Model comparison
gpt-oss-120b vs Mistral Large
gpt-oss-120b is the stronger model overall, scoring 36.3 to 31.9 on the Noometry Index.
Last verified . 35 shared benchmarks.
Mistral AISummary
- They share 35 benchmarks with published results for both. gpt-oss-120b scores higher in 6 categories and Mistral Large in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-120b leads 52.5 to 18.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 88.9% for gpt-oss-120b and 8.5% for Mistral Large.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $2 / $6 for Mistral Large.
Side by side
| gpt-oss-120b | Mistral Large | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 36.3 | 31.9 |
| Released | 2025-08-05 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 131K | 131K |
| Max output | 41K | 16K |
| Input $ / M tokens | $0.037 | $2 |
| Output $ / M tokens | $0.17 | $6 |
| Results tracked | 48 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
gpt-oss-120b: 33.5 (#256), Mistral Large: 34.3 (#240)
| Benchmark | gpt-oss-120b | Mistral Large |
|---|---|---|
| SciCode | 36% | 36.2% |
| LMArena Coding | 1380 | 1277 |
| ALE-Bench | 575.62 | 264.7 |
| SWE-bench Verified (bash only) | 26% | — |
| Aider Polyglot | 41.8% | — |
| WeirdML | 48.2% | — |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| AlgoTune | 1.41 | — |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use Mistral Large leads
gpt-oss-120b: 12.2 (#153), Mistral Large: 28.6 (#89)
| Benchmark | gpt-oss-120b | Mistral Large |
|---|---|---|
| Terminal-Bench | 18.7% | — |
| APEX-Agents | 4.4% | — |
| Berkeley Function Calling Leaderboard | — | 38.4% |
| METR Time Horizons | 56.6% | — |
| Vending-Bench 2 | -21.53 | — |
Reasoning gpt-oss-120b leads
gpt-oss-120b: 20.0 (#245), Mistral Large: 15.8 (#310)
| Benchmark | gpt-oss-120b | Mistral Large |
|---|---|---|
| SimpleBench | 22.1% | 22.5% |
| CritPt | 1.1% | 0% |
| LMArena Hard Prompts | 1364 | 1257 |
| DTBench | 76.3% | 65.1% |
| LMCA | 22.1% | 16.7% |
| Epoch Capabilities Index | 139.93 | 128.52 |
| Kagi LLM Benchmark | 58.6% | — |
| Chess Puzzles | 20% | — |
| LiveBench Reasoning | — | 43.5% |
| Mystery Game Puzzles | 2% | — |
| LiveBench Data Analysis | — | 50.1% |
| Surface Evolver Bench | 25% | — |
| ForecastBench | — | 57.1 |
| LiveBench | — | 48.4% |
Math gpt-oss-120b leads
gpt-oss-120b: 52.5 (#50), Mistral Large: 18.2 (#291)
| Benchmark | gpt-oss-120b | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 8.5% |
| Omni-MATH | 68.8% | 28.1% |
| LMArena Math | 1389 | 1262 |
| LiveBench Math | — | 42.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge gpt-oss-120b leads
gpt-oss-120b: 42.4 (#96), Mistral Large: 30.1 (#230)
| Benchmark | gpt-oss-120b | Mistral Large |
|---|---|---|
| GPQA Diamond | 75.8% | 51.3% |
| MMLU-Pro | 79.5% | 59.9% |
| Confabulations | 15.7% | 21.4% |
| Vectara Hallucination Rate | 14.2% | 4.5% |
| GPQA (HELM) | 68.4% | 43.5% |
| LMArena Expert | 1356 | 1232 |
| MMLU | — | 80% |
Multilingual gpt-oss-120b leads
gpt-oss-120b: 48.0 (#147), Mistral Large: 40.0 (#219)
| Benchmark | gpt-oss-120b | Mistral Large |
|---|---|---|
| LMArena Non-English | 1351 | 1237 |
| LMArena Chinese | 1385 | 1240 |
| LMArena French | 1369 | 1325 |
| LMArena German | 1353 | 1254 |
| LMArena Japanese | 1331 | 1188 |
| LMArena Korean | 1282 | 1202 |
| LMArena Russian | 1343 | 1257 |
| LMArena Spanish | 1389 | 1268 |
Instruction Following gpt-oss-120b leads
gpt-oss-120b: 69.3 (#173), Mistral Large: 67.9 (#191)
| Benchmark | gpt-oss-120b | Mistral Large |
|---|---|---|
| IFEval | 83.6% | 87.7% |
| LMArena Instruction Following | 1318 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
Long Context Mistral Large leads
gpt-oss-120b: 31.4 (#278), Mistral Large: 38.3 (#199)
| Benchmark | gpt-oss-120b | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1319 | 1261 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference gpt-oss-120b leads
gpt-oss-120b: 46.5 (#217), Mistral Large: 40.7 (#242)
| Benchmark | gpt-oss-120b | Mistral Large |
|---|---|---|
| LMArena Text | 1365 | 1266 |
| LMArena Creative Writing | 1275 | 1243 |
| Short-Story Creative Writing | 77.1% | 69% |
| EQ-Bench Creative Writing | 961 | 985 |
| WildBench | 84.5% | 80.1% |
| LMArena Multi-Turn | 1340 | 1260 |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is gpt-oss-120b better than Mistral Large?
gpt-oss-120b is the stronger model overall, scoring 36.3 to 31.9 on the Noometry Index.
Which is cheaper, gpt-oss-120b or Mistral Large?
gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; Mistral Large lists at $2 and $6.
Is gpt-oss-120b or Mistral Large better for coding?
They score almost the same on coding (33.5 vs 34.3); test both on your own repository before choosing.
Which has the bigger context window?
Both accept 131K tokens.
How many benchmarks do gpt-oss-120b and Mistral Large share?
35 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Mistral Large has 51.