Model comparison
gpt-oss-120b vs Qwen1.5-72B
gpt-oss-120b is the stronger model overall, scoring 36.3 to 30.8 on the Noometry Index.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. gpt-oss-120b scores higher in 6 categories and Qwen1.5-72B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where gpt-oss-120b leads 42.4 to 11.5.
- The biggest single-benchmark swing is GPQA Diamond: 75.8% for gpt-oss-120b and 28.8% for Qwen1.5-72B.
Side by side
| gpt-oss-120b | Qwen1.5-72B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 36.3 | 30.8 |
| Released | 2025-08-05 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 41K | — |
| Input $ / M tokens | $0.037 | — |
| Output $ / M tokens | $0.17 | — |
| Results tracked | 48 | 22 |
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), Qwen1.5-72B: 31.9 (#277)
| Benchmark | gpt-oss-120b | Qwen1.5-72B |
|---|---|---|
| LMArena Coding | 1380 | 1165 |
| SWE-bench Verified (bash only) | 26% | — |
| Aider Polyglot | 41.8% | — |
| SciCode | 36% | — |
| WeirdML | 48.2% | — |
| BigCodeBench Instruct | — | 33.2% |
| BigCodeBench Complete | — | 40.3% |
| ALE-Bench | 575.62 | — |
| AlgoTune | 1.41 | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |
Agentic & Tool Use Not comparable
gpt-oss-120b: 12.2 (#153), Qwen1.5-72B: —
| Benchmark | gpt-oss-120b | Qwen1.5-72B |
|---|---|---|
| Terminal-Bench | 18.7% | — |
| APEX-Agents | 4.4% | — |
| METR Time Horizons | 56.6% | — |
| Vending-Bench 2 | -21.53 | — |
Reasoning Qwen1.5-72B leads
gpt-oss-120b: 20.0 (#245), Qwen1.5-72B: 22.2 (#203)
| Benchmark | gpt-oss-120b | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1364 | 1148 |
| 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), Qwen1.5-72B: 33.2 (#205)
| Benchmark | gpt-oss-120b | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1389 | 1164 |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| Omni-MATH | 68.8% | — |
Knowledge gpt-oss-120b leads
gpt-oss-120b: 42.4 (#96), Qwen1.5-72B: 11.5 (#300)
| Benchmark | gpt-oss-120b | Qwen1.5-72B |
|---|---|---|
| GPQA Diamond | 75.8% | 28.8% |
| LMArena Expert | 1356 | 1136 |
| 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), Qwen1.5-72B: 33.2 (#253)
| Benchmark | gpt-oss-120b | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1351 | 1135 |
| LMArena Chinese | 1385 | 1186 |
| LMArena French | 1369 | 1159 |
| LMArena German | 1353 | 1084 |
| LMArena Japanese | 1331 | 1061 |
| LMArena Korean | 1282 | 1050 |
| LMArena Russian | 1343 | 1104 |
| LMArena Spanish | 1389 | 1110 |
Instruction Following gpt-oss-120b leads
gpt-oss-120b: 69.3 (#173), Qwen1.5-72B: 59.3 (#256)
| Benchmark | gpt-oss-120b | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1318 | 1141 |
| IFEval | 83.6% | — |
Long Context Qwen1.5-72B leads
gpt-oss-120b: 31.4 (#278), Qwen1.5-72B: 35.1 (#243)
| Benchmark | gpt-oss-120b | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1319 | 1157 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference gpt-oss-120b leads
gpt-oss-120b: 46.5 (#217), Qwen1.5-72B: 37.3 (#258)
| Benchmark | gpt-oss-120b | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1365 | 1166 |
| LMArena Creative Writing | 1275 | 1137 |
| LMArena Multi-Turn | 1340 | 1160 |
| Short-Story Creative Writing | 77.1% | — |
| EQ-Bench Creative Writing | 961 | — |
| WildBench | 84.5% | — |
Frequently asked questions
Is gpt-oss-120b better than Qwen1.5-72B?
gpt-oss-120b is the stronger model overall, scoring 36.3 to 30.8 on the Noometry Index.
Is gpt-oss-120b or Qwen1.5-72B better for coding?
gpt-oss-120b scores higher on coding benchmarks: 33.5 versus 31.9 in the Noometry coding category.
How many benchmarks do gpt-oss-120b and Qwen1.5-72B share?
18 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Qwen1.5-72B has 22.