Model comparison
gpt-oss-120b vs Llama 2-13B
gpt-oss-120b is the stronger model overall, scoring 36.3 to 29.6 on the Noometry Index.
Last verified . 20 shared benchmarks.
MetaSummary
- They share 20 benchmarks with published results for both. gpt-oss-120b scores higher in 7 categories and Llama 2-13B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where gpt-oss-120b leads 48.0 to 26.5.
- The biggest single-benchmark swing is DTBench: 76.3% for gpt-oss-120b and 42.2% for Llama 2-13B.
Side by side
| gpt-oss-120b | Llama 2-13B | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 36.3 | 29.6 |
| Released | 2025-08-05 | 2023-07-18 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 41K | — |
| Input $ / M tokens | $0.037 | — |
| Output $ / M tokens | $0.17 | — |
| Results tracked | 48 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding gpt-oss-120b leads
gpt-oss-120b: 33.5 (#256), Llama 2-13B: 30.9 (#291)
| Benchmark | gpt-oss-120b | Llama 2-13B |
|---|---|---|
| LMArena Coding | 1380 | 1062 |
| 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 Not comparable
gpt-oss-120b: 12.2 (#153), Llama 2-13B: —
| Benchmark | gpt-oss-120b | Llama 2-13B |
|---|---|---|
| Terminal-Bench | 18.7% | — |
| APEX-Agents | 4.4% | — |
| METR Time Horizons | 56.6% | — |
| Vending-Bench 2 | -21.53 | — |
Reasoning gpt-oss-120b leads
gpt-oss-120b: 20.0 (#245), Llama 2-13B: 12.8 (#337)
| Benchmark | gpt-oss-120b | Llama 2-13B |
|---|---|---|
| Chess Puzzles | 20% | 0% |
| LMArena Hard Prompts | 1364 | 1051 |
| DTBench | 76.3% | 42.2% |
| Epoch Capabilities Index | 139.93 | 106.17 |
| SimpleBench | 22.1% | — |
| Kagi LLM Benchmark | 58.6% | — |
| CritPt | 1.1% | — |
| Mystery Game Puzzles | 2% | — |
| LMCA | 22.1% | — |
| Surface Evolver Bench | 25% | — |
| BIG-Bench Hard | — | 58.2% |
| HellaSwag | — | 80.7% |
| LAMBADA | — | 76.5% |
| PIQA | — | 80.8% |
| WinoGrande | — | 72.8% |
Math gpt-oss-120b leads
gpt-oss-120b: 52.5 (#50), Llama 2-13B: 31.1 (#229)
| Benchmark | gpt-oss-120b | Llama 2-13B |
|---|---|---|
| LMArena Math | 1389 | 1065 |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| Omni-MATH | 68.8% | — |
| GSM8K | — | 36.9% |
Knowledge gpt-oss-120b leads
gpt-oss-120b: 42.4 (#96), Llama 2-13B: 28.1 (#249)
| Benchmark | gpt-oss-120b | Llama 2-13B |
|---|---|---|
| LMArena Expert | 1356 | 1030 |
| GPQA Diamond | 75.8% | — |
| MMLU-Pro | 79.5% | — |
| Confabulations | 15.7% | — |
| Vectara Hallucination Rate | 14.2% | — |
| GPQA (HELM) | 68.4% | — |
| ARC (AI2) Challenge | — | 60.3% |
| BoolQ | — | 82.4% |
| MMLU | — | 55.6% |
| OpenBookQA | — | 57% |
| TriviaQA | — | 79.6% |
Multimodal Not comparable
gpt-oss-120b: —, Llama 2-13B: —
| Benchmark | gpt-oss-120b | Llama 2-13B |
|---|---|---|
| ScienceQA | — | 55.8% |
Multilingual gpt-oss-120b leads
gpt-oss-120b: 48.0 (#147), Llama 2-13B: 26.5 (#279)
| Benchmark | gpt-oss-120b | Llama 2-13B |
|---|---|---|
| LMArena Non-English | 1351 | 1024 |
| LMArena Chinese | 1385 | 1001 |
| LMArena French | 1369 | 1044 |
| LMArena German | 1353 | 1009 |
| LMArena Japanese | 1331 | 894 |
| LMArena Korean | 1282 | 953 |
| LMArena Russian | 1343 | 1055 |
| LMArena Spanish | 1389 | 1087 |
Instruction Following gpt-oss-120b leads
gpt-oss-120b: 69.3 (#173), Llama 2-13B: 53.3 (#287)
| Benchmark | gpt-oss-120b | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | 1318 | 1045 |
| IFEval | 83.6% | — |
Long Context Too close to call
gpt-oss-120b: 31.4 (#278), Llama 2-13B: 32.3 (#269)
| Benchmark | gpt-oss-120b | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | 1319 | 1064 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference gpt-oss-120b leads
gpt-oss-120b: 46.5 (#217), Llama 2-13B: 29.8 (#289)
| Benchmark | gpt-oss-120b | Llama 2-13B |
|---|---|---|
| LMArena Text | 1365 | 1084 |
| LMArena Creative Writing | 1275 | 1047 |
| LMArena Multi-Turn | 1340 | 1050 |
| Short-Story Creative Writing | 77.1% | — |
| EQ-Bench Creative Writing | 961 | — |
| WildBench | 84.5% | — |
Frequently asked questions
Is gpt-oss-120b better than Llama 2-13B?
gpt-oss-120b is the stronger model overall, scoring 36.3 to 29.6 on the Noometry Index.
Is gpt-oss-120b or Llama 2-13B better for coding?
gpt-oss-120b scores higher on coding benchmarks: 33.5 versus 30.9 in the Noometry coding category.
How many benchmarks do gpt-oss-120b and Llama 2-13B share?
20 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Llama 2-13B has 32.