# DeepSeek LLM 67B vs gpt-oss-120b

> gpt-oss-120b is the stronger model overall, scoring 36.3 to 24.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-llm-67b-vs-gpt-oss-120b
- Last updated: 2026-10-12
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 1 category and gpt-oss-120b in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-120b leads 52.5 to 8.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 88.9% for gpt-oss-120b.

## Snapshot

| | DeepSeek LLM 67B | gpt-oss-120b |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 24.9 | 36.3 |
| Rank | 347 | 217 |
| Context | — | 131K |
| Input $/M | — | $0.037 |
| Output $/M | — | $0.17 |
| Weights | Open | Open |

## Coding

- DeepSeek LLM 67B: 31.9 (#278)
- gpt-oss-120b: 33.5 (#256)

| Benchmark | DeepSeek LLM 67B | gpt-oss-120b |
|---|---|---|
| LMArena Coding | 1096 | 1380 |
| SWE-bench Verified (bash only) | — | 26% |
| Aider Polyglot | — | 41.8% |
| SciCode | — | 36% |
| WeirdML | — | 48.2% |
| ALE-Bench | — | 575.62 |
| AlgoTune | — | 1.41 |

## Agentic & Tool Use

- DeepSeek LLM 67B: —
- gpt-oss-120b: 12.2 (#153)

| Benchmark | DeepSeek LLM 67B | gpt-oss-120b |
|---|---|---|
| Terminal-Bench | — | 18.7% |
| APEX-Agents | — | 4.4% |
| METR Time Horizons | — | 56.6% |
| Vending-Bench 2 | — | -21.53 |

## Reasoning

- DeepSeek LLM 67B: 16.5 (#304)
- gpt-oss-120b: 20.0 (#245)

| Benchmark | DeepSeek LLM 67B | gpt-oss-120b |
|---|---|---|
| Chess Puzzles | 0% | 20% |
| LMArena Hard Prompts | 1070 | 1364 |
| Epoch Capabilities Index | 110.5 | 139.93 |
| SimpleBench | — | 22.1% |
| Kagi LLM Benchmark | — | 58.6% |
| CritPt | — | 1.1% |
| Mystery Game Puzzles | — | 2% |
| DTBench | — | 76.3% |
| LMCA | — | 22.1% |
| Surface Evolver Bench | — | 25% |

## Math

- DeepSeek LLM 67B: 8.7 (#324)
- gpt-oss-120b: 52.5 (#50)

| Benchmark | DeepSeek LLM 67B | gpt-oss-120b |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 88.9% |
| LMArena Math | 1108 | 1389 |
| Omni-MATH | — | 68.8% |
| MATH Level 5 | 6.4% | — |

## Knowledge

- DeepSeek LLM 67B: 7.0 (#313)
- gpt-oss-120b: 42.4 (#96)

| Benchmark | DeepSeek LLM 67B | gpt-oss-120b |
|---|---|---|
| GPQA Diamond | 24.6% | 75.8% |
| MMLU-Pro | — | 79.5% |
| Confabulations | — | 15.7% |
| Vectara Hallucination Rate | — | 14.2% |
| GPQA (HELM) | — | 68.4% |
| LMArena Expert | — | 1356 |

## Multilingual

- DeepSeek LLM 67B: 29.4 (#267)
- gpt-oss-120b: 48.0 (#147)

| Benchmark | DeepSeek LLM 67B | gpt-oss-120b |
|---|---|---|
| LMArena Non-English | 1073 | 1351 |
| LMArena Chinese | 1132 | 1385 |
| LMArena French | — | 1369 |
| LMArena German | — | 1353 |
| LMArena Japanese | — | 1331 |
| LMArena Korean | — | 1282 |
| LMArena Russian | — | 1343 |
| LMArena Spanish | — | 1389 |

## Instruction Following

- DeepSeek LLM 67B: 55.4 (#277)
- gpt-oss-120b: 69.3 (#173)

| Benchmark | DeepSeek LLM 67B | gpt-oss-120b |
|---|---|---|
| LMArena Instruction Following | 1079 | 1318 |
| IFEval | — | 83.6% |

## Long Context

- DeepSeek LLM 67B: 33.1 (#265)
- gpt-oss-120b: 31.4 (#278)

| Benchmark | DeepSeek LLM 67B | gpt-oss-120b |
|---|---|---|
| LMArena Longer Query | 1092 | 1319 |
| Fiction.LiveBench | — | 44.4% |

## Writing & Preference

- DeepSeek LLM 67B: 31.6 (#282)
- gpt-oss-120b: 46.5 (#217)

| Benchmark | DeepSeek LLM 67B | gpt-oss-120b |
|---|---|---|
| LMArena Text | 1105 | 1365 |
| LMArena Creative Writing | 1067 | 1275 |
| LMArena Multi-Turn | 1082 | 1340 |
| Short-Story Creative Writing | — | 77.1% |
| EQ-Bench Creative Writing | — | 961 |
| WildBench | — | 84.5% |

## FAQ

### Is DeepSeek LLM 67B better than gpt-oss-120b?

gpt-oss-120b is the stronger model overall, scoring 36.3 to 24.9 on the Noometry Index.

### Is DeepSeek LLM 67B or gpt-oss-120b better for coding?

gpt-oss-120b scores higher on coding benchmarks: 33.5 versus 31.9 in the Noometry coding category.

### How many benchmarks do DeepSeek LLM 67B and gpt-oss-120b share?

14 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and gpt-oss-120b has 48.