# Codellama 34b Instruct vs gpt-oss-120b

> gpt-oss-120b is the stronger model overall, scoring 36.0 to 30.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-34b-instruct-vs-gpt-oss-120b
- Last updated: 2026-10-10
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both. Codellama 34b Instruct scores higher in 0 categories and gpt-oss-120b in 7 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where gpt-oss-120b leads 48.2 to 25.9.

## Snapshot

| | Codellama 34b Instruct | gpt-oss-120b |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 30.2 | 36.0 |
| Rank | 285 | 210 |
| Context | — | 131K |
| Input $/M | — | $0.037 |
| Output $/M | — | $0.17 |
| Weights | Open | Open |

## Coding

- Codellama 34b Instruct: 28.0 (#310)
- gpt-oss-120b: 33.2 (#251)

| Benchmark | Codellama 34b Instruct | gpt-oss-120b |
|---|---|---|
| LMArena Coding | 1046 | 1380 |
| SWE-bench Verified (bash only) | — | 26% |
| Aider Polyglot | — | 41.8% |
| SciCode | — | 36% |
| WeirdML | — | 48.2% |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| ALE-Bench | — | 575.62 |
| AlgoTune | — | 1.41 |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |

## Agentic & Tool Use

- Codellama 34b Instruct: —
- gpt-oss-120b: 12.1 (#145)

| Benchmark | Codellama 34b Instruct | gpt-oss-120b |
|---|---|---|
| Terminal-Bench | — | 18.7% |
| APEX-Agents | — | 4.4% |
| METR Time Horizons | — | 56.6% |
| Vending-Bench 2 | — | -21.53 |

## Reasoning

- Codellama 34b Instruct: 18.8 (#250)
- gpt-oss-120b: 19.5 (#236)

| Benchmark | Codellama 34b Instruct | gpt-oss-120b |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1364 |
| SimpleBench | — | 22.1% |
| Kagi LLM Benchmark | — | 58.6% |
| CritPt | — | 1.1% |
| Chess Puzzles | — | 20% |
| Mystery Game Puzzles | — | 2% |
| DTBench | — | 76.3% |
| LMCA | — | 22.1% |
| Surface Evolver Bench | — | 25% |
| Epoch Capabilities Index | — | 139.94 |

## Math

- Codellama 34b Instruct: 28.5 (#227)
- gpt-oss-120b: 50.6 (#43)

| Benchmark | Codellama 34b Instruct | gpt-oss-120b |
|---|---|---|
| LMArena Math | 1056 | 1388 |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| Omni-MATH | — | 68.8% |

## Knowledge

- Codellama 34b Instruct: —
- gpt-oss-120b: 42.3 (#89)

| Benchmark | Codellama 34b Instruct | gpt-oss-120b |
|---|---|---|
| GPQA Diamond | — | 75.8% |
| MMLU-Pro | — | 79.5% |
| Confabulations | — | 15.7% |
| Vectara Hallucination Rate | — | 14.2% |
| GPQA (HELM) | — | 68.4% |
| LMArena Expert | — | 1356 |

## Multilingual

- Codellama 34b Instruct: 25.9 (#279)
- gpt-oss-120b: 48.2 (#142)

| Benchmark | Codellama 34b Instruct | gpt-oss-120b |
|---|---|---|
| LMArena Non-English | 1011 | 1350 |
| LMArena Chinese | 976 | 1384 |
| LMArena French | — | 1370 |
| LMArena German | — | 1355 |
| LMArena Japanese | — | 1332 |
| LMArena Korean | — | 1283 |
| LMArena Russian | — | 1343 |
| LMArena Spanish | — | 1388 |

## Instruction Following

- Codellama 34b Instruct: 52.4 (#286)
- gpt-oss-120b: 69.5 (#168)

| Benchmark | Codellama 34b Instruct | gpt-oss-120b |
|---|---|---|
| LMArena Instruction Following | 1028 | 1318 |
| IFEval | — | 83.6% |

## Long Context

- Codellama 34b Instruct: 30.8 (#279)
- gpt-oss-120b: 31.4 (#273)

| Benchmark | Codellama 34b Instruct | gpt-oss-120b |
|---|---|---|
| LMArena Longer Query | 1014 | 1319 |
| Fiction.LiveBench | — | 44.4% |

## Writing & Preference

- Codellama 34b Instruct: 28.4 (#292)
- gpt-oss-120b: 46.7 (#213)

| Benchmark | Codellama 34b Instruct | gpt-oss-120b |
|---|---|---|
| LMArena Text | 1066 | 1366 |
| LMArena Creative Writing | 1032 | 1274 |
| LMArena Multi-Turn | 1015 | 1340 |
| Short-Story Creative Writing | — | 77.1% |
| EQ-Bench Creative Writing | — | 961 |
| WildBench | — | 84.5% |

## FAQ

### Is Codellama 34b Instruct better than gpt-oss-120b?

gpt-oss-120b is the stronger model overall, scoring 36.0 to 30.2 on the Noometry Index.

### Is Codellama 34b Instruct or gpt-oss-120b better for coding?

gpt-oss-120b scores higher on coding benchmarks: 33.2 versus 28.0 in the Noometry coding category.

### How many benchmarks do Codellama 34b Instruct and gpt-oss-120b share?

10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and gpt-oss-120b has 48.