Model comparison
gpt-oss-20b vs Qwen3.7 Plus
Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 32.5 on the Noometry Index. gpt-oss-20b costs 19× less per token, which makes it the better buy when Qwen3.7 Plus's lead doesn't matter for your workload.
Last verified . 24 shared benchmarks.
Alibaba (Qwen)Summary
- They share 24 benchmarks with published results for both. gpt-oss-20b scores higher in 1 category and Qwen3.7 Plus in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.7 Plus leads 64.3 to 35.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 65.3% for gpt-oss-20b and 93.3% for Qwen3.7 Plus.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $0.40 / $1.60 for Qwen3.7 Plus.
- Qwen3.7 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 | Qwen3.7 Plus | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 32.5 | 45.3 |
| Released | 2025-08-05 | 2026-06-02 |
| Weights | Open | Proprietary |
| Context window | 131K | 1M |
| Max output | 16K | 131K |
| Input $ / M tokens | $0.018 | $0.40 |
| Output $ / M tokens | $0.09 | $1.60 |
| Results tracked | 34 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding gpt-oss-20b leads
gpt-oss-20b: 37.6 (#192), Qwen3.7 Plus: 36.6 (#206)
| Benchmark | gpt-oss-20b | Qwen3.7 Plus |
|---|---|---|
| SciCode | 34.4% | 45.5% |
| LMArena Coding | 1306 | 1473 |
| FrontierCode | — | 10.2% |
| WeirdML | 40.9% | — |
| ALE-Bench | 566.05 | — |
Agentic & Tool Use Qwen3.7 Plus leads
gpt-oss-20b: 9.3 (#154), Qwen3.7 Plus: 21.4 (#138)
| Benchmark | gpt-oss-20b | Qwen3.7 Plus |
|---|---|---|
| Terminal-Bench | 3.4% | — |
| OSWorld 2.0 | — | 2.8% |
Reasoning Qwen3.7 Plus leads
gpt-oss-20b: 19.3 (#261), Qwen3.7 Plus: 39.3 (#59)
| Benchmark | gpt-oss-20b | Qwen3.7 Plus |
|---|---|---|
| CritPt | 1.4% | 9.1% |
| Chess Puzzles | 4% | 24% |
| LMArena Hard Prompts | 1274 | 1460 |
| DTBench | 68% | 84% |
| LMCA | 14.5% | 37.6% |
| Epoch Capabilities Index | 137.82 | 147.37 |
| Kagi LLM Benchmark | 53.2% | — |
| NYT Connections (extended) | — | 74.8% |
| Mystery Game Puzzles | — | 17% |
Math Qwen3.7 Plus leads
gpt-oss-20b: 39.4 (#103), Qwen3.7 Plus: 50.5 (#56)
| Benchmark | gpt-oss-20b | Qwen3.7 Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 65.3% | 93.3% |
| LMArena Math | 1317 | 1466 |
| FrontierMath (Tiers 1-3) | — | 34.4% |
| Omni-MATH | 56.5% | — |
Knowledge Qwen3.7 Plus leads
gpt-oss-20b: 34.6 (#195), Qwen3.7 Plus: 54.9 (#51)
| Benchmark | gpt-oss-20b | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | 60.8% | 87.9% |
| LMArena Expert | 1258 | 1467 |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |
Multimodal Not comparable
gpt-oss-20b: —, Qwen3.7 Plus: 41.8 (#33)
| Benchmark | gpt-oss-20b | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | — | 1279 |
| LMArena Document | — | 1444 |
Multilingual Qwen3.7 Plus leads
gpt-oss-20b: 42.2 (#197), Qwen3.7 Plus: 54.8 (#38)
| Benchmark | gpt-oss-20b | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1268 | 1445 |
| LMArena Chinese | 1314 | 1510 |
| LMArena German | 1255 | 1471 |
| LMArena Japanese | 1244 | 1413 |
| LMArena Korean | 1236 | 1415 |
| LMArena Russian | 1278 | 1457 |
| LMArena Spanish | 1267 | 1457 |
| LMArena French | — | 1473 |
Instruction Following Qwen3.7 Plus leads
gpt-oss-20b: 61.8 (#240), Qwen3.7 Plus: 75.8 (#52)
| Benchmark | gpt-oss-20b | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1236 | 1440 |
| IFEval | 73.2% | — |
Long Context Qwen3.7 Plus leads
gpt-oss-20b: 37.9 (#209), Qwen3.7 Plus: 44.5 (#65)
| Benchmark | gpt-oss-20b | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1250 | 1455 |
Writing & Preference Qwen3.7 Plus leads
gpt-oss-20b: 35.5 (#265), Qwen3.7 Plus: 64.3 (#56)
| Benchmark | gpt-oss-20b | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1287 | 1455 |
| LMArena Creative Writing | 1201 | 1439 |
| LMArena Multi-Turn | 1268 | 1460 |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |
Frequently asked questions
Is gpt-oss-20b better than Qwen3.7 Plus?
Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 32.5 on the Noometry Index. gpt-oss-20b costs 19× less per token, which makes it the better buy when Qwen3.7 Plus's lead doesn't matter for your workload.
Which is cheaper, gpt-oss-20b or Qwen3.7 Plus?
gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Qwen3.7 Plus lists at $0.40 and $1.60.
Is gpt-oss-20b or Qwen3.7 Plus better for coding?
gpt-oss-20b scores higher on coding benchmarks: 37.6 versus 36.6 in the Noometry coding category.
Which has the bigger context window?
Qwen3.7 Plus does, with 1M tokens against 131K.
How many benchmarks do gpt-oss-20b and Qwen3.7 Plus share?
24 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Qwen3.7 Plus has 32.