# gpt-oss-120b vs Hy3

> Hy3 is the stronger model overall, scoring 44.2 to 36.3 on the Noometry Index. gpt-oss-120b costs 2.1× less per token, which makes it the better buy when Hy3's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-oss-120b-vs-hy3
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. gpt-oss-120b scores higher in 2 categories and Hy3 in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Hy3 leads 62.2 to 46.5.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $0.0825 / $0.33 for Hy3.
- Hy3 accepts more context: 262K tokens versus 131K.

## Snapshot

| | gpt-oss-120b | Hy3 |
|---|---|---|
| Provider | OpenAI | Tencent |
| Noometry Index | 36.3 | 44.2 |
| Rank | 217 | 79 |
| Context | 131K | 262K |
| Input $/M | $0.037 | $0.0825 |
| Output $/M | $0.17 | $0.33 |
| Weights | Open | Open |

## Coding

- gpt-oss-120b: 33.5 (#256)
- Hy3: 46.8 (#63)

| Benchmark | gpt-oss-120b | Hy3 |
|---|---|---|
| LMArena Coding | 1380 | 1464 |
| SWE-bench Verified (bash only) | 26% | — |
| Aider Polyglot | 41.8% | — |
| LMArena WebDev | — | 1508 |
| SciCode | 36% | — |
| WeirdML | 48.2% | — |
| ALE-Bench | 575.62 | — |
| AlgoTune | 1.41 | — |

## Agentic & Tool Use

- gpt-oss-120b: 12.2 (#153)
- Hy3: —

| Benchmark | gpt-oss-120b | Hy3 |
|---|---|---|
| Terminal-Bench | 18.7% | — |
| APEX-Agents | 4.4% | — |
| METR Time Horizons | 56.6% | — |
| Vending-Bench 2 | -21.53 | — |

## Reasoning

- gpt-oss-120b: 20.0 (#245)
- Hy3: 26.1 (#136)

| Benchmark | gpt-oss-120b | Hy3 |
|---|---|---|
| LMArena Hard Prompts | 1364 | 1447 |
| SimpleBench | 22.1% | — |
| Kagi LLM Benchmark | 58.6% | — |
| NYT Connections (extended) | — | 41.2% |
| CritPt | 1.1% | — |
| Chess Puzzles | 20% | — |
| Mystery Game Puzzles | 2% | — |
| DTBench | 76.3% | — |
| LMCA | 22.1% | — |
| Surface Evolver Bench | 25% | — |
| Epoch Capabilities Index | 139.93 | — |

## Math

- gpt-oss-120b: 52.5 (#50)
- Hy3: 40.1 (#93)

| Benchmark | gpt-oss-120b | Hy3 |
|---|---|---|
| LMArena Math | 1389 | 1475 |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| Omni-MATH | 68.8% | — |

## Knowledge

- gpt-oss-120b: 42.4 (#96)
- Hy3: 40.8 (#114)

| Benchmark | gpt-oss-120b | Hy3 |
|---|---|---|
| LMArena Expert | 1356 | 1460 |
| GPQA Diamond | 75.8% | — |
| MMLU-Pro | 79.5% | — |
| Confabulations | 15.7% | — |
| Vectara Hallucination Rate | 14.2% | — |
| GPQA (HELM) | 68.4% | — |

## Multilingual

- gpt-oss-120b: 48.0 (#147)
- Hy3: 53.5 (#65)

| Benchmark | gpt-oss-120b | Hy3 |
|---|---|---|
| LMArena Non-English | 1351 | 1426 |
| LMArena Chinese | 1385 | 1493 |
| LMArena French | 1369 | 1461 |
| LMArena German | 1353 | 1439 |
| LMArena Japanese | 1331 | 1392 |
| LMArena Korean | 1282 | 1395 |
| LMArena Russian | 1343 | 1432 |
| LMArena Spanish | 1389 | 1456 |

## Instruction Following

- gpt-oss-120b: 69.3 (#173)
- Hy3: 75.1 (#70)

| Benchmark | gpt-oss-120b | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1318 | 1426 |
| IFEval | 83.6% | — |

## Long Context

- gpt-oss-120b: 31.4 (#278)
- Hy3: 44.1 (#75)

| Benchmark | gpt-oss-120b | Hy3 |
|---|---|---|
| LMArena Longer Query | 1319 | 1442 |
| Fiction.LiveBench | 44.4% | — |

## Writing & Preference

- gpt-oss-120b: 46.5 (#217)
- Hy3: 62.2 (#81)

| Benchmark | gpt-oss-120b | Hy3 |
|---|---|---|
| LMArena Text | 1365 | 1439 |
| LMArena Creative Writing | 1275 | 1402 |
| LMArena Multi-Turn | 1340 | 1436 |
| Short-Story Creative Writing | 77.1% | — |
| EQ-Bench Creative Writing | 961 | — |
| WildBench | 84.5% | — |

## FAQ

### Is gpt-oss-120b better than Hy3?

Hy3 is the stronger model overall, scoring 44.2 to 36.3 on the Noometry Index. gpt-oss-120b costs 2.1× less per token, which makes it the better buy when Hy3's lead doesn't matter for your workload.

### Which is cheaper, gpt-oss-120b or Hy3?

gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; Hy3 lists at $0.0825 and $0.33.

### Is gpt-oss-120b or Hy3 better for coding?

Hy3 scores higher on coding benchmarks: 46.8 versus 33.5 in the Noometry coding category.

### Which has the bigger context window?

Hy3 does, with 262K tokens against 131K.

### How many benchmarks do gpt-oss-120b and Hy3 share?

17 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Hy3 has 19.