Model comparison
gpt-oss-120b vs Llama 2-70B
gpt-oss-120b is the stronger model overall, scoring 36.3 to 24.4 on the Noometry Index.
Last verified . 21 shared benchmarks.
MetaSummary
- They share 21 benchmarks with published results for both. gpt-oss-120b scores higher in 7 categories and Llama 2-70B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-120b leads 52.5 to 8.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 88.9% for gpt-oss-120b and 0% for Llama 2-70B.
Side by side
| gpt-oss-120b | Llama 2-70B | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 36.3 | 24.4 |
| 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 | 35 |
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 2-70B: 31.4 (#286)
| Benchmark | gpt-oss-120b | Llama 2-70B |
|---|---|---|
| LMArena Coding | 1380 | 1079 |
| 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 2-70B: —
| Benchmark | gpt-oss-120b | Llama 2-70B |
|---|---|---|
| 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 2-70B: 14.4 (#325)
| Benchmark | gpt-oss-120b | Llama 2-70B |
|---|---|---|
| LMArena Hard Prompts | 1364 | 1073 |
| DTBench | 76.3% | 41.6% |
| Epoch Capabilities Index | 139.93 | 113.79 |
| SimpleBench | 22.1% | — |
| Kagi LLM Benchmark | 58.6% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | 20% | — |
| Mystery Game Puzzles | 2% | — |
| LMCA | 22.1% | — |
| Surface Evolver Bench | 25% | — |
| BIG-Bench Hard | — | 64.9% |
| CommonsenseQA 2.0 | — | 50% |
| ForecastBench | — | 51.4 |
| HellaSwag | — | 85.3% |
| LAMBADA | — | 78.9% |
| PIQA | — | 82.8% |
| WinoGrande | — | 80.2% |
Math gpt-oss-120b leads
gpt-oss-120b: 52.5 (#50), Llama 2-70B: 8.1 (#326)
| Benchmark | gpt-oss-120b | Llama 2-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 0% |
| LMArena Math | 1389 | 1091 |
| Omni-MATH | 68.8% | — |
| MATH Level 5 | — | 3.3% |
| GSM8K | — | 69.6% |
Knowledge gpt-oss-120b leads
gpt-oss-120b: 42.4 (#96), Llama 2-70B: 7.4 (#310)
| Benchmark | gpt-oss-120b | Llama 2-70B |
|---|---|---|
| GPQA Diamond | 75.8% | 26.3% |
| LMArena Expert | 1356 | 1039 |
| MMLU-Pro | 79.5% | — |
| Confabulations | 15.7% | — |
| Vectara Hallucination Rate | 14.2% | — |
| GPQA (HELM) | 68.4% | — |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 88.6% |
| MMLU | — | 69.9% |
| OpenBookQA | — | 60.2% |
| TriviaQA | — | 87.6% |
Multilingual gpt-oss-120b leads
gpt-oss-120b: 48.0 (#147), Llama 2-70B: 27.7 (#274)
| Benchmark | gpt-oss-120b | Llama 2-70B |
|---|---|---|
| LMArena Non-English | 1351 | 1045 |
| LMArena Chinese | 1385 | 995 |
| LMArena French | 1369 | 1090 |
| LMArena German | 1353 | 1041 |
| LMArena Japanese | 1331 | 927 |
| LMArena Korean | 1282 | 964 |
| LMArena Russian | 1343 | 1083 |
| LMArena Spanish | 1389 | 1143 |
Instruction Following gpt-oss-120b leads
gpt-oss-120b: 69.3 (#173), Llama 2-70B: 54.9 (#278)
| Benchmark | gpt-oss-120b | Llama 2-70B |
|---|---|---|
| LMArena Instruction Following | 1318 | 1071 |
| IFEval | 83.6% | — |
Long Context Too close to call
gpt-oss-120b: 31.4 (#278), Llama 2-70B: 32.3 (#270)
| Benchmark | gpt-oss-120b | Llama 2-70B |
|---|---|---|
| LMArena Longer Query | 1319 | 1062 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference gpt-oss-120b leads
gpt-oss-120b: 46.5 (#217), Llama 2-70B: 32.3 (#279)
| Benchmark | gpt-oss-120b | Llama 2-70B |
|---|---|---|
| LMArena Text | 1365 | 1115 |
| LMArena Creative Writing | 1275 | 1075 |
| LMArena Multi-Turn | 1340 | 1088 |
| Short-Story Creative Writing | 77.1% | — |
| EQ-Bench Creative Writing | 961 | — |
| WildBench | 84.5% | — |
Frequently asked questions
Is gpt-oss-120b better than Llama 2-70B?
gpt-oss-120b is the stronger model overall, scoring 36.3 to 24.4 on the Noometry Index.
Is gpt-oss-120b or Llama 2-70B better for coding?
gpt-oss-120b scores higher on coding benchmarks: 33.5 versus 31.4 in the Noometry coding category.
How many benchmarks do gpt-oss-120b and Llama 2-70B share?
21 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Llama 2-70B has 35.