Model comparison
gpt-oss-20b vs Qwen Plus
Qwen Plus is the stronger model overall, scoring 37.1 to 32.5 on the Noometry Index. gpt-oss-20b costs 17× less per token, which makes it the better buy when Qwen Plus's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. gpt-oss-20b scores higher in 2 categories and Qwen Plus in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen Plus leads 52.2 to 35.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 65.3% for gpt-oss-20b and 17.8% for Qwen Plus.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $0.40 / $1.20 for Qwen Plus.
- Qwen Plus accepts more context: 1M tokens versus 131K.
- gpt-oss-20b has downloadable open weights; the other is API-only.
Side by side
| gpt-oss-20b | Qwen Plus | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 32.5 | 37.1 |
| Released | 2025-08-05 | 2024-01-25 |
| Weights | Open | Proprietary |
| Context window | 131K | 1M |
| Max output | 16K | 33K |
| Input $ / M tokens | $0.018 | $0.40 |
| Output $ / M tokens | $0.09 | $1.20 |
| Results tracked | 34 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen Plus leads
gpt-oss-20b: 37.6 (#192), Qwen Plus: 38.9 (#167)
| Benchmark | gpt-oss-20b | Qwen Plus |
|---|---|---|
| LMArena Coding | 1306 | 1328 |
| SciCode | 34.4% | — |
| WeirdML | 40.9% | — |
| ALE-Bench | 566.05 | — |
Agentic & Tool Use Not comparable
gpt-oss-20b: 9.3 (#154), Qwen Plus: —
| Benchmark | gpt-oss-20b | Qwen Plus |
|---|---|---|
| Terminal-Bench | 3.4% | — |
Reasoning Qwen Plus leads
gpt-oss-20b: 19.3 (#261), Qwen Plus: 28.4 (#107)
| Benchmark | gpt-oss-20b | Qwen Plus |
|---|---|---|
| Kagi LLM Benchmark | 53.2% | 63.3% |
| LMArena Hard Prompts | 1274 | 1317 |
| DTBench | 68% | 81.1% |
| LMCA | 14.5% | 24% |
| CritPt | 1.4% | — |
| Chess Puzzles | 4% | — |
| Epoch Capabilities Index | 137.82 | — |
Math gpt-oss-20b leads
gpt-oss-20b: 39.4 (#103), Qwen Plus: 23.3 (#271)
| Benchmark | gpt-oss-20b | Qwen Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 65.3% | 17.8% |
| LMArena Math | 1317 | 1326 |
| Omni-MATH | 56.5% | — |
| MATH Level 5 | — | 65.3% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge gpt-oss-20b leads
gpt-oss-20b: 34.6 (#195), Qwen Plus: 27.4 (#251)
| Benchmark | gpt-oss-20b | Qwen Plus |
|---|---|---|
| GPQA Diamond | 60.8% | 48.1% |
| LMArena Expert | 1258 | 1328 |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |
Multilingual Qwen Plus leads
gpt-oss-20b: 42.2 (#197), Qwen Plus: 45.1 (#175)
| Benchmark | gpt-oss-20b | Qwen Plus |
|---|---|---|
| LMArena Non-English | 1268 | 1310 |
| LMArena Chinese | 1314 | 1347 |
| LMArena Japanese | 1244 | 1251 |
| LMArena Russian | 1278 | 1323 |
| LMArena German | 1255 | — |
| LMArena Korean | 1236 | — |
| LMArena Spanish | 1267 | — |
Instruction Following Qwen Plus leads
gpt-oss-20b: 61.8 (#240), Qwen Plus: 68.8 (#181)
| Benchmark | gpt-oss-20b | Qwen Plus |
|---|---|---|
| LMArena Instruction Following | 1236 | 1303 |
| IFEval | 73.2% | — |
Long Context Qwen Plus leads
gpt-oss-20b: 37.9 (#209), Qwen Plus: 40.3 (#158)
| Benchmark | gpt-oss-20b | Qwen Plus |
|---|---|---|
| LMArena Longer Query | 1250 | 1324 |
Writing & Preference Qwen Plus leads
gpt-oss-20b: 35.5 (#265), Qwen Plus: 52.2 (#176)
| Benchmark | gpt-oss-20b | Qwen Plus |
|---|---|---|
| LMArena Text | 1287 | 1326 |
| LMArena Creative Writing | 1201 | 1293 |
| LMArena Multi-Turn | 1268 | 1336 |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |
Frequently asked questions
Is gpt-oss-20b better than Qwen Plus?
Qwen Plus is the stronger model overall, scoring 37.1 to 32.5 on the Noometry Index. gpt-oss-20b costs 17× less per token, which makes it the better buy when Qwen Plus's lead doesn't matter for your workload.
Which is cheaper, gpt-oss-20b or Qwen Plus?
gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Qwen Plus lists at $0.40 and $1.20.
Is gpt-oss-20b or Qwen Plus better for coding?
Qwen Plus scores higher on coding benchmarks: 38.9 versus 37.6 in the Noometry coding category.
Which has the bigger context window?
Qwen Plus does, with 1M tokens against 131K.
How many benchmarks do gpt-oss-20b and Qwen Plus share?
18 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Qwen Plus has 20.