Model comparison
gpt-oss-120b vs Qwen Max
gpt-oss-120b is the stronger model overall, scoring 36.3 to 34.7 on the Noometry Index.
Last verified . 21 shared benchmarks.
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. gpt-oss-120b scores higher in 5 categories and Qwen Max in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-120b leads 52.5 to 22.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 88.9% for gpt-oss-120b and 16.1% for Qwen Max.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $1.60 / $6.40 for Qwen Max.
- gpt-oss-120b accepts more context: 131K tokens versus 33K.
- gpt-oss-120b has downloadable open weights; the other is API-only.
Side by side
| gpt-oss-120b | Qwen Max | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 36.3 | 34.7 |
| Released | 2025-08-05 | 2024-04-03 |
| Weights | Open | Proprietary |
| Context window | 131K | 33K |
| Max output | 41K | 8K |
| Input $ / M tokens | $0.037 | $1.60 |
| Output $ / M tokens | $0.17 | $6.40 |
| Results tracked | 48 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding gpt-oss-120b leads
gpt-oss-120b: 33.5 (#256), Qwen Max: 30.7 (#292)
| Benchmark | gpt-oss-120b | Qwen Max |
|---|---|---|
| Aider Polyglot | 41.8% | 21.8% |
| LMArena Coding | 1380 | 1288 |
| SWE-bench Verified (bash only) | 26% | — |
| SciCode | 36% | — |
| WeirdML | 48.2% | — |
| ALE-Bench | 575.62 | — |
| AlgoTune | 1.41 | — |
Agentic & Tool Use Not comparable
gpt-oss-120b: 12.2 (#153), Qwen Max: —
| Benchmark | gpt-oss-120b | Qwen Max |
|---|---|---|
| Terminal-Bench | 18.7% | — |
| APEX-Agents | 4.4% | — |
| METR Time Horizons | 56.6% | — |
| Vending-Bench 2 | -21.53 | — |
Reasoning Qwen Max leads
gpt-oss-120b: 20.0 (#245), Qwen Max: 25.1 (#151)
| Benchmark | gpt-oss-120b | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1364 | 1269 |
| SimpleBench | 22.1% | — |
| Kagi LLM Benchmark | 58.6% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | 20% | — |
| Mystery Game Puzzles | 2% | — |
| DTBench | 76.3% | — |
| LMCA | 22.1% | — |
| Surface Evolver Bench | 25% | — |
| Epoch Capabilities Index | 139.93 | — |
Math gpt-oss-120b leads
gpt-oss-120b: 52.5 (#50), Qwen Max: 22.3 (#276)
| Benchmark | gpt-oss-120b | Qwen Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 16.1% |
| LMArena Math | 1389 | 1275 |
| Omni-MATH | 68.8% | — |
| MATH Level 5 | — | 67.2% |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge gpt-oss-120b leads
gpt-oss-120b: 42.4 (#96), Qwen Max: 30.3 (#228)
| Benchmark | gpt-oss-120b | Qwen Max |
|---|---|---|
| GPQA Diamond | 75.8% | 56.1% |
| LMArena Expert | 1356 | 1248 |
| MMLU-Pro | 79.5% | — |
| Confabulations | 15.7% | — |
| Vectara Hallucination Rate | 14.2% | — |
| GPQA (HELM) | 68.4% | — |
Multilingual gpt-oss-120b leads
gpt-oss-120b: 48.0 (#147), Qwen Max: 41.8 (#202)
| Benchmark | gpt-oss-120b | Qwen Max |
|---|---|---|
| LMArena Non-English | 1351 | 1263 |
| LMArena Chinese | 1385 | 1254 |
| LMArena French | 1369 | 1330 |
| LMArena German | 1353 | 1254 |
| LMArena Japanese | 1331 | 1205 |
| LMArena Korean | 1282 | 1142 |
| LMArena Russian | 1343 | 1274 |
| LMArena Spanish | 1389 | 1290 |
Instruction Following gpt-oss-120b leads
gpt-oss-120b: 69.3 (#173), Qwen Max: 66.5 (#208)
| Benchmark | gpt-oss-120b | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1318 | 1262 |
| IFEval | 83.6% | — |
Long Context Qwen Max leads
gpt-oss-120b: 31.4 (#278), Qwen Max: 39.4 (#180)
| Benchmark | gpt-oss-120b | Qwen Max |
|---|---|---|
| Fiction.LiveBench | 44.4% | 66.7% |
| LMArena Longer Query | 1319 | 1288 |
Writing & Preference Qwen Max leads
gpt-oss-120b: 46.5 (#217), Qwen Max: 47.8 (#205)
| Benchmark | gpt-oss-120b | Qwen Max |
|---|---|---|
| LMArena Text | 1365 | 1282 |
| LMArena Creative Writing | 1275 | 1248 |
| LMArena Multi-Turn | 1340 | 1277 |
| Short-Story Creative Writing | 77.1% | — |
| EQ-Bench Creative Writing | 961 | — |
| WildBench | 84.5% | — |
Frequently asked questions
Is gpt-oss-120b better than Qwen Max?
gpt-oss-120b is the stronger model overall, scoring 36.3 to 34.7 on the Noometry Index.
Which is cheaper, gpt-oss-120b or Qwen Max?
gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; Qwen Max lists at $1.60 and $6.40.
Is gpt-oss-120b or Qwen Max better for coding?
gpt-oss-120b scores higher on coding benchmarks: 33.5 versus 30.7 in the Noometry coding category.
Which has the bigger context window?
gpt-oss-120b does, with 131K tokens against 33K.
How many benchmarks do gpt-oss-120b and Qwen Max share?
21 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Qwen Max has 23.