# gpt-oss-20b vs Yi-34B

> gpt-oss-20b is the stronger model overall, scoring 32.1 to 27.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-oss-20b-vs-yi-34b
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. gpt-oss-20b scores higher in 7 categories and Yi-34B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where gpt-oss-20b leads 34.6 to 7.5.
- The biggest single-benchmark swing is GPQA Diamond: 60.8% for gpt-oss-20b and 14.7% for Yi-34B.

## Snapshot

| | gpt-oss-20b | Yi-34B |
|---|---|---|
| Provider | OpenAI | 01.AI |
| Noometry Index | 32.1 | 27.4 |
| Rank | 249 | 325 |
| Context | 131K | — |
| Input $/M | $0.018 | — |
| Output $/M | $0.09 | — |
| Weights | Open | Open |

## Coding

- gpt-oss-20b: 37.1 (#185)
- Yi-34B: 31.8 (#269)

| Benchmark | gpt-oss-20b | Yi-34B |
|---|---|---|
| LMArena Coding | 1307 | 1112 |
| SciCode | 34.4% | — |
| WeirdML | 40.9% | — |
| ALE-Bench | 566.05 | — |

## Agentic & Tool Use

- gpt-oss-20b: 9.2 (#146)
- Yi-34B: —

| Benchmark | gpt-oss-20b | Yi-34B |
|---|---|---|
| Terminal-Bench | 3.4% | — |

## Reasoning

- gpt-oss-20b: 18.8 (#251)
- Yi-34B: 20.3 (#222)

| Benchmark | gpt-oss-20b | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1274 | 1104 |
| Epoch Capabilities Index | 137.81 | 117.28 |
| Kagi LLM Benchmark | 53.2% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 4% | — |
| DTBench | 68% | — |
| LMCA | 14.5% | — |
| BIG-Bench Hard | — | 71.7% |

## Math

- gpt-oss-20b: 37.6 (#93)
- Yi-34B: 19.8 (#277)

| Benchmark | gpt-oss-20b | Yi-34B |
|---|---|---|
| LMArena Math | 1317 | 1114 |
| OTIS Mock AIME 2024-2025 | 65.3% | — |
| Omni-MATH | 56.5% | — |
| MATH Level 5 | — | 5.1% |
| GSM8K | — | 76% |

## Knowledge

- gpt-oss-20b: 34.6 (#186)
- Yi-34B: 7.5 (#304)

| Benchmark | gpt-oss-20b | Yi-34B |
|---|---|---|
| GPQA Diamond | 60.8% | 14.7% |
| LMArena Expert | 1258 | 1061 |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |
| MMLU | — | 76.3% |

## Multilingual

- gpt-oss-20b: 42.4 (#192)
- Yi-34B: 29.9 (#259)

| Benchmark | gpt-oss-20b | Yi-34B |
|---|---|---|
| LMArena Non-English | 1269 | 1079 |
| LMArena Chinese | 1311 | 1175 |
| LMArena German | 1249 | 1042 |
| LMArena Japanese | 1245 | 993 |
| LMArena Korean | 1239 | 959 |
| LMArena Russian | 1279 | 1050 |
| LMArena Spanish | 1267 | 1070 |
| LMArena French | — | 1080 |

## Instruction Following

- gpt-oss-20b: 62.0 (#235)
- Yi-34B: 56.4 (#269)

| Benchmark | gpt-oss-20b | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1236 | 1091 |
| IFEval | 73.2% | — |

## Long Context

- gpt-oss-20b: 37.9 (#203)
- Yi-34B: 33.2 (#259)

| Benchmark | gpt-oss-20b | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1251 | 1094 |

## Writing & Preference

- gpt-oss-20b: 35.8 (#260)
- Yi-34B: 34.3 (#268)

| Benchmark | gpt-oss-20b | Yi-34B |
|---|---|---|
| LMArena Text | 1288 | 1129 |
| LMArena Creative Writing | 1201 | 1108 |
| LMArena Multi-Turn | 1268 | 1113 |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |

## FAQ

### Is gpt-oss-20b better than Yi-34B?

gpt-oss-20b is the stronger model overall, scoring 32.1 to 27.4 on the Noometry Index.

### Is gpt-oss-20b or Yi-34B better for coding?

gpt-oss-20b scores higher on coding benchmarks: 37.1 versus 31.8 in the Noometry coding category.

### How many benchmarks do gpt-oss-20b and Yi-34B share?

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