# gpt-oss-20b vs Qwen2-72B

> gpt-oss-20b is the stronger model overall, scoring 32.1 to 29.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-oss-20b-vs-qwen2-72b
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. gpt-oss-20b scores higher in 6 categories and Qwen2-72B in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where gpt-oss-20b leads 34.6 to 21.2.
- The biggest single-benchmark swing is WeirdML: 40.9% for gpt-oss-20b and 11.3% for Qwen2-72B.

## Snapshot

| | gpt-oss-20b | Qwen2-72B |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 32.1 | 29.5 |
| Rank | 249 | 294 |
| Context | 131K | — |
| Input $/M | $0.018 | — |
| Output $/M | $0.09 | — |
| Weights | Open | Open |

## Coding

- gpt-oss-20b: 37.1 (#185)
- Qwen2-72B: 28.7 (#303)

| Benchmark | gpt-oss-20b | Qwen2-72B |
|---|---|---|
| WeirdML | 40.9% | 11.3% |
| LMArena Coding | 1307 | 1196 |
| SciCode | 34.4% | — |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
| ALE-Bench | 566.05 | — |

## Agentic & Tool Use

- gpt-oss-20b: 9.2 (#146)
- Qwen2-72B: 16.9 (#138)

| Benchmark | gpt-oss-20b | Qwen2-72B |
|---|---|---|
| Terminal-Bench | 3.4% | — |
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |

## Reasoning

- gpt-oss-20b: 18.8 (#251)
- Qwen2-72B: 22.2 (#184)

| Benchmark | gpt-oss-20b | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1274 | 1191 |
| Epoch Capabilities Index | 137.81 | 125.27 |
| Kagi LLM Benchmark | 53.2% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 4% | — |
| DTBench | 68% | — |
| LMCA | 14.5% | — |

## Math

- gpt-oss-20b: 37.6 (#93)
- Qwen2-72B: 27.9 (#232)

| Benchmark | gpt-oss-20b | Qwen2-72B |
|---|---|---|
| LMArena Math | 1317 | 1235 |
| OTIS Mock AIME 2024-2025 | 65.3% | — |
| Omni-MATH | 56.5% | — |
| MATH Level 5 | — | 39.1% |

## Knowledge

- gpt-oss-20b: 34.6 (#186)
- Qwen2-72B: 21.2 (#270)

| Benchmark | gpt-oss-20b | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 60.8% | 40.8% |
| LMArena Expert | 1258 | 1171 |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |
| MMLU | — | 82.4% |

## Multilingual

- gpt-oss-20b: 42.4 (#192)
- Qwen2-72B: 36.0 (#239)

| Benchmark | gpt-oss-20b | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1269 | 1176 |
| LMArena Chinese | 1311 | 1240 |
| LMArena German | 1249 | 1151 |
| LMArena Japanese | 1245 | 1111 |
| LMArena Korean | 1239 | 1083 |
| LMArena Russian | 1279 | 1169 |
| LMArena Spanish | 1267 | 1168 |
| LMArena French | — | 1169 |

## Instruction Following

- gpt-oss-20b: 62.0 (#235)
- Qwen2-72B: 62.0 (#236)

| Benchmark | gpt-oss-20b | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1236 | 1181 |
| IFEval | 73.2% | — |

## Long Context

- gpt-oss-20b: 37.9 (#203)
- Qwen2-72B: 36.1 (#230)

| Benchmark | gpt-oss-20b | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1251 | 1193 |

## Writing & Preference

- gpt-oss-20b: 35.8 (#260)
- Qwen2-72B: 41.0 (#236)

| Benchmark | gpt-oss-20b | Qwen2-72B |
|---|---|---|
| LMArena Text | 1288 | 1203 |
| LMArena Creative Writing | 1201 | 1181 |
| LMArena Multi-Turn | 1268 | 1195 |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |

## FAQ

### Is gpt-oss-20b better than Qwen2-72B?

gpt-oss-20b is the stronger model overall, scoring 32.1 to 29.5 on the Noometry Index.

### Is gpt-oss-20b or Qwen2-72B better for coding?

gpt-oss-20b scores higher on coding benchmarks: 37.1 versus 28.7 in the Noometry coding category.

### How many benchmarks do gpt-oss-20b and Qwen2-72B share?

19 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Qwen2-72B has 26.