Model comparison
gpt-oss-120b vs Qwen3 Max
Qwen3 Max is the stronger model overall, scoring 43.5 to 36.0 on the Noometry Index. gpt-oss-120b costs 34× less per token, which makes it the better buy when Qwen3 Max's lead doesn't matter for your workload.
Last verified . 28 shared benchmarks.
Alibaba (Qwen)Summary
- They share 28 benchmarks with published results for both. gpt-oss-120b scores higher in 1 category and Qwen3 Max in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3 Max leads 62.6 to 46.7.
- The biggest single-benchmark swing is Fiction.LiveBench: 44.4% for gpt-oss-120b and 66.7% for Qwen3 Max.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $1.20 / $6 for Qwen3 Max.
- Qwen3 Max accepts more context: 262K tokens versus 131K.
- gpt-oss-120b has downloadable open weights; the other is API-only.
Side by side
| gpt-oss-120b | Qwen3 Max | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 36.0 | 43.5 |
| Released | 2025-08-05 | 2025-09-23 |
| Weights | Open | Proprietary |
| Context window | 131K | 262K |
| Max output | 41K | 66K |
| Input $ / M tokens | $0.037 | $1.20 |
| Output $ / M tokens | $0.17 | $6 |
| Results tracked | 48 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 Max leads
gpt-oss-120b: 33.2 (#251), Qwen3 Max: 42.4 (#93)
| Benchmark | gpt-oss-120b | Qwen3 Max |
|---|---|---|
| LMArena Coding | 1380 | 1456 |
| ALE-Bench | 575.62 | 370.45 |
| SWE-bench Verified (bash only) | 26% | — |
| Aider Polyglot | 41.8% | — |
| SciCode | 36% | — |
| WeirdML | 48.2% | — |
| AlgoTune | 1.41 | — |
Agentic & Tool Use Not comparable
gpt-oss-120b: 12.1 (#145), Qwen3 Max: —
| Benchmark | gpt-oss-120b | Qwen3 Max |
|---|---|---|
| Vending-Bench 2 | -21.53 | 71.56 |
| Terminal-Bench | 18.7% | — |
| APEX-Agents | 4.4% | — |
| METR Time Horizons | 56.6% | — |
Reasoning Qwen3 Max leads
gpt-oss-120b: 19.5 (#236), Qwen3 Max: 22.0 (#186)
| Benchmark | gpt-oss-120b | Qwen3 Max |
|---|---|---|
| Kagi LLM Benchmark | 58.6% | 72.5% |
| Chess Puzzles | 20% | 4% |
| LMArena Hard Prompts | 1364 | 1448 |
| Mystery Game Puzzles | 2% | 5% |
| DTBench | 76.3% | 82.1% |
| LMCA | 22.1% | 28.3% |
| Epoch Capabilities Index | 139.94 | 142.41 |
| SimpleBench | 22.1% | — |
| NYT Connections (extended) | — | 30.1% |
| CritPt | 1.1% | — |
| Surface Evolver Bench | 25% | — |
Math gpt-oss-120b leads
gpt-oss-120b: 50.6 (#43), Qwen3 Max: 37.6 (#94)
| Benchmark | gpt-oss-120b | Qwen3 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 73.3% |
| LMArena Math | 1388 | 1447 |
| FrontierMath (Tiers 1-3) | — | 18.9% |
| Omni-MATH | 68.8% | — |
| MATH Level 5 | — | 97.1% |
Knowledge Qwen3 Max leads
gpt-oss-120b: 42.3 (#89), Qwen3 Max: 48.1 (#72)
| Benchmark | gpt-oss-120b | Qwen3 Max |
|---|---|---|
| GPQA Diamond | 75.8% | 72.6% |
| LMArena Expert | 1356 | 1457 |
| SimpleQA Verified | — | 48.7% |
| MMLU-Pro | 79.5% | — |
| Confabulations | 15.7% | — |
| Vectara Hallucination Rate | 14.2% | — |
| GPQA (HELM) | 68.4% | — |
Multilingual Qwen3 Max leads
gpt-oss-120b: 48.2 (#142), Qwen3 Max: 53.9 (#58)
| Benchmark | gpt-oss-120b | Qwen3 Max |
|---|---|---|
| LMArena Non-English | 1350 | 1429 |
| LMArena Chinese | 1384 | 1479 |
| LMArena French | 1370 | 1450 |
| LMArena German | 1355 | 1463 |
| LMArena Japanese | 1332 | 1399 |
| LMArena Korean | 1283 | 1397 |
| LMArena Russian | 1343 | 1428 |
| LMArena Spanish | 1388 | 1463 |
Instruction Following Qwen3 Max leads
gpt-oss-120b: 69.5 (#168), Qwen3 Max: 75.0 (#81)
| Benchmark | gpt-oss-120b | Qwen3 Max |
|---|---|---|
| LMArena Instruction Following | 1318 | 1420 |
| IFEval | 83.6% | — |
Long Context Qwen3 Max leads
gpt-oss-120b: 31.4 (#273), Qwen3 Max: 41.6 (#129)
| Benchmark | gpt-oss-120b | Qwen3 Max |
|---|---|---|
| Fiction.LiveBench | 44.4% | 66.7% |
| LMArena Longer Query | 1319 | 1439 |
| CL-bench | — | 14.5% |
Writing & Preference Qwen3 Max leads
gpt-oss-120b: 46.7 (#213), Qwen3 Max: 62.6 (#72)
| Benchmark | gpt-oss-120b | Qwen3 Max |
|---|---|---|
| LMArena Text | 1366 | 1439 |
| LMArena Creative Writing | 1274 | 1401 |
| LMArena Multi-Turn | 1340 | 1446 |
| Short-Story Creative Writing | 77.1% | — |
| EQ-Bench Creative Writing | 961 | — |
| WildBench | 84.5% | — |
Frequently asked questions
Is gpt-oss-120b better than Qwen3 Max?
Qwen3 Max is the stronger model overall, scoring 43.5 to 36.0 on the Noometry Index. gpt-oss-120b costs 34× less per token, which makes it the better buy when Qwen3 Max's lead doesn't matter for your workload.
Which is cheaper, gpt-oss-120b or Qwen3 Max?
gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; Qwen3 Max lists at $1.20 and $6.
Is gpt-oss-120b or Qwen3 Max better for coding?
Qwen3 Max scores higher on coding benchmarks: 42.4 versus 33.2 in the Noometry coding category.
Which has the bigger context window?
Qwen3 Max does, with 262K tokens against 131K.
How many benchmarks do gpt-oss-120b and Qwen3 Max share?
28 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Qwen3 Max has 33.