Model comparison
gpt-oss-120b vs o3-mini
gpt-oss-120b and o3-mini score almost the same on the Noometry Index (36.3 vs 36.7), so choose on price, context window or the category you care about most.
Last verified . 32 shared benchmarks.
Summary
- They share 32 benchmarks with published results for both. gpt-oss-120b scores higher in 4 categories and o3-mini in 5 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-120b leads 52.5 to 28.1.
- The biggest single-benchmark swing is Aider Polyglot: 41.8% for gpt-oss-120b and 60.4% for o3-mini.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $1.10 / $4.40 for o3-mini.
- o3-mini accepts more context: 200K tokens versus 131K.
- gpt-oss-120b has downloadable open weights; the other is API-only.
Side by side
| gpt-oss-120b | o3-mini | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 36.3 | 36.7 |
| Released | 2025-08-05 | 2024-12-20 |
| Weights | Open | Proprietary |
| Context window | 131K | 200K |
| Max output | 41K | 100K |
| Input $ / M tokens | $0.037 | $1.10 |
| Output $ / M tokens | $0.17 | $4.40 |
| Results tracked | 48 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
gpt-oss-120b: 33.5 (#256), o3-mini: 40.8 (#132)
| Benchmark | gpt-oss-120b | o3-mini |
|---|---|---|
| Aider Polyglot | 41.8% | 60.4% |
| SciCode | 36% | 39.8% |
| WeirdML | 48.2% | 43.7% |
| LMArena Coding | 1380 | 1378 |
| SWE-bench Verified (bash only) | 26% | — |
| GSO | — | 1.3% |
| LiveBench Coding | — | 82.7% |
| CadEval | — | 54% |
| ALE-Bench | 575.62 | — |
| AlgoTune | 1.41 | — |
Agentic & Tool Use o3-mini leads
gpt-oss-120b: 12.2 (#153), o3-mini: 29.6 (#84)
| Benchmark | gpt-oss-120b | o3-mini |
|---|---|---|
| Terminal-Bench | 18.7% | — |
| APEX-Agents | 4.4% | — |
| Cybench | — | 22.5% |
| METR Time Horizons | 56.6% | — |
| Vending-Bench 2 | -21.53 | — |
Reasoning gpt-oss-120b leads
gpt-oss-120b: 20.0 (#245), o3-mini: 16.3 (#305)
| Benchmark | gpt-oss-120b | o3-mini |
|---|---|---|
| SimpleBench | 22.1% | 22.8% |
| CritPt | 1.1% | 0.3% |
| Chess Puzzles | 20% | 17% |
| LMArena Hard Prompts | 1364 | 1366 |
| Mystery Game Puzzles | 2% | 7% |
| DTBench | 76.3% | 68.8% |
| LMCA | 22.1% | 19% |
| Epoch Capabilities Index | 139.93 | 140.34 |
| ARC-AGI-2 | — | 3% |
| Kagi LLM Benchmark | 58.6% | — |
| ARC-AGI-1 | — | 34.5% |
| LiveBench Reasoning | — | 89.6% |
| LiveBench Data Analysis | — | 70.6% |
| Surface Evolver Bench | 25% | — |
| ForecastBench | — | 59.6 |
| LiveBench | — | 75.9% |
Math gpt-oss-120b leads
gpt-oss-120b: 52.5 (#50), o3-mini: 28.1 (#244)
| Benchmark | gpt-oss-120b | o3-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 76.9% |
| LMArena Math | 1389 | 1396 |
| FrontierMath (Tiers 1-3) | — | 18.6% |
| FrontierMath Tier 4 | — | 0% |
| Omni-MATH | 68.8% | — |
| LiveBench Math | — | 77.3% |
| MATH Level 5 | — | 96.5% |
| FrontierMath (Feb 2025 set) | — | 12.4% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge gpt-oss-120b leads
gpt-oss-120b: 42.4 (#96), o3-mini: 38.3 (#146)
| Benchmark | gpt-oss-120b | o3-mini |
|---|---|---|
| GPQA Diamond | 75.8% | 77% |
| Confabulations | 15.7% | 17.9% |
| LMArena Expert | 1356 | 1364 |
| SimpleQA Verified | — | 15.3% |
| MMLU-Pro | 79.5% | — |
| Vectara Hallucination Rate | 14.2% | — |
| GPQA (HELM) | 68.4% | — |
Multilingual gpt-oss-120b leads
gpt-oss-120b: 48.0 (#147), o3-mini: 45.7 (#164)
| Benchmark | gpt-oss-120b | o3-mini |
|---|---|---|
| LMArena Non-English | 1351 | 1319 |
| LMArena Chinese | 1385 | 1379 |
| LMArena French | 1369 | 1334 |
| LMArena German | 1353 | 1303 |
| LMArena Japanese | 1331 | 1286 |
| LMArena Korean | 1282 | 1314 |
| LMArena Russian | 1343 | 1304 |
| LMArena Spanish | 1389 | 1321 |
Instruction Following o3-mini leads
gpt-oss-120b: 69.3 (#173), o3-mini: 75.1 (#72)
| Benchmark | gpt-oss-120b | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1318 | 1337 |
| LiveBench Instruction Following | — | 84.4% |
| IFEval | 83.6% | — |
Long Context o3-mini leads
gpt-oss-120b: 31.4 (#278), o3-mini: 33.8 (#256)
| Benchmark | gpt-oss-120b | o3-mini |
|---|---|---|
| Fiction.LiveBench | 44.4% | 50% |
| LMArena Longer Query | 1319 | 1343 |
Writing & Preference o3-mini leads
gpt-oss-120b: 46.5 (#217), o3-mini: 50.3 (#182)
| Benchmark | gpt-oss-120b | o3-mini |
|---|---|---|
| LMArena Text | 1365 | 1337 |
| LMArena Creative Writing | 1275 | 1286 |
| Short-Story Creative Writing | 77.1% | 61.7% |
| LMArena Multi-Turn | 1340 | 1320 |
| EQ-Bench Creative Writing | 961 | — |
| WildBench | 84.5% | — |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is gpt-oss-120b better than o3-mini?
gpt-oss-120b and o3-mini score almost the same on the Noometry Index (36.3 vs 36.7), so choose on price, context window or the category you care about most.
Which is cheaper, gpt-oss-120b or o3-mini?
gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; o3-mini lists at $1.10 and $4.40.
Is gpt-oss-120b or o3-mini better for coding?
o3-mini scores higher on coding benchmarks: 40.8 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
o3-mini does, with 200K tokens against 131K.
How many benchmarks do gpt-oss-120b and o3-mini share?
32 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and o3-mini has 51.