Model comparison
Codellama 34b Instruct vs gpt-oss-20b
gpt-oss-20b is the stronger model overall, scoring 32.5 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 1 category and gpt-oss-20b in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where gpt-oss-20b leads 42.2 to 25.8.
Side by side
| Codellama 34b Instruct | gpt-oss-20b | |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 30.8 | 32.5 |
| Released | — | 2025-08-05 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.018 |
| Output $ / M tokens | — | $0.09 |
| Results tracked | 14 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding gpt-oss-20b leads
Codellama 34b Instruct: 28.5 (#314), gpt-oss-20b: 37.6 (#192)
| Benchmark | Codellama 34b Instruct | gpt-oss-20b |
|---|---|---|
| LMArena Coding | 1046 | 1306 |
| SciCode | — | 34.4% |
| WeirdML | — | 40.9% |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| ALE-Bench | — | 566.05 |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Agentic & Tool Use Not comparable
Codellama 34b Instruct: —, gpt-oss-20b: 9.3 (#154)
| Benchmark | Codellama 34b Instruct | gpt-oss-20b |
|---|---|---|
| Terminal-Bench | — | 3.4% |
Reasoning Too close to call
Codellama 34b Instruct: 19.6 (#255), gpt-oss-20b: 19.3 (#261)
| Benchmark | Codellama 34b Instruct | gpt-oss-20b |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1274 |
| Kagi LLM Benchmark | — | 53.2% |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 4% |
| DTBench | — | 68% |
| LMCA | — | 14.5% |
| Epoch Capabilities Index | — | 137.82 |
Math gpt-oss-20b leads
Codellama 34b Instruct: 31.0 (#230), gpt-oss-20b: 39.4 (#103)
| Benchmark | Codellama 34b Instruct | gpt-oss-20b |
|---|---|---|
| LMArena Math | 1056 | 1317 |
| OTIS Mock AIME 2024-2025 | — | 65.3% |
| Omni-MATH | — | 56.5% |
Knowledge Not comparable
Codellama 34b Instruct: —, gpt-oss-20b: 34.6 (#195)
| Benchmark | Codellama 34b Instruct | gpt-oss-20b |
|---|---|---|
| GPQA Diamond | — | 60.8% |
| MMLU-Pro | — | 74% |
| GPQA (HELM) | — | 59.4% |
| LMArena Expert | — | 1258 |
Multilingual gpt-oss-20b leads
Codellama 34b Instruct: 25.8 (#284), gpt-oss-20b: 42.2 (#197)
| Benchmark | Codellama 34b Instruct | gpt-oss-20b |
|---|---|---|
| LMArena Non-English | 1011 | 1268 |
| LMArena Chinese | 976 | 1314 |
| LMArena German | — | 1255 |
| LMArena Japanese | — | 1244 |
| LMArena Korean | — | 1236 |
| LMArena Russian | — | 1278 |
| LMArena Spanish | — | 1267 |
Instruction Following gpt-oss-20b leads
Codellama 34b Instruct: 52.2 (#291), gpt-oss-20b: 61.8 (#240)
| Benchmark | Codellama 34b Instruct | gpt-oss-20b |
|---|---|---|
| LMArena Instruction Following | 1028 | 1236 |
| IFEval | — | 73.2% |
Long Context gpt-oss-20b leads
Codellama 34b Instruct: 30.9 (#284), gpt-oss-20b: 37.9 (#209)
| Benchmark | Codellama 34b Instruct | gpt-oss-20b |
|---|---|---|
| LMArena Longer Query | 1013 | 1250 |
Writing & Preference gpt-oss-20b leads
Codellama 34b Instruct: 28.2 (#297), gpt-oss-20b: 35.5 (#265)
| Benchmark | Codellama 34b Instruct | gpt-oss-20b |
|---|---|---|
| LMArena Text | 1066 | 1287 |
| LMArena Creative Writing | 1032 | 1201 |
| LMArena Multi-Turn | 1015 | 1268 |
| EQ-Bench Creative Writing | — | 666 |
| WildBench | — | 73.7% |
Frequently asked questions
Is Codellama 34b Instruct better than gpt-oss-20b?
gpt-oss-20b is the stronger model overall, scoring 32.5 to 30.8 on the Noometry Index.
Is Codellama 34b Instruct or gpt-oss-20b better for coding?
gpt-oss-20b scores higher on coding benchmarks: 37.6 versus 28.5 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and gpt-oss-20b share?
10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and gpt-oss-20b has 34.