Model comparison
Ministral 8B vs o3-pro
o3-pro is the stronger model overall, scoring 42.9 to 28.2 on the Noometry Index. Ministral 8B costs 233× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.
Last verified . 2 shared benchmarks.
Mistral AISummary
- They share 2 benchmarks with published results for both. Ministral 8B scores higher in 0 categories and o3-pro in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in long context, where o3-pro leads 72.2 to 36.7.
- The biggest single-benchmark swing is DTBench: 45.7% for Ministral 8B and 86.9% for o3-pro.
- Ministral 8B is cheaper at $0.15 / $0.15 per million input/output tokens, against $20 / $80 for o3-pro.
- Ministral 8B accepts more context: 262K tokens versus 200K.
- Ministral 8B has downloadable open weights; the other is API-only.
Side by side
| Ministral 8B | o3-pro | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 28.2 | 42.9 |
| Released | 2024-10-01 | 2025-06-10 |
| Weights | Open | Proprietary |
| Context window | 262K | 200K |
| Max output | 262K | 100K |
| Input $ / M tokens | $0.15 | $20 |
| Output $ / M tokens | $0.15 | $80 |
| Results tracked | 17 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
Ministral 8B: 35.0 (#230), o3-pro: 55.5 (#24)
| Benchmark | Ministral 8B | o3-pro |
|---|---|---|
| Aider Polyglot | — | 84.9% |
| WeirdML | — | 58.2% |
| LMArena Coding | 1202 | — |
Agentic & Tool Use Not comparable
Ministral 8B: 16.4 (#148), o3-pro: —
| Benchmark | Ministral 8B | o3-pro |
|---|---|---|
| Berkeley Function Calling Leaderboard | 11.1% | — |
Reasoning o3-pro leads
Ministral 8B: 18.4 (#281), o3-pro: 23.8 (#171)
| Benchmark | Ministral 8B | o3-pro |
|---|---|---|
| DTBench | 45.7% | 86.9% |
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 72.1% |
| ARC-AGI-1 | — | 59.3% |
| LMArena Hard Prompts | 1191 | — |
| LMCA | — | 38.5% |
| Epoch Capabilities Index | — | 147.42 |
Math Not comparable
Ministral 8B: 25.7 (#267), o3-pro: —
| Benchmark | Ministral 8B | o3-pro |
|---|---|---|
| LMArena Math | 1188 | — |
| MATH Level 5 | 14.9% | — |
Knowledge o3-pro leads
Ministral 8B: 12.6 (#297), o3-pro: 29.5 (#238)
| Benchmark | Ministral 8B | o3-pro |
|---|---|---|
| Vectara Hallucination Rate | 7.4% | 23.3% |
| GPQA Diamond | 27.1% | — |
| Confabulations | — | 14.2% |
| LMArena Expert | 1170 | — |
Multilingual Not comparable
Ministral 8B: 35.1 (#247), o3-pro: —
| Benchmark | Ministral 8B | o3-pro |
|---|---|---|
| LMArena Non-English | 1165 | — |
| LMArena Chinese | 1193 | — |
| LMArena Russian | 1195 | — |
Instruction Following Not comparable
Ministral 8B: 60.5 (#250), o3-pro: —
| Benchmark | Ministral 8B | o3-pro |
|---|---|---|
| LMArena Instruction Following | 1161 | — |
Long Context o3-pro leads
Ministral 8B: 36.7 (#227), o3-pro: 72.2 (#1)
| Benchmark | Ministral 8B | o3-pro |
|---|---|---|
| Fiction.LiveBench | — | 97.2% |
| LMArena Longer Query | 1212 | — |
Writing & Preference o3-pro leads
Ministral 8B: 39.6 (#246), o3-pro: 57.1 (#133)
| Benchmark | Ministral 8B | o3-pro |
|---|---|---|
| LMArena Text | 1191 | — |
| LMArena Creative Writing | 1175 | — |
| Short-Story Creative Writing | — | 84.4% |
| LMArena Multi-Turn | 1166 | — |
Frequently asked questions
Is Ministral 8B better than o3-pro?
o3-pro is the stronger model overall, scoring 42.9 to 28.2 on the Noometry Index. Ministral 8B costs 233× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.
Which is cheaper, Ministral 8B or o3-pro?
Ministral 8B is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; o3-pro lists at $20 and $80.
Is Ministral 8B or o3-pro better for coding?
o3-pro scores higher on coding benchmarks: 55.5 versus 35.0 in the Noometry coding category.
Which has the bigger context window?
Ministral 8B does, with 262K tokens against 200K.
How many benchmarks do Ministral 8B and o3-pro share?
2 benchmarks have published results for both models. Ministral 8B has 17 scored results on Noometry and o3-pro has 12.