Model comparison
Mistral Nemo vs o3-mini
o3-mini is the stronger model overall, scoring 36.7 to 26.4 on the Noometry Index. Mistral Nemo costs 13× less per token, which makes it the better buy when o3-mini's lead doesn't matter for your workload.
Last verified . 4 shared benchmarks.
Mistral AISummary
- They share 4 benchmarks with published results for both. Mistral Nemo scores higher in 1 category and o3-mini in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o3-mini leads 38.3 to 12.3.
- The biggest single-benchmark swing is MATH Level 5: 10.8% for Mistral Nemo and 96.5% for o3-mini.
- Mistral Nemo is cheaper at $0.15 / $0.15 per million input/output tokens, against $1.10 / $4.40 for o3-mini.
- o3-mini accepts more context: 200K tokens versus 128K.
- Mistral Nemo has downloadable open weights; the other is API-only.
Side by side
| Mistral Nemo | o3-mini | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 26.4 | 36.7 |
| Released | 2024-07-01 | 2024-12-20 |
| Weights | Open | Proprietary |
| Context window | 128K | 200K |
| Max output | 128K | 100K |
| Input $ / M tokens | $0.15 | $1.10 |
| Output $ / M tokens | $0.15 | $4.40 |
| Results tracked | 10 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Mistral Nemo: —, o3-mini: 40.8 (#132)
| Benchmark | Mistral Nemo | o3-mini |
|---|---|---|
| Aider Polyglot | — | 60.4% |
| SciCode | — | 39.8% |
| GSO | — | 1.3% |
| WeirdML | — | 43.7% |
| LiveBench Coding | — | 82.7% |
| LMArena Coding | — | 1378 |
| CadEval | — | 54% |
Agentic & Tool Use o3-mini leads
Mistral Nemo: 23.5 (#125), o3-mini: 29.6 (#84)
| Benchmark | Mistral Nemo | o3-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.6% | — |
| Cybench | — | 22.5% |
| BALROG | 17.6% | — |
Reasoning Mistral Nemo leads
Mistral Nemo: 20.7 (#232), o3-mini: 16.3 (#305)
| Benchmark | Mistral Nemo | o3-mini |
|---|---|---|
| DTBench | 48.6% | 68.8% |
| Epoch Capabilities Index | 118.68 | 140.34 |
| ARC-AGI-2 | — | 3% |
| SimpleBench | — | 22.8% |
| ARC-AGI-1 | — | 34.5% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 17% |
| LiveBench Reasoning | — | 89.6% |
| LMArena Hard Prompts | — | 1366 |
| Mystery Game Puzzles | — | 7% |
| LiveBench Data Analysis | — | 70.6% |
| LMCA | — | 19% |
| ForecastBench | — | 59.6 |
| LiveBench | — | 75.9% |
| PIQA | 83.5% | — |
Math o3-mini leads
Mistral Nemo: 25.5 (#268), o3-mini: 28.1 (#244)
| Benchmark | Mistral Nemo | o3-mini |
|---|---|---|
| MATH Level 5 | 10.8% | 96.5% |
| FrontierMath (Tiers 1-3) | — | 18.6% |
| FrontierMath Tier 4 | — | 0% |
| OTIS Mock AIME 2024-2025 | — | 76.9% |
| LiveBench Math | — | 77.3% |
| LMArena Math | — | 1396 |
| FrontierMath (Feb 2025 set) | — | 12.4% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
| GSM8K | 84.2% | — |
Knowledge o3-mini leads
Mistral Nemo: 12.3 (#298), o3-mini: 38.3 (#146)
| Benchmark | Mistral Nemo | o3-mini |
|---|---|---|
| GPQA Diamond | 29.9% | 77% |
| SimpleQA Verified | — | 15.3% |
| Confabulations | — | 17.9% |
| LMArena Expert | — | 1364 |
| BoolQ | 82.5% | — |
Multilingual Not comparable
Mistral Nemo: —, o3-mini: 45.7 (#164)
| Benchmark | Mistral Nemo | o3-mini |
|---|---|---|
| LMArena Non-English | — | 1319 |
| LMArena Chinese | — | 1379 |
| LMArena French | — | 1334 |
| LMArena German | — | 1303 |
| LMArena Japanese | — | 1286 |
| LMArena Korean | — | 1314 |
| LMArena Russian | — | 1304 |
| LMArena Spanish | — | 1321 |
Instruction Following Not comparable
Mistral Nemo: —, o3-mini: 75.1 (#72)
| Benchmark | Mistral Nemo | o3-mini |
|---|---|---|
| LiveBench Instruction Following | — | 84.4% |
| LMArena Instruction Following | — | 1337 |
Long Context Not comparable
Mistral Nemo: —, o3-mini: 33.8 (#256)
| Benchmark | Mistral Nemo | o3-mini |
|---|---|---|
| Fiction.LiveBench | — | 50% |
| LMArena Longer Query | — | 1343 |
Writing & Preference o3-mini leads
Mistral Nemo: 28.5 (#296), o3-mini: 50.3 (#182)
| Benchmark | Mistral Nemo | o3-mini |
|---|---|---|
| LMArena Text | — | 1337 |
| LMArena Creative Writing | — | 1286 |
| Short-Story Creative Writing | — | 61.7% |
| EQ-Bench Creative Writing | 881 | — |
| LMArena Multi-Turn | — | 1320 |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is Mistral Nemo better than o3-mini?
o3-mini is the stronger model overall, scoring 36.7 to 26.4 on the Noometry Index. Mistral Nemo costs 13× less per token, which makes it the better buy when o3-mini's lead doesn't matter for your workload.
Which is cheaper, Mistral Nemo or o3-mini?
Mistral Nemo is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; o3-mini lists at $1.10 and $4.40.
Which has the bigger context window?
o3-mini does, with 200K tokens against 128K.
How many benchmarks do Mistral Nemo and o3-mini share?
4 benchmarks have published results for both models. Mistral Nemo has 10 scored results on Noometry and o3-mini has 51.