Model comparison
Llama 3.1-405B vs Llama 4 Maverick
Llama 3.1-405B and Llama 4 Maverick score almost the same on the Noometry Index (30.7 vs 30.9), so choose on price, context window or the category you care about most.
Last verified . 33 shared benchmarks.
MetaSummary
- They share 33 benchmarks with published results for both. Llama 3.1-405B scores higher in 4 categories and Llama 4 Maverick in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Llama 4 Maverick leads 26.0 to 18.4.
- The biggest single-benchmark swing is MATH Level 5: 49.8% for Llama 3.1-405B and 73% for Llama 4 Maverick.
Side by side
| Llama 3.1-405B | Llama 4 Maverick | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 30.7 | 30.9 |
| Released | 2024-07-23 | 2025-04-05 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.19 |
| Output $ / M tokens | — | $0.65 |
| Results tracked | 42 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3.1-405B leads
Llama 3.1-405B: 33.1 (#262), Llama 4 Maverick: 26.6 (#324)
| Benchmark | Llama 3.1-405B | Llama 4 Maverick |
|---|---|---|
| WeirdML | 21.4% | 24.5% |
| LMArena Coding | 1291 | 1302 |
| SWE-bench Verified (bash only) | — | 21% |
| Aider Polyglot | — | 15.6% |
| SciCode | — | 33.1% |
| BigCodeBench Instruct | — | 49.7% |
| BigCodeBench Complete | — | 61.4% |
| ALE-Bench | — | 172.97 |
Agentic & Tool Use Llama 4 Maverick leads
Llama 3.1-405B: 21.0 (#140), Llama 4 Maverick: 28.2 (#91)
| Benchmark | Llama 3.1-405B | Llama 4 Maverick |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.3% |
| TheAgentCompany | 7.4% | — |
| Cybench | 7.5% | — |
Reasoning Llama 3.1-405B leads
Llama 3.1-405B: 16.8 (#300), Llama 4 Maverick: 10.1 (#342)
| Benchmark | Llama 3.1-405B | Llama 4 Maverick |
|---|---|---|
| SimpleBench | 23% | 27.7% |
| Kagi LLM Benchmark | 45% | 55.9% |
| LMArena Hard Prompts | 1269 | 1281 |
| DTBench | 61.4% | 61.9% |
| Epoch Capabilities Index | 128.75 | 132.2 |
| ForecastBench | 59.9 | 57.5 |
| ARC-AGI-2 | — | 0% |
| NYT Connections (extended) | — | 8% |
| ARC-AGI-1 | — | 4.4% |
| CritPt | — | 0% |
| EnigmaEval | — | 0.6% |
| LMCA | — | 15.9% |
| BIG-Bench Hard | 82.9% | — |
| HellaSwag | 89.2% | — |
| PIQA | 85.9% | — |
| WinoGrande | 89.2% | — |
Math Llama 4 Maverick leads
Llama 3.1-405B: 18.4 (#290), Llama 4 Maverick: 26.0 (#262)
| Benchmark | Llama 3.1-405B | Llama 4 Maverick |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 9.7% | 20.6% |
| Omni-MATH | 24.9% | 42.2% |
| LMArena Math | 1281 | 1299 |
| MATH Level 5 | 49.8% | 73% |
| FrontierMath (Feb 2025 set) | — | 0.7% |
Knowledge Llama 4 Maverick leads
Llama 3.1-405B: 30.4 (#227), Llama 4 Maverick: 33.4 (#204)
| Benchmark | Llama 3.1-405B | Llama 4 Maverick |
|---|---|---|
| GPQA Diamond | 50.9% | 67% |
| MMLU-Pro | 72.3% | 81% |
| Confabulations | 17.6% | 22.6% |
| GPQA (HELM) | 52.2% | 65% |
| LMArena Expert | 1243 | 1259 |
| Humanity's Last Exam | — | 5.7% |
| Vectara Hallucination Rate | — | 8.2% |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 84.5% | — |
| TriviaQA | 82.7% | — |
Multimodal Not comparable
Llama 3.1-405B: —, Llama 4 Maverick: 31.6 (#105)
| Benchmark | Llama 3.1-405B | Llama 4 Maverick |
|---|---|---|
| LMArena Vision | — | 1142 |
| GeoBench | — | 52% |
| SpatialViz-Bench | — | 31.8% |
Multilingual Llama 4 Maverick leads
Llama 3.1-405B: 40.7 (#214), Llama 4 Maverick: 42.2 (#195)
| Benchmark | Llama 3.1-405B | Llama 4 Maverick |
|---|---|---|
| LMArena Non-English | 1248 | 1269 |
| LMArena Chinese | 1242 | 1277 |
| LMArena French | 1279 | 1259 |
| LMArena German | 1252 | 1291 |
| LMArena Japanese | 1208 | 1207 |
| LMArena Korean | 1184 | 1203 |
| LMArena Russian | 1265 | 1286 |
| LMArena Spanish | 1260 | 1293 |
Instruction Following Llama 4 Maverick leads
Llama 3.1-405B: 65.9 (#214), Llama 4 Maverick: 71.7 (#146)
| Benchmark | Llama 3.1-405B | Llama 4 Maverick |
|---|---|---|
| IFEval | 81.1% | 90.8% |
| LMArena Instruction Following | 1259 | 1267 |
Long Context Llama 3.1-405B leads
Llama 3.1-405B: 38.4 (#197), Llama 4 Maverick: 31.4 (#279)
| Benchmark | Llama 3.1-405B | Llama 4 Maverick |
|---|---|---|
| LMArena Longer Query | 1266 | 1280 |
| Fiction.LiveBench | — | 46.2% |
Writing & Preference Too close to call
Llama 3.1-405B: 38.9 (#251), Llama 4 Maverick: 38.8 (#252)
| Benchmark | Llama 3.1-405B | Llama 4 Maverick |
|---|---|---|
| LMArena Text | 1284 | 1287 |
| LMArena Creative Writing | 1262 | 1267 |
| EQ-Bench Creative Writing | 870 | 860 |
| WildBench | 78.3% | 80% |
| LMArena Multi-Turn | 1297 | 1289 |
| Short-Story Creative Writing | — | 62% |
Frequently asked questions
Is Llama 3.1-405B better than Llama 4 Maverick?
Llama 3.1-405B and Llama 4 Maverick score almost the same on the Noometry Index (30.7 vs 30.9), so choose on price, context window or the category you care about most.
Is Llama 3.1-405B or Llama 4 Maverick better for coding?
Llama 3.1-405B scores higher on coding benchmarks: 33.1 versus 26.6 in the Noometry coding category.
How many benchmarks do Llama 3.1-405B and Llama 4 Maverick share?
33 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and Llama 4 Maverick has 54.