Model comparison
gpt-oss-20b vs Qwen3.6 Max Preview
Qwen3.6 Max Preview is the stronger model overall, scoring 51.1 to 32.1 on the Noometry Index. gpt-oss-20b costs 81× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. gpt-oss-20b scores higher in 0 categories and Qwen3.6 Max Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.6 Max Preview leads 64.0 to 35.8.
- The biggest single-benchmark swing is LMCA: 14.5% for gpt-oss-20b and 42.5% for Qwen3.6 Max Preview.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $1.30 / $7.80 for Qwen3.6 Max Preview.
- Qwen3.6 Max Preview accepts more context: 262K tokens versus 131K.
- gpt-oss-20b has downloadable open weights; the other is API-only.
Side by side
| gpt-oss-20b | Qwen3.6 Max Preview | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 32.1 | 51.1 |
| Released | 2025-08-05 | 2026-04-20 |
| Weights | Open | Proprietary |
| Context window | 131K | 262K |
| Max output | 16K | 66K |
| Input $ / M tokens | $0.018 | $1.30 |
| Output $ / M tokens | $0.09 | $7.80 |
| Results tracked | 34 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 Max Preview leads
gpt-oss-20b: 37.1 (#185), Qwen3.6 Max Preview: 48.6 (#50)
| Benchmark | gpt-oss-20b | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Coding | 1307 | 1472 |
| SWE-bench Verified | — | 76.7% |
| LMArena WebDev | — | 1482 |
| SciCode | 34.4% | — |
| WeirdML | 40.9% | — |
| ALE-Bench | 566.05 | — |
Agentic & Tool Use Not comparable
gpt-oss-20b: 9.2 (#146), Qwen3.6 Max Preview: —
| Benchmark | gpt-oss-20b | Qwen3.6 Max Preview |
|---|---|---|
| Terminal-Bench | 3.4% | — |
| Vending-Bench 2 | — | 4,254 |
Reasoning Qwen3.6 Max Preview leads
gpt-oss-20b: 18.8 (#251), Qwen3.6 Max Preview: 40.8 (#47)
| Benchmark | gpt-oss-20b | Qwen3.6 Max Preview |
|---|---|---|
| Chess Puzzles | 4% | 20% |
| LMArena Hard Prompts | 1274 | 1457 |
| DTBench | 68% | 87.2% |
| LMCA | 14.5% | 42.5% |
| Epoch Capabilities Index | 137.81 | 149.27 |
| SimpleBench | — | 63% |
| Kagi LLM Benchmark | 53.2% | — |
| NYT Connections (extended) | — | 74.1% |
| CritPt | 1.4% | — |
| Mystery Game Puzzles | — | 19% |
Math Qwen3.6 Max Preview leads
gpt-oss-20b: 37.6 (#93), Qwen3.6 Max Preview: 52.2 (#40)
| Benchmark | gpt-oss-20b | Qwen3.6 Max Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 65.3% | 91.1% |
| LMArena Math | 1317 | 1465 |
| Omni-MATH | 56.5% | — |
| FrontierMath (Feb 2025 set) | — | 23.1% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Qwen3.6 Max Preview leads
gpt-oss-20b: 34.6 (#186), Qwen3.6 Max Preview: 57.6 (#35)
| Benchmark | gpt-oss-20b | Qwen3.6 Max Preview |
|---|---|---|
| GPQA Diamond | 60.8% | 87.4% |
| LMArena Expert | 1258 | 1476 |
| SimpleQA Verified | — | 52% |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |
Multilingual Qwen3.6 Max Preview leads
gpt-oss-20b: 42.4 (#192), Qwen3.6 Max Preview: 54.3 (#46)
| Benchmark | gpt-oss-20b | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Non-English | 1269 | 1436 |
| LMArena Chinese | 1311 | 1487 |
| LMArena Russian | 1279 | 1444 |
| LMArena Spanish | 1267 | 1452 |
| LMArena French | — | 1449 |
| LMArena German | 1249 | — |
| LMArena Japanese | 1245 | — |
| LMArena Korean | 1239 | — |
Instruction Following Qwen3.6 Max Preview leads
gpt-oss-20b: 62.0 (#235), Qwen3.6 Max Preview: 75.8 (#51)
| Benchmark | gpt-oss-20b | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1236 | 1437 |
| IFEval | 73.2% | — |
Long Context Qwen3.6 Max Preview leads
gpt-oss-20b: 37.9 (#203), Qwen3.6 Max Preview: 44.6 (#59)
| Benchmark | gpt-oss-20b | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Longer Query | 1251 | 1457 |
Writing & Preference Qwen3.6 Max Preview leads
gpt-oss-20b: 35.8 (#260), Qwen3.6 Max Preview: 64.0 (#58)
| Benchmark | gpt-oss-20b | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Text | 1288 | 1447 |
| LMArena Creative Writing | 1201 | 1435 |
| LMArena Multi-Turn | 1268 | 1456 |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |
Frequently asked questions
Is gpt-oss-20b better than Qwen3.6 Max Preview?
Qwen3.6 Max Preview is the stronger model overall, scoring 51.1 to 32.1 on the Noometry Index. gpt-oss-20b costs 81× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
Which is cheaper, gpt-oss-20b or Qwen3.6 Max Preview?
gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Qwen3.6 Max Preview lists at $1.30 and $7.80.
Is gpt-oss-20b or Qwen3.6 Max Preview better for coding?
Qwen3.6 Max Preview scores higher on coding benchmarks: 48.6 versus 37.1 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 Max Preview does, with 262K tokens against 131K.
How many benchmarks do gpt-oss-20b and Qwen3.6 Max Preview share?
19 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Qwen3.6 Max Preview has 29.