Model comparison
gpt-oss-120b vs Llama 4 Maverick
gpt-oss-120b is the stronger model overall, scoring 36.0 to 30.6 on the Noometry Index.
Last verified . 40 shared benchmarks.
MetaSummary
- They share 40 benchmarks with published results for both. gpt-oss-120b scores higher in 7 categories and Llama 4 Maverick in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-120b leads 50.6 to 24.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 88.9% for gpt-oss-120b and 20.6% for Llama 4 Maverick.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $0.19 / $0.65 for Llama 4 Maverick.
- gpt-oss-120b accepts more context: 131K tokens versus 128K.
Side by side
| gpt-oss-120b | Llama 4 Maverick | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 36.0 | 30.6 |
| Released | 2025-08-05 | 2025-04-05 |
| Weights | Open | Open |
| Context window | 131K | 128K |
| Max output | 41K | 4K |
| Input $ / M tokens | $0.037 | $0.19 |
| Output $ / M tokens | $0.17 | $0.65 |
| Results tracked | 48 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding gpt-oss-120b leads
gpt-oss-120b: 33.2 (#251), Llama 4 Maverick: 26.3 (#318)
| Benchmark | gpt-oss-120b | Llama 4 Maverick |
|---|---|---|
| SWE-bench Verified (bash only) | 26% | 21% |
| Aider Polyglot | 41.8% | 15.6% |
| SciCode | 36% | 33.1% |
| WeirdML | 48.2% | 24.5% |
| LMArena Coding | 1380 | 1302 |
| ALE-Bench | 575.62 | 172.97 |
| BigCodeBench Instruct | — | 49.7% |
| BigCodeBench Complete | — | 61.4% |
| AlgoTune | 1.41 | — |
Agentic & Tool Use Llama 4 Maverick leads
gpt-oss-120b: 12.1 (#145), Llama 4 Maverick: 27.9 (#86)
| Benchmark | gpt-oss-120b | Llama 4 Maverick |
|---|---|---|
| Terminal-Bench | 18.7% | — |
| APEX-Agents | 4.4% | — |
| Berkeley Function Calling Leaderboard | — | 37.3% |
| METR Time Horizons | 56.6% | — |
| Vending-Bench 2 | -21.53 | — |
Reasoning gpt-oss-120b leads
gpt-oss-120b: 19.5 (#236), Llama 4 Maverick: 10.1 (#337)
| Benchmark | gpt-oss-120b | Llama 4 Maverick |
|---|---|---|
| SimpleBench | 22.1% | 27.7% |
| Kagi LLM Benchmark | 58.6% | 55.9% |
| CritPt | 1.1% | 0% |
| LMArena Hard Prompts | 1364 | 1281 |
| DTBench | 76.3% | 61.9% |
| LMCA | 22.1% | 15.9% |
| Epoch Capabilities Index | 139.94 | 132.2 |
| ARC-AGI-2 | — | 0% |
| NYT Connections (extended) | — | 8% |
| ARC-AGI-1 | — | 4.4% |
| Chess Puzzles | 20% | — |
| EnigmaEval | — | 0.6% |
| Mystery Game Puzzles | 2% | — |
| Surface Evolver Bench | 25% | — |
| ForecastBench | — | 57.5 |
Math gpt-oss-120b leads
gpt-oss-120b: 50.6 (#43), Llama 4 Maverick: 24.6 (#256)
| Benchmark | gpt-oss-120b | Llama 4 Maverick |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 20.6% |
| Omni-MATH | 68.8% | 42.2% |
| LMArena Math | 1388 | 1299 |
| MATH Level 5 | — | 73% |
| FrontierMath (Feb 2025 set) | — | 0.7% |
Knowledge gpt-oss-120b leads
gpt-oss-120b: 42.3 (#89), Llama 4 Maverick: 33.3 (#196)
| Benchmark | gpt-oss-120b | Llama 4 Maverick |
|---|---|---|
| GPQA Diamond | 75.8% | 67% |
| MMLU-Pro | 79.5% | 81% |
| Confabulations | 15.7% | 22.6% |
| Vectara Hallucination Rate | 14.2% | 8.2% |
| GPQA (HELM) | 68.4% | 65% |
| LMArena Expert | 1356 | 1259 |
| Humanity's Last Exam | — | 5.7% |
Multimodal Not comparable
gpt-oss-120b: —, Llama 4 Maverick: 30.9 (#100)
| Benchmark | gpt-oss-120b | Llama 4 Maverick |
|---|---|---|
| LMArena Vision | — | 1141 |
| GeoBench | — | 52% |
| SpatialViz-Bench | — | 31.8% |
Multilingual gpt-oss-120b leads
gpt-oss-120b: 48.2 (#142), Llama 4 Maverick: 42.4 (#190)
| Benchmark | gpt-oss-120b | Llama 4 Maverick |
|---|---|---|
| LMArena Non-English | 1350 | 1269 |
| LMArena Chinese | 1384 | 1277 |
| LMArena French | 1370 | 1258 |
| LMArena German | 1355 | 1291 |
| LMArena Japanese | 1332 | 1207 |
| LMArena Korean | 1283 | 1203 |
| LMArena Russian | 1343 | 1286 |
| LMArena Spanish | 1388 | 1293 |
Instruction Following Llama 4 Maverick leads
gpt-oss-120b: 69.5 (#168), Llama 4 Maverick: 71.9 (#140)
| Benchmark | gpt-oss-120b | Llama 4 Maverick |
|---|---|---|
| IFEval | 83.6% | 90.8% |
| LMArena Instruction Following | 1318 | 1267 |
Long Context Too close to call
gpt-oss-120b: 31.4 (#273), Llama 4 Maverick: 31.4 (#274)
| Benchmark | gpt-oss-120b | Llama 4 Maverick |
|---|---|---|
| Fiction.LiveBench | 44.4% | 46.2% |
| LMArena Longer Query | 1319 | 1280 |
Writing & Preference gpt-oss-120b leads
gpt-oss-120b: 46.7 (#213), Llama 4 Maverick: 39.0 (#247)
| Benchmark | gpt-oss-120b | Llama 4 Maverick |
|---|---|---|
| LMArena Text | 1366 | 1287 |
| LMArena Creative Writing | 1274 | 1266 |
| Short-Story Creative Writing | 77.1% | 62% |
| EQ-Bench Creative Writing | 961 | 860 |
| WildBench | 84.5% | 80% |
| LMArena Multi-Turn | 1340 | 1289 |
Frequently asked questions
Is gpt-oss-120b better than Llama 4 Maverick?
gpt-oss-120b is the stronger model overall, scoring 36.0 to 30.6 on the Noometry Index.
Which is cheaper, gpt-oss-120b or Llama 4 Maverick?
gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; Llama 4 Maverick lists at $0.19 and $0.65.
Is gpt-oss-120b or Llama 4 Maverick better for coding?
gpt-oss-120b scores higher on coding benchmarks: 33.2 versus 26.3 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 Maverick share?
40 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Llama 4 Maverick has 54.