Model comparison
gpt-oss-120b vs o1-mini
gpt-oss-120b is the stronger model overall, scoring 36.3 to 34.0 on the Noometry Index.
Last verified . 25 shared benchmarks.
Summary
- They share 25 benchmarks with published results for both. gpt-oss-120b scores higher in 5 categories and o1-mini in 4 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-120b leads 52.5 to 35.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 88.9% for gpt-oss-120b and 46.9% for o1-mini.
- gpt-oss-120b has downloadable open weights; the other is API-only.
Side by side
| gpt-oss-120b | o1-mini | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 36.3 | 34.0 |
| Released | 2025-08-05 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 41K | — |
| Input $ / M tokens | $0.037 | — |
| Output $ / M tokens | $0.17 | — |
| Results tracked | 48 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1-mini leads
gpt-oss-120b: 33.5 (#256), o1-mini: 35.5 (#224)
| Benchmark | gpt-oss-120b | o1-mini |
|---|---|---|
| Aider Polyglot | 41.8% | 32.9% |
| WeirdML | 48.2% | 36.3% |
| LMArena Coding | 1380 | 1362 |
| SWE-bench Verified (bash only) | 26% | — |
| SciCode | 36% | — |
| LiveBench Coding | — | 48% |
| ALE-Bench | 575.62 | — |
| AlgoTune | 1.41 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |
Agentic & Tool Use o1-mini leads
gpt-oss-120b: 12.2 (#153), o1-mini: 24.6 (#118)
| Benchmark | gpt-oss-120b | o1-mini |
|---|---|---|
| Terminal-Bench | 18.7% | — |
| APEX-Agents | 4.4% | — |
| Cybench | — | 10% |
| METR Time Horizons | 56.6% | — |
| Vending-Bench 2 | -21.53 | — |
Reasoning gpt-oss-120b leads
gpt-oss-120b: 20.0 (#245), o1-mini: 8.8 (#346)
| Benchmark | gpt-oss-120b | o1-mini |
|---|---|---|
| SimpleBench | 22.1% | 18.1% |
| LMArena Hard Prompts | 1364 | 1333 |
| Epoch Capabilities Index | 139.93 | 135.82 |
| ARC-AGI-2 | — | 0.8% |
| Kagi LLM Benchmark | 58.6% | — |
| ARC-AGI-1 | — | 14% |
| CritPt | 1.1% | — |
| Chess Puzzles | 20% | — |
| LiveBench Reasoning | — | 72.3% |
| Mystery Game Puzzles | 2% | — |
| DTBench | 76.3% | — |
| LiveBench Data Analysis | — | 57.9% |
| LMCA | 22.1% | — |
| Surface Evolver Bench | 25% | — |
| LiveBench | — | 57.8% |
Math gpt-oss-120b leads
gpt-oss-120b: 52.5 (#50), o1-mini: 35.4 (#186)
| Benchmark | gpt-oss-120b | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 46.9% |
| LMArena Math | 1389 | 1358 |
| Omni-MATH | 68.8% | — |
| LiveBench Math | — | 62% |
| MATH Level 5 | — | 89.2% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge gpt-oss-120b leads
gpt-oss-120b: 42.4 (#96), o1-mini: 34.9 (#192)
| Benchmark | gpt-oss-120b | o1-mini |
|---|---|---|
| GPQA Diamond | 75.8% | 62.4% |
| Confabulations | 15.7% | 18.6% |
| LMArena Expert | 1356 | 1316 |
| MMLU-Pro | 79.5% | — |
| Vectara Hallucination Rate | 14.2% | — |
| GPQA (HELM) | 68.4% | — |
Multilingual gpt-oss-120b leads
gpt-oss-120b: 48.0 (#147), o1-mini: 43.6 (#182)
| Benchmark | gpt-oss-120b | o1-mini |
|---|---|---|
| LMArena Non-English | 1351 | 1289 |
| LMArena Chinese | 1385 | 1314 |
| LMArena French | 1369 | 1293 |
| LMArena German | 1353 | 1278 |
| LMArena Japanese | 1331 | 1245 |
| LMArena Korean | 1282 | 1223 |
| LMArena Russian | 1343 | 1283 |
| LMArena Spanish | 1389 | 1303 |
Instruction Following gpt-oss-120b leads
gpt-oss-120b: 69.3 (#173), o1-mini: 66.7 (#206)
| Benchmark | gpt-oss-120b | o1-mini |
|---|---|---|
| LMArena Instruction Following | 1318 | 1304 |
| LiveBench Instruction Following | — | 65.4% |
| IFEval | 83.6% | — |
Long Context o1-mini leads
gpt-oss-120b: 31.4 (#278), o1-mini: 40.1 (#161)
| Benchmark | gpt-oss-120b | o1-mini |
|---|---|---|
| LMArena Longer Query | 1319 | 1320 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference o1-mini leads
gpt-oss-120b: 46.5 (#217), o1-mini: 48.4 (#202)
| Benchmark | gpt-oss-120b | o1-mini |
|---|---|---|
| LMArena Text | 1365 | 1317 |
| LMArena Creative Writing | 1275 | 1244 |
| Short-Story Creative Writing | 77.1% | 64.9% |
| LMArena Multi-Turn | 1340 | 1314 |
| EQ-Bench Creative Writing | 961 | — |
| WildBench | 84.5% | — |
| LiveBench Language | — | 40.9% |
Frequently asked questions
Is gpt-oss-120b better than o1-mini?
gpt-oss-120b is the stronger model overall, scoring 36.3 to 34.0 on the Noometry Index.
Is gpt-oss-120b or o1-mini better for coding?
o1-mini scores higher on coding benchmarks: 35.5 versus 33.5 in the Noometry coding category.
How many benchmarks do gpt-oss-120b and o1-mini share?
25 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and o1-mini has 39.