Model comparison
Codellama 34b Instruct vs gpt-oss-120b
gpt-oss-120b is the stronger model overall, scoring 36.3 to 30.8 on the Noometry Index.
Last verified . 10 shared benchmarks.
MetaSummary
- 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 48.0 to 25.8.
Side by side
| Codellama 34b Instruct | gpt-oss-120b | |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 30.8 | 36.3 |
| Released | — | 2025-08-05 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 41K |
| Input $ / M tokens | — | $0.037 |
| Output $ / M tokens | — | $0.17 |
| Results tracked | 14 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding gpt-oss-120b leads
Codellama 34b Instruct: 28.5 (#314), gpt-oss-120b: 33.5 (#256)
| 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 Not comparable
Codellama 34b Instruct: —, gpt-oss-120b: 12.2 (#153)
| 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 Too close to call
Codellama 34b Instruct: 19.6 (#255), gpt-oss-120b: 20.0 (#245)
| 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 | — | 139.93 |
Math gpt-oss-120b leads
Codellama 34b Instruct: 31.0 (#230), gpt-oss-120b: 52.5 (#50)
| Benchmark | Codellama 34b Instruct | gpt-oss-120b |
|---|---|---|
| LMArena Math | 1056 | 1389 |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| Omni-MATH | — | 68.8% |
Knowledge Not comparable
Codellama 34b Instruct: —, gpt-oss-120b: 42.4 (#96)
| 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 gpt-oss-120b leads
Codellama 34b Instruct: 25.8 (#284), gpt-oss-120b: 48.0 (#147)
| Benchmark | Codellama 34b Instruct | gpt-oss-120b |
|---|---|---|
| LMArena Non-English | 1011 | 1351 |
| LMArena Chinese | 976 | 1385 |
| LMArena French | — | 1369 |
| LMArena German | — | 1353 |
| LMArena Japanese | — | 1331 |
| LMArena Korean | — | 1282 |
| LMArena Russian | — | 1343 |
| LMArena Spanish | — | 1389 |
Instruction Following gpt-oss-120b leads
Codellama 34b Instruct: 52.2 (#291), gpt-oss-120b: 69.3 (#173)
| Benchmark | Codellama 34b Instruct | gpt-oss-120b |
|---|---|---|
| LMArena Instruction Following | 1028 | 1318 |
| IFEval | — | 83.6% |
Long Context Too close to call
Codellama 34b Instruct: 30.9 (#284), gpt-oss-120b: 31.4 (#278)
| Benchmark | Codellama 34b Instruct | gpt-oss-120b |
|---|---|---|
| LMArena Longer Query | 1013 | 1319 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference gpt-oss-120b leads
Codellama 34b Instruct: 28.2 (#297), gpt-oss-120b: 46.5 (#217)
| Benchmark | Codellama 34b Instruct | gpt-oss-120b |
|---|---|---|
| LMArena Text | 1066 | 1365 |
| LMArena Creative Writing | 1032 | 1275 |
| LMArena Multi-Turn | 1015 | 1340 |
| Short-Story Creative Writing | — | 77.1% |
| EQ-Bench Creative Writing | — | 961 |
| WildBench | — | 84.5% |
Frequently asked questions
Is Codellama 34b Instruct better than gpt-oss-120b?
gpt-oss-120b is the stronger model overall, scoring 36.3 to 30.8 on the Noometry Index.
Is Codellama 34b Instruct or gpt-oss-120b better for coding?
gpt-oss-120b scores higher on coding benchmarks: 33.5 versus 28.5 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.