# gpt-oss-20b vs Qwen Max

> Qwen Max is the stronger model overall, scoring 34.7 to 32.5 on the Noometry Index. gpt-oss-20b costs 78× less per token, which makes it the better buy when Qwen Max's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-oss-20b-vs-qwen-max
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. gpt-oss-20b scores higher in 4 categories and Qwen Max in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-20b leads 39.4 to 22.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 65.3% for gpt-oss-20b and 16.1% for Qwen Max.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $1.60 / $6.40 for Qwen Max.
- gpt-oss-20b accepts more context: 131K tokens versus 33K.
- gpt-oss-20b has downloadable open weights; the other is API-only.

## Snapshot

| | gpt-oss-20b | Qwen Max |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 32.5 | 34.7 |
| Rank | 255 | 230 |
| Context | 131K | 33K |
| Input $/M | $0.018 | $1.60 |
| Output $/M | $0.09 | $6.40 |
| Weights | Open | Proprietary |

## Coding

- gpt-oss-20b: 37.6 (#192)
- Qwen Max: 30.7 (#292)

| Benchmark | gpt-oss-20b | Qwen Max |
|---|---|---|
| LMArena Coding | 1306 | 1288 |
| Aider Polyglot | — | 21.8% |
| SciCode | 34.4% | — |
| WeirdML | 40.9% | — |
| ALE-Bench | 566.05 | — |

## Agentic & Tool Use

- gpt-oss-20b: 9.3 (#154)
- Qwen Max: —

| Benchmark | gpt-oss-20b | Qwen Max |
|---|---|---|
| Terminal-Bench | 3.4% | — |

## Reasoning

- gpt-oss-20b: 19.3 (#261)
- Qwen Max: 25.1 (#151)

| Benchmark | gpt-oss-20b | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1274 | 1269 |
| Kagi LLM Benchmark | 53.2% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 4% | — |
| DTBench | 68% | — |
| LMCA | 14.5% | — |
| Epoch Capabilities Index | 137.82 | — |

## Math

- gpt-oss-20b: 39.4 (#103)
- Qwen Max: 22.3 (#276)

| Benchmark | gpt-oss-20b | Qwen Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 65.3% | 16.1% |
| LMArena Math | 1317 | 1275 |
| Omni-MATH | 56.5% | — |
| MATH Level 5 | — | 67.2% |
| FrontierMath (Feb 2025 set) | — | 1% |

## Knowledge

- gpt-oss-20b: 34.6 (#195)
- Qwen Max: 30.3 (#228)

| Benchmark | gpt-oss-20b | Qwen Max |
|---|---|---|
| GPQA Diamond | 60.8% | 56.1% |
| LMArena Expert | 1258 | 1248 |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |

## Multilingual

- gpt-oss-20b: 42.2 (#197)
- Qwen Max: 41.8 (#202)

| Benchmark | gpt-oss-20b | Qwen Max |
|---|---|---|
| LMArena Non-English | 1268 | 1263 |
| LMArena Chinese | 1314 | 1254 |
| LMArena German | 1255 | 1254 |
| LMArena Japanese | 1244 | 1205 |
| LMArena Korean | 1236 | 1142 |
| LMArena Russian | 1278 | 1274 |
| LMArena Spanish | 1267 | 1290 |
| LMArena French | — | 1330 |

## Instruction Following

- gpt-oss-20b: 61.8 (#240)
- Qwen Max: 66.5 (#208)

| Benchmark | gpt-oss-20b | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1236 | 1262 |
| IFEval | 73.2% | — |

## Long Context

- gpt-oss-20b: 37.9 (#209)
- Qwen Max: 39.4 (#180)

| Benchmark | gpt-oss-20b | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1250 | 1288 |
| Fiction.LiveBench | — | 66.7% |

## Writing & Preference

- gpt-oss-20b: 35.5 (#265)
- Qwen Max: 47.8 (#205)

| Benchmark | gpt-oss-20b | Qwen Max |
|---|---|---|
| LMArena Text | 1287 | 1282 |
| LMArena Creative Writing | 1201 | 1248 |
| LMArena Multi-Turn | 1268 | 1277 |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |

## FAQ

### Is gpt-oss-20b better than Qwen Max?

Qwen Max is the stronger model overall, scoring 34.7 to 32.5 on the Noometry Index. gpt-oss-20b costs 78× less per token, which makes it the better buy when Qwen Max's lead doesn't matter for your workload.

### Which is cheaper, gpt-oss-20b or Qwen Max?

gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Qwen Max lists at $1.60 and $6.40.

### Is gpt-oss-20b or Qwen Max better for coding?

gpt-oss-20b scores higher on coding benchmarks: 37.6 versus 30.7 in the Noometry coding category.

### Which has the bigger context window?

gpt-oss-20b does, with 131K tokens against 33K.

### How many benchmarks do gpt-oss-20b and Qwen Max share?

18 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Qwen Max has 23.