Model comparison
gpt-oss-20b vs Qwen1.5-32B
gpt-oss-20b is the stronger model overall, scoring 32.1 to 30.0 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. gpt-oss-20b scores higher in 7 categories and Qwen1.5-32B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where gpt-oss-20b leads 34.6 to 13.5.
- The biggest single-benchmark swing is GPQA Diamond: 60.8% for gpt-oss-20b and 30.7% for Qwen1.5-32B.
Side by side
| gpt-oss-20b | Qwen1.5-32B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 32.1 | 30.0 |
| Released | 2025-08-05 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.018 | — |
| Output $ / M tokens | $0.09 | — |
| Results tracked | 34 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding gpt-oss-20b leads
gpt-oss-20b: 37.1 (#185), Qwen1.5-32B: 31.1 (#278)
| Benchmark | gpt-oss-20b | Qwen1.5-32B |
|---|---|---|
| LMArena Coding | 1307 | 1155 |
| SciCode | 34.4% | — |
| WeirdML | 40.9% | — |
| BigCodeBench Instruct | — | 32.3% |
| BigCodeBench Complete | — | 42% |
| ALE-Bench | 566.05 | — |
Agentic & Tool Use Not comparable
gpt-oss-20b: 9.2 (#146), Qwen1.5-32B: —
| Benchmark | gpt-oss-20b | Qwen1.5-32B |
|---|---|---|
| Terminal-Bench | 3.4% | — |
Reasoning Qwen1.5-32B leads
gpt-oss-20b: 18.8 (#251), Qwen1.5-32B: 20.9 (#210)
| Benchmark | gpt-oss-20b | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1274 | 1131 |
| Kagi LLM Benchmark | 53.2% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 4% | — |
| DTBench | 68% | — |
| LMCA | 14.5% | — |
| Epoch Capabilities Index | 137.81 | — |
Math gpt-oss-20b leads
gpt-oss-20b: 37.6 (#93), Qwen1.5-32B: 30.5 (#207)
| Benchmark | gpt-oss-20b | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1317 | 1155 |
| OTIS Mock AIME 2024-2025 | 65.3% | — |
| Omni-MATH | 56.5% | — |
Knowledge gpt-oss-20b leads
gpt-oss-20b: 34.6 (#186), Qwen1.5-32B: 13.5 (#291)
| Benchmark | gpt-oss-20b | Qwen1.5-32B |
|---|---|---|
| GPQA Diamond | 60.8% | 30.7% |
| LMArena Expert | 1258 | 1126 |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |
| MMLU | — | 74.4% |
Multilingual gpt-oss-20b leads
gpt-oss-20b: 42.4 (#192), Qwen1.5-32B: 31.6 (#254)
| Benchmark | gpt-oss-20b | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1269 | 1106 |
| LMArena Chinese | 1311 | 1176 |
| LMArena German | 1249 | 1058 |
| LMArena Japanese | 1245 | 1027 |
| LMArena Korean | 1239 | 1007 |
| LMArena Russian | 1279 | 1073 |
| LMArena Spanish | 1267 | 1089 |
| LMArena French | — | 1100 |
Instruction Following gpt-oss-20b leads
gpt-oss-20b: 62.0 (#235), Qwen1.5-32B: 58.0 (#260)
| Benchmark | gpt-oss-20b | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1236 | 1116 |
| IFEval | 73.2% | — |
Long Context gpt-oss-20b leads
gpt-oss-20b: 37.9 (#203), Qwen1.5-32B: 34.7 (#241)
| Benchmark | gpt-oss-20b | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1251 | 1146 |
Writing & Preference gpt-oss-20b leads
gpt-oss-20b: 35.8 (#260), Qwen1.5-32B: 34.4 (#266)
| Benchmark | gpt-oss-20b | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1288 | 1137 |
| LMArena Creative Writing | 1201 | 1083 |
| LMArena Multi-Turn | 1268 | 1140 |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |
Frequently asked questions
Is gpt-oss-20b better than Qwen1.5-32B?
gpt-oss-20b is the stronger model overall, scoring 32.1 to 30.0 on the Noometry Index.
Is gpt-oss-20b or Qwen1.5-32B better for coding?
gpt-oss-20b scores higher on coding benchmarks: 37.1 versus 31.1 in the Noometry coding category.
How many benchmarks do gpt-oss-20b and Qwen1.5-32B share?
17 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Qwen1.5-32B has 21.