Model comparison
gpt-oss-120b vs Llama 4 Scout
gpt-oss-120b is the stronger model overall, scoring 36.3 to 27.7 on the Noometry Index.
Last verified . 34 shared benchmarks.
MetaSummary
- They share 34 benchmarks with published results for both. gpt-oss-120b scores higher in 8 categories and Llama 4 Scout in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-120b leads 52.5 to 19.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 88.9% for gpt-oss-120b and 7.8% for Llama 4 Scout.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $0.10 / $0.30 for Llama 4 Scout.
- gpt-oss-120b accepts more context: 131K tokens versus 128K.
Side by side
| gpt-oss-120b | Llama 4 Scout | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 36.3 | 27.7 |
| Released | 2025-08-05 | 2025-04-05 |
| Weights | Open | Open |
| Context window | 131K | 128K |
| Max output | 41K | 4K |
| Input $ / M tokens | $0.037 | $0.10 |
| Output $ / M tokens | $0.17 | $0.30 |
| Results tracked | 48 | 43 |
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 4 Scout: 20.2 (#339)
| Benchmark | gpt-oss-120b | Llama 4 Scout |
|---|---|---|
| SWE-bench Verified (bash only) | 26% | 9.1% |
| SciCode | 36% | 17% |
| LMArena Coding | 1380 | 1286 |
| Aider Polyglot | 41.8% | — |
| WeirdML | 48.2% | — |
| BigCodeBench Complete | — | 43.1% |
| ALE-Bench | 575.62 | — |
| AlgoTune | 1.41 | — |
Agentic & Tool Use Llama 4 Scout leads
gpt-oss-120b: 12.2 (#153), Llama 4 Scout: 24.6 (#119)
| Benchmark | gpt-oss-120b | Llama 4 Scout |
|---|---|---|
| Terminal-Bench | 18.7% | — |
| APEX-Agents | 4.4% | — |
| Berkeley Function Calling Leaderboard | — | 28.1% |
| METR Time Horizons | 56.6% | — |
| Vending-Bench 2 | -21.53 | — |
Reasoning gpt-oss-120b leads
gpt-oss-120b: 20.0 (#245), Llama 4 Scout: 9.1 (#345)
| Benchmark | gpt-oss-120b | Llama 4 Scout |
|---|---|---|
| Kagi LLM Benchmark | 58.6% | 36.9% |
| CritPt | 1.1% | 0% |
| LMArena Hard Prompts | 1364 | 1266 |
| DTBench | 76.3% | 57.9% |
| LMCA | 22.1% | 12% |
| Epoch Capabilities Index | 139.93 | 129.64 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | 22.1% | — |
| ARC-AGI-1 | — | 0.5% |
| Chess Puzzles | 20% | — |
| Mystery Game Puzzles | 2% | — |
| Surface Evolver Bench | 25% | — |
| ForecastBench | — | 57.5 |
Math gpt-oss-120b leads
gpt-oss-120b: 52.5 (#50), Llama 4 Scout: 19.6 (#286)
| Benchmark | gpt-oss-120b | Llama 4 Scout |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 7.8% |
| Omni-MATH | 68.8% | 37.3% |
| LMArena Math | 1389 | 1287 |
| MATH Level 5 | — | 62.3% |
| FrontierMath (Feb 2025 set) | — | 0% |
Knowledge gpt-oss-120b leads
gpt-oss-120b: 42.4 (#96), Llama 4 Scout: 31.9 (#217)
| Benchmark | gpt-oss-120b | Llama 4 Scout |
|---|---|---|
| GPQA Diamond | 75.8% | 51.8% |
| MMLU-Pro | 79.5% | 74.2% |
| Vectara Hallucination Rate | 14.2% | 7.7% |
| GPQA (HELM) | 68.4% | 50.7% |
| LMArena Expert | 1356 | 1235 |
| Confabulations | 15.7% | — |
Multimodal Not comparable
gpt-oss-120b: —, Llama 4 Scout: 32.2 (#102)
| Benchmark | gpt-oss-120b | Llama 4 Scout |
|---|---|---|
| LMArena Vision | — | 1118 |
| SpatialViz-Bench | — | 34.2% |
Multilingual gpt-oss-120b leads
gpt-oss-120b: 48.0 (#147), Llama 4 Scout: 41.0 (#212)
| Benchmark | gpt-oss-120b | Llama 4 Scout |
|---|---|---|
| LMArena Non-English | 1351 | 1252 |
| LMArena Chinese | 1385 | 1255 |
| LMArena French | 1369 | 1282 |
| LMArena German | 1353 | 1272 |
| LMArena Japanese | 1331 | 1206 |
| LMArena Korean | 1282 | 1207 |
| LMArena Russian | 1343 | 1263 |
| LMArena Spanish | 1389 | 1278 |
Instruction Following gpt-oss-120b leads
gpt-oss-120b: 69.3 (#173), Llama 4 Scout: 65.8 (#217)
| Benchmark | gpt-oss-120b | Llama 4 Scout |
|---|---|---|
| IFEval | 83.6% | 81.8% |
| LMArena Instruction Following | 1318 | 1248 |
Long Context gpt-oss-120b leads
gpt-oss-120b: 31.4 (#278), Llama 4 Scout: 27.5 (#294)
| Benchmark | gpt-oss-120b | Llama 4 Scout |
|---|---|---|
| Fiction.LiveBench | 44.4% | 36% |
| LMArena Longer Query | 1319 | 1265 |
Writing & Preference gpt-oss-120b leads
gpt-oss-120b: 46.5 (#217), Llama 4 Scout: 37.0 (#261)
| Benchmark | gpt-oss-120b | Llama 4 Scout |
|---|---|---|
| LMArena Text | 1365 | 1279 |
| LMArena Creative Writing | 1275 | 1249 |
| EQ-Bench Creative Writing | 961 | 783 |
| WildBench | 84.5% | 78% |
| LMArena Multi-Turn | 1340 | 1280 |
| Short-Story Creative Writing | 77.1% | — |
Frequently asked questions
Is gpt-oss-120b better than Llama 4 Scout?
gpt-oss-120b is the stronger model overall, scoring 36.3 to 27.7 on the Noometry Index.
Which is cheaper, gpt-oss-120b or Llama 4 Scout?
gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; Llama 4 Scout lists at $0.10 and $0.30.
Is gpt-oss-120b or Llama 4 Scout better for coding?
gpt-oss-120b scores higher on coding benchmarks: 33.5 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
gpt-oss-120b does, with 131K tokens against 128K.
How many benchmarks do gpt-oss-120b and Llama 4 Scout share?
34 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Llama 4 Scout has 43.