Model comparison
gpt-oss-20b vs Qwen3.5 Plus
Qwen3.5 Plus is the stronger model overall, scoring 42.3 to 32.1 on the Noometry Index. gpt-oss-20b costs 25× less per token, which makes it the better buy when Qwen3.5 Plus's lead doesn't matter for your workload.
Last verified . 7 shared benchmarks.
Alibaba (Qwen)Summary
- They share 7 benchmarks with published results for both. gpt-oss-20b scores higher in 0 categories and Qwen3.5 Plus in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.5 Plus leads 32.0 to 18.8.
- The biggest single-benchmark swing is GPQA Diamond: 60.8% for gpt-oss-20b and 84.8% for Qwen3.5 Plus.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $0.40 / $2.40 for Qwen3.5 Plus.
- Qwen3.5 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 | Qwen3.5 Plus | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 32.1 | 42.3 |
| Released | 2025-08-05 | 2026-02-16 |
| Weights | Open | Proprietary |
| Context window | 131K | 1M |
| Max output | 16K | 66K |
| Input $ / M tokens | $0.018 | $0.40 |
| Output $ / M tokens | $0.09 | $2.40 |
| Results tracked | 34 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
gpt-oss-20b: 37.1 (#185), Qwen3.5 Plus: —
| Benchmark | gpt-oss-20b | Qwen3.5 Plus |
|---|---|---|
| ALE-Bench | 566.05 | 621.92 |
| SciCode | 34.4% | — |
| WeirdML | 40.9% | — |
| LMArena Coding | 1307 | — |
Agentic & Tool Use Not comparable
gpt-oss-20b: 9.2 (#146), Qwen3.5 Plus: —
| Benchmark | gpt-oss-20b | Qwen3.5 Plus |
|---|---|---|
| Terminal-Bench | 3.4% | — |
| Vending-Bench 2 | — | 0.54 |
Reasoning Qwen3.5 Plus leads
gpt-oss-20b: 18.8 (#251), Qwen3.5 Plus: 32.0 (#67)
| Benchmark | gpt-oss-20b | Qwen3.5 Plus |
|---|---|---|
| Chess Puzzles | 4% | 22% |
| DTBench | 68% | 80.5% |
| LMCA | 14.5% | 36.4% |
| Epoch Capabilities Index | 137.81 | 146.79 |
| Kagi LLM Benchmark | 53.2% | — |
| CritPt | 1.4% | — |
| LMArena Hard Prompts | 1274 | — |
| Mystery Game Puzzles | — | 17% |
Math Qwen3.5 Plus leads
gpt-oss-20b: 37.6 (#93), Qwen3.5 Plus: 47.9 (#55)
| Benchmark | gpt-oss-20b | Qwen3.5 Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 65.3% | 86.7% |
| Omni-MATH | 56.5% | — |
| LMArena Math | 1317 | — |
| FrontierMath (Feb 2025 set) | — | 21% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge Qwen3.5 Plus leads
gpt-oss-20b: 34.6 (#186), Qwen3.5 Plus: 46.0 (#78)
| Benchmark | gpt-oss-20b | Qwen3.5 Plus |
|---|---|---|
| GPQA Diamond | 60.8% | 84.8% |
| SimpleQA Verified | — | 25.4% |
| MMLU-Pro | 74% | — |
| Vectara Hallucination Rate | — | 10.7% |
| GPQA (HELM) | 59.4% | — |
| LMArena Expert | 1258 | — |
Multilingual Not comparable
gpt-oss-20b: 42.4 (#192), Qwen3.5 Plus: —
| Benchmark | gpt-oss-20b | Qwen3.5 Plus |
|---|---|---|
| LMArena Non-English | 1269 | — |
| LMArena Chinese | 1311 | — |
| LMArena German | 1249 | — |
| LMArena Japanese | 1245 | — |
| LMArena Korean | 1239 | — |
| LMArena Russian | 1279 | — |
| LMArena Spanish | 1267 | — |
Instruction Following Not comparable
gpt-oss-20b: 62.0 (#235), Qwen3.5 Plus: —
| Benchmark | gpt-oss-20b | Qwen3.5 Plus |
|---|---|---|
| IFEval | 73.2% | — |
| LMArena Instruction Following | 1236 | — |
Long Context Qwen3.5 Plus leads
gpt-oss-20b: 37.9 (#203), Qwen3.5 Plus: 42.9 (#109)
| Benchmark | gpt-oss-20b | Qwen3.5 Plus |
|---|---|---|
| CL-bench | — | 19.8% |
| CL-bench Life | — | 12.4% |
| LMArena Longer Query | 1251 | — |
Writing & Preference Not comparable
gpt-oss-20b: 35.8 (#260), Qwen3.5 Plus: —
| Benchmark | gpt-oss-20b | Qwen3.5 Plus |
|---|---|---|
| LMArena Text | 1288 | — |
| LMArena Creative Writing | 1201 | — |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |
| LMArena Multi-Turn | 1268 | — |
Frequently asked questions
Is gpt-oss-20b better than Qwen3.5 Plus?
Qwen3.5 Plus is the stronger model overall, scoring 42.3 to 32.1 on the Noometry Index. gpt-oss-20b costs 25× less per token, which makes it the better buy when Qwen3.5 Plus's lead doesn't matter for your workload.
Which is cheaper, gpt-oss-20b or Qwen3.5 Plus?
gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Qwen3.5 Plus lists at $0.40 and $2.40.
Which has the bigger context window?
Qwen3.5 Plus does, with 1M tokens against 131K.
How many benchmarks do gpt-oss-20b and Qwen3.5 Plus share?
7 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Qwen3.5 Plus has 15.