Model comparison
Ministral 8B vs o1
o1 is the stronger model overall, scoring 40.6 to 27.8 on the Noometry Index. Ministral 8B costs 263× less per token, which makes it the better buy when o1's lead doesn't matter for your workload.
Last verified . 15 shared benchmarks.
Mistral AISummary
- They share 15 benchmarks with published results for both. Ministral 8B scores higher in 0 categories and o1 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o1 leads 41.5 to 12.5.
- The biggest single-benchmark swing is MATH Level 5: 14.9% for Ministral 8B and 94.7% for o1.
- Ministral 8B is cheaper at $0.10 / $0.10 per million input/output tokens, against $15 / $60 for o1.
- o1 accepts more context: 200K tokens versus 128K.
- Ministral 8B has downloadable open weights; the other is API-only.
Side by side
| Ministral 8B | o1 | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 27.8 | 40.6 |
| Released | 2024-10-01 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | 128K | 200K |
| Max output | 128K | 100K |
| Input $ / M tokens | $0.10 | $15 |
| Output $ / M tokens | $0.10 | $60 |
| Results tracked | 17 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1 leads
Ministral 8B: 34.4 (#226), o1: 45.7 (#64)
| Benchmark | Ministral 8B | o1 |
|---|---|---|
| LMArena Coding | 1202 | 1367 |
| Aider Polyglot | — | 61.7% |
| WeirdML | — | 47.6% |
| LiveBench Coding | — | 69.7% |
| CadEval | — | 56% |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |
Agentic & Tool Use o1 leads
Ministral 8B: 16.2 (#140), o1: 24.3 (#111)
| Benchmark | Ministral 8B | o1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 11.1% | — |
| Cybench | — | 10% |
| METR Time Horizons | — | 51.1% |
Reasoning o1 leads
Ministral 8B: 17.7 (#279), o1: 27.5 (#103)
| Benchmark | Ministral 8B | o1 |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1372 |
| DTBench | 45.7% | 74.7% |
| SimpleBench | — | 41.7% |
| ARC-AGI-1 | — | 30.7% |
| Chess Puzzles | — | 15% |
| EnigmaEval | — | 5.7% |
| LiveBench Reasoning | — | 91.6% |
| LiveBench Data Analysis | — | 65.5% |
| LMCA | — | 22.3% |
| Epoch Capabilities Index | — | 141.92 |
| LiveBench | — | 75.7% |
Math o1 leads
Ministral 8B: 23.7 (#262), o1: 34.9 (#150)
| Benchmark | Ministral 8B | o1 |
|---|---|---|
| LMArena Math | 1188 | 1388 |
| MATH Level 5 | 14.9% | 94.7% |
| FrontierMath (Tiers 1-3) | — | 14.7% |
| OTIS Mock AIME 2024-2025 | — | 73.3% |
| LiveBench Math | — | 80.3% |
| FrontierMath (Feb 2025 set) | — | 9.3% |
Knowledge o1 leads
Ministral 8B: 12.5 (#292), o1: 41.5 (#101)
| Benchmark | Ministral 8B | o1 |
|---|---|---|
| GPQA Diamond | 27.1% | 76.8% |
| LMArena Expert | 1170 | 1362 |
| Humanity's Last Exam | — | 8% |
| SimpleQA Verified | — | 41.1% |
| Confabulations | — | 11.7% |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Not comparable
Ministral 8B: —, o1: 33.6 (#87)
| Benchmark | Ministral 8B | o1 |
|---|---|---|
| LMArena Vision | — | 1168 |
| GeoBench | — | 80% |
| VPCT | — | 37% |
| SpatialViz-Bench | — | 41.4% |
Multilingual o1 leads
Ministral 8B: 35.3 (#242), o1: 48.8 (#137)
| Benchmark | Ministral 8B | o1 |
|---|---|---|
| LMArena Non-English | 1165 | 1359 |
| LMArena Chinese | 1193 | 1394 |
| LMArena Russian | 1195 | 1356 |
| LMArena French | — | 1343 |
| LMArena German | — | 1337 |
| LMArena Japanese | — | 1346 |
| LMArena Korean | — | 1396 |
| LMArena Spanish | — | 1345 |
Instruction Following o1 leads
Ministral 8B: 60.7 (#245), o1: 75.0 (#82)
| Benchmark | Ministral 8B | o1 |
|---|---|---|
| LMArena Instruction Following | 1161 | 1368 |
| LiveBench Instruction Following | — | 81.5% |
Long Context o1 leads
Ministral 8B: 36.7 (#222), o1: 50.3 (#9)
| Benchmark | Ministral 8B | o1 |
|---|---|---|
| LMArena Longer Query | 1212 | 1378 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference o1 leads
Ministral 8B: 39.8 (#241), o1: 55.8 (#139)
| Benchmark | Ministral 8B | o1 |
|---|---|---|
| LMArena Text | 1191 | 1366 |
| LMArena Creative Writing | 1175 | 1347 |
| LMArena Multi-Turn | 1166 | 1368 |
| Short-Story Creative Writing | — | 70.2% |
| LiveBench Language | — | 65.4% |
Frequently asked questions
Is Ministral 8B better than o1?
o1 is the stronger model overall, scoring 40.6 to 27.8 on the Noometry Index. Ministral 8B costs 263× less per token, which makes it the better buy when o1's lead doesn't matter for your workload.
Which is cheaper, Ministral 8B or o1?
Ministral 8B is cheaper. It lists at $0.10 per million input tokens and $0.10 per million output tokens; o1 lists at $15 and $60.
Is Ministral 8B or o1 better for coding?
o1 scores higher on coding benchmarks: 45.7 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
o1 does, with 200K tokens against 128K.
How many benchmarks do Ministral 8B and o1 share?
15 benchmarks have published results for both models. Ministral 8B has 17 scored results on Noometry and o1 has 52.