | — | 6.1% |
| SimpleBench | — | 38.7% |
| NYT Connections (extended) | 7.5% | — |
| ARC-AGI-1 | — | 58.7% |
| CritPt | — | 0.6% |
| Chess Puzzles | — | 26% |
| EnigmaEval | — | 9.2% |
| Thematic Generalization | 23% | — |
| Mystery Game Puzzles | — | 5% |
| DTBench | — | 77.6% |
| LMCA | — | 26.5% |
| Epoch Capabilities Index | — | 145.64 |
| ForecastBench | — | 61.8 |
Math o4-mini leads
Mistral Large 3: 38.7 (#129), o4-mini: 40.8 (#89)
| Benchmark | Mistral Large 3 | o4-mini |
|---|---|---|
| LMArena Math | 1414 | 1389 |
| FrontierMath (Tiers 1-3) | — | 36.1% |
| FrontierMath Tier 4 | — | 4.9% |
| OTIS Mock AIME 2024-2025 | — | 81.7% |
| Omni-MATH | — | 72% |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 24.8% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge o4-mini leads
Mistral Large 3: 36.0 (#177), o4-mini: 43.6 (#91)
| Benchmark | Mistral Large 3 | o4-mini |
|---|---|---|
| Vectara Hallucination Rate | 14.5% | 18.6% |
| LMArena Expert | 1421 | 1343 |
| GPQA Diamond | — | 79.6% |
| Humanity's Last Exam | — | 18.1% |
| SimpleQA Verified | — | 19.6% |
| MMLU-Pro | — | 82% |
| Confabulations | — | 15.8% |
| GPQA (HELM) | — | 73.5% |
Multimodal o4-mini leads
Mistral Large 3: 38.2 (#66), o4-mini: 40.2 (#49)
| Benchmark | Mistral Large 3 | o4-mini |
|---|---|---|
| LMArena Vision | 1221 | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
Multilingual Mistral Large 3 leads
Mistral Large 3: 52.5 (#84), o4-mini: 47.0 (#154)
| Benchmark | Mistral Large 3 | o4-mini |
|---|---|---|
| LMArena Non-English | 1413 | 1337 |
| LMArena Chinese | 1447 | 1354 |
| LMArena French | 1455 | 1364 |
| LMArena German | 1437 | 1336 |
| LMArena Japanese | 1394 | 1308 |
| LMArena Korean | 1384 | 1312 |
| LMArena Russian | 1411 | 1334 |
| LMArena Spanish | 1440 | 1347 |
Instruction Following o4-mini leads
Mistral Large 3: 74.0 (#108), o4-mini: 75.2 (#68)
| Benchmark | Mistral Large 3 | o4-mini |
|---|---|---|
| LMArena Instruction Following | 1403 | 1321 |
| IFEval | — | 92.8% |
Long Context o4-mini leads
Mistral Large 3: 43.1 (#105), o4-mini: 45.5 (#33)
| Benchmark | Mistral Large 3 | o4-mini |
|---|---|---|
| LMArena Longer Query | 1413 | 1315 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference Mistral Large 3 leads
Mistral Large 3: 60.0 (#101), o4-mini: 54.0 (#152)
| Benchmark | Mistral Large 3 | o4-mini |
|---|---|---|
| LMArena Text | 1428 | 1353 |
| LMArena Creative Writing | 1386 | 1294 |
| LMArena Multi-Turn | 1429 | 1350 |
| Short-Story Creative Writing | — | 75% |
| EQ-Bench Creative Writing | 1412 | — |
| WildBench | — | 85.4% |
Frequently asked questions
Is Mistral Large 3 better than o4-mini?
o4-mini is the stronger model overall, scoring 41.6 to 39.1 on the Noometry Index. Mistral Large 3 costs 5.1× less per token, which makes it the better buy when o4-mini's lead doesn't matter for your workload.
Which is cheaper, Mistral Large 3 or o4-mini?
Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; o4-mini lists at $1.10 and $4.40.
Is Mistral Large 3 or o4-mini better for coding?
o4-mini scores higher on coding benchmarks: 40.9 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
Mistral Large 3 does, with 262K tokens against 200K.
How many benchmarks do Mistral Large 3 and o4-mini share?
20 benchmarks have published results for both models. Mistral Large 3 has 24 scored results on Noometry and o4-mini has 60.