Model comparison
gpt-oss-20b vs Qwen3.6 27B
Qwen3.6 27B is the stronger model overall, scoring 42.2 to 32.5 on the Noometry Index. gpt-oss-20b costs 38× less per token, which makes it the better buy when Qwen3.6 27B's lead doesn't matter for your workload.
Last verified . 8 shared benchmarks.
Alibaba (Qwen)Summary
- They share 8 benchmarks with published results for both. gpt-oss-20b scores higher in 0 categories and Qwen3.6 27B in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.6 27B leads 52.4 to 34.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 65.3% for gpt-oss-20b and 91.1% for Qwen3.6 27B.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $0.60 / $3.60 for Qwen3.6 27B.
- Qwen3.6 27B accepts more context: 262K tokens versus 131K.
Side by side
| gpt-oss-20b | Qwen3.6 27B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 32.5 | 42.2 |
| Released | 2025-08-05 | 2026-04-22 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 16K | 66K |
| Input $ / M tokens | $0.018 | $0.60 |
| Output $ / M tokens | $0.09 | $3.60 |
| Results tracked | 34 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 27B leads
gpt-oss-20b: 37.6 (#192), Qwen3.6 27B: 39.1 (#163)
| Benchmark | gpt-oss-20b | Qwen3.6 27B |
|---|---|---|
| SciCode | 34.4% | 37.3% |
| WeirdML | 40.9% | — |
| LMArena Coding | 1306 | — |
| ALE-Bench | 566.05 | — |
Agentic & Tool Use Not comparable
gpt-oss-20b: 9.3 (#154), Qwen3.6 27B: —
| Benchmark | gpt-oss-20b | Qwen3.6 27B |
|---|---|---|
| Terminal-Bench | 3.4% | — |
Reasoning Qwen3.6 27B leads
gpt-oss-20b: 19.3 (#261), Qwen3.6 27B: 25.0 (#153)
| Benchmark | gpt-oss-20b | Qwen3.6 27B |
|---|---|---|
| CritPt | 1.4% | 0.9% |
| Chess Puzzles | 4% | 22% |
| DTBench | 68% | 78.1% |
| LMCA | 14.5% | 34.5% |
| Epoch Capabilities Index | 137.82 | 146.5 |
| Kagi LLM Benchmark | 53.2% | — |
| LMArena Hard Prompts | 1274 | — |
| Mystery Game Puzzles | — | 7% |
Math Qwen3.6 27B leads
gpt-oss-20b: 39.4 (#103), Qwen3.6 27B: 48.5 (#62)
| Benchmark | gpt-oss-20b | Qwen3.6 27B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 65.3% | 91.1% |
| FrontierMath (Tiers 1-3) | — | 35.1% |
| Omni-MATH | 56.5% | — |
| LMArena Math | 1317 | — |
Knowledge Qwen3.6 27B leads
gpt-oss-20b: 34.6 (#195), Qwen3.6 27B: 52.4 (#63)
| Benchmark | gpt-oss-20b | Qwen3.6 27B |
|---|---|---|
| GPQA Diamond | 60.8% | 85.9% |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |
| LMArena Expert | 1258 | — |
Multilingual Not comparable
gpt-oss-20b: 42.2 (#197), Qwen3.6 27B: —
| Benchmark | gpt-oss-20b | Qwen3.6 27B |
|---|---|---|
| LMArena Non-English | 1268 | — |
| LMArena Chinese | 1314 | — |
| LMArena German | 1255 | — |
| LMArena Japanese | 1244 | — |
| LMArena Korean | 1236 | — |
| LMArena Russian | 1278 | — |
| LMArena Spanish | 1267 | — |
Instruction Following Not comparable
gpt-oss-20b: 61.8 (#240), Qwen3.6 27B: —
| Benchmark | gpt-oss-20b | Qwen3.6 27B |
|---|---|---|
| IFEval | 73.2% | — |
| LMArena Instruction Following | 1236 | — |
Long Context Not comparable
gpt-oss-20b: 37.9 (#209), Qwen3.6 27B: —
| Benchmark | gpt-oss-20b | Qwen3.6 27B |
|---|---|---|
| LMArena Longer Query | 1250 | — |
Writing & Preference Qwen3.6 27B leads
gpt-oss-20b: 35.5 (#265), Qwen3.6 27B: 50.3 (#181)
| Benchmark | gpt-oss-20b | Qwen3.6 27B |
|---|---|---|
| LMArena Text | 1287 | — |
| LMArena Creative Writing | 1201 | — |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |
| EQ-Bench 4 | — | 1026 |
| LMArena Multi-Turn | 1268 | — |
Frequently asked questions
Is gpt-oss-20b better than Qwen3.6 27B?
Qwen3.6 27B is the stronger model overall, scoring 42.2 to 32.5 on the Noometry Index. gpt-oss-20b costs 38× less per token, which makes it the better buy when Qwen3.6 27B's lead doesn't matter for your workload.
Which is cheaper, gpt-oss-20b or Qwen3.6 27B?
gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Qwen3.6 27B lists at $0.60 and $3.60.
Is gpt-oss-20b or Qwen3.6 27B better for coding?
Qwen3.6 27B scores higher on coding benchmarks: 39.1 versus 37.6 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 27B does, with 262K tokens against 131K.
How many benchmarks do gpt-oss-20b and Qwen3.6 27B share?
8 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Qwen3.6 27B has 11.