Model comparison
gpt-oss-120b vs Ministral 8B
gpt-oss-120b is the stronger model overall, scoring 36.3 to 28.2 on the Noometry Index.
Last verified . 15 shared benchmarks.
Mistral AISummary
- They share 15 benchmarks with published results for both. gpt-oss-120b scores higher in 6 categories and Ministral 8B in 3 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where gpt-oss-120b leads 42.4 to 12.6.
- The biggest single-benchmark swing is GPQA Diamond: 75.8% for gpt-oss-120b and 27.1% for Ministral 8B.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $0.15 / $0.15 for Ministral 8B.
- Ministral 8B accepts more context: 262K tokens versus 131K.
Side by side
| gpt-oss-120b | Ministral 8B | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 36.3 | 28.2 |
| Released | 2025-08-05 | 2024-10-01 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 41K | 262K |
| Input $ / M tokens | $0.037 | $0.15 |
| Output $ / M tokens | $0.17 | $0.15 |
| Results tracked | 48 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Ministral 8B leads
gpt-oss-120b: 33.5 (#256), Ministral 8B: 35.0 (#230)
| Benchmark | gpt-oss-120b | Ministral 8B |
|---|---|---|
| LMArena Coding | 1380 | 1202 |
| SWE-bench Verified (bash only) | 26% | — |
| Aider Polyglot | 41.8% | — |
| SciCode | 36% | — |
| WeirdML | 48.2% | — |
| ALE-Bench | 575.62 | — |
| AlgoTune | 1.41 | — |
Agentic & Tool Use Ministral 8B leads
gpt-oss-120b: 12.2 (#153), Ministral 8B: 16.4 (#148)
| Benchmark | gpt-oss-120b | Ministral 8B |
|---|---|---|
| Terminal-Bench | 18.7% | — |
| APEX-Agents | 4.4% | — |
| Berkeley Function Calling Leaderboard | — | 11.1% |
| METR Time Horizons | 56.6% | — |
| Vending-Bench 2 | -21.53 | — |
Reasoning gpt-oss-120b leads
gpt-oss-120b: 20.0 (#245), Ministral 8B: 18.4 (#281)
| Benchmark | gpt-oss-120b | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1364 | 1191 |
| DTBench | 76.3% | 45.7% |
| SimpleBench | 22.1% | — |
| Kagi LLM Benchmark | 58.6% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | 20% | — |
| Mystery Game Puzzles | 2% | — |
| LMCA | 22.1% | — |
| Surface Evolver Bench | 25% | — |
| Epoch Capabilities Index | 139.93 | — |
Math gpt-oss-120b leads
gpt-oss-120b: 52.5 (#50), Ministral 8B: 25.7 (#267)
| Benchmark | gpt-oss-120b | Ministral 8B |
|---|---|---|
| LMArena Math | 1389 | 1188 |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| Omni-MATH | 68.8% | — |
| MATH Level 5 | — | 14.9% |
Knowledge gpt-oss-120b leads
gpt-oss-120b: 42.4 (#96), Ministral 8B: 12.6 (#297)
| Benchmark | gpt-oss-120b | Ministral 8B |
|---|---|---|
| GPQA Diamond | 75.8% | 27.1% |
| Vectara Hallucination Rate | 14.2% | 7.4% |
| LMArena Expert | 1356 | 1170 |
| MMLU-Pro | 79.5% | — |
| Confabulations | 15.7% | — |
| GPQA (HELM) | 68.4% | — |
Multilingual gpt-oss-120b leads
gpt-oss-120b: 48.0 (#147), Ministral 8B: 35.1 (#247)
| Benchmark | gpt-oss-120b | Ministral 8B |
|---|---|---|
| LMArena Non-English | 1351 | 1165 |
| LMArena Chinese | 1385 | 1193 |
| LMArena Russian | 1343 | 1195 |
| LMArena French | 1369 | — |
| LMArena German | 1353 | — |
| LMArena Japanese | 1331 | — |
| LMArena Korean | 1282 | — |
| LMArena Spanish | 1389 | — |
Instruction Following gpt-oss-120b leads
gpt-oss-120b: 69.3 (#173), Ministral 8B: 60.5 (#250)
| Benchmark | gpt-oss-120b | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1318 | 1161 |
| IFEval | 83.6% | — |
Long Context Ministral 8B leads
gpt-oss-120b: 31.4 (#278), Ministral 8B: 36.7 (#227)
| Benchmark | gpt-oss-120b | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 1319 | 1212 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference gpt-oss-120b leads
gpt-oss-120b: 46.5 (#217), Ministral 8B: 39.6 (#246)
| Benchmark | gpt-oss-120b | Ministral 8B |
|---|---|---|
| LMArena Text | 1365 | 1191 |
| LMArena Creative Writing | 1275 | 1175 |
| LMArena Multi-Turn | 1340 | 1166 |
| Short-Story Creative Writing | 77.1% | — |
| EQ-Bench Creative Writing | 961 | — |
| WildBench | 84.5% | — |
Frequently asked questions
Is gpt-oss-120b better than Ministral 8B?
gpt-oss-120b is the stronger model overall, scoring 36.3 to 28.2 on the Noometry Index.
Which is cheaper, gpt-oss-120b or Ministral 8B?
gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; Ministral 8B lists at $0.15 and $0.15.
Is gpt-oss-120b or Ministral 8B better for coding?
Ministral 8B scores higher on coding benchmarks: 35.0 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
Ministral 8B does, with 262K tokens against 131K.
How many benchmarks do gpt-oss-120b and Ministral 8B share?
15 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Ministral 8B has 17.