Model comparison
Claude 3.5 Sonnet vs Llama 4 Maverick
Claude 3.5 Sonnet is the stronger model overall, scoring 34.6 to 30.9 on the Noometry Index.
Last verified . 41 shared benchmarks.
MetaSummary
- They share 41 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 6 categories and Llama 4 Maverick in 4 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude 3.5 Sonnet leads 52.9 to 38.8.
- The biggest single-benchmark swing is Aider Polyglot: 51.6% for Claude 3.5 Sonnet and 15.6% for Llama 4 Maverick.
- Llama 4 Maverick has downloadable open weights; the other is API-only.
Side by side
| Claude 3.5 Sonnet | Llama 4 Maverick | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 34.6 | 30.9 |
| Released | 2024-06-20 | 2025-04-05 |
| Weights | Proprietary | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.19 |
| Output $ / M tokens | — | $0.65 |
| Results tracked | 60 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 39.0 (#165), Llama 4 Maverick: 26.6 (#324)
| Benchmark | Claude 3.5 Sonnet | Llama 4 Maverick |
|---|---|---|
| Aider Polyglot | 51.6% | 15.6% |
| WeirdML | 40% | 24.5% |
| BigCodeBench Instruct | 46.8% | 49.7% |
| LMArena Coding | 1342 | 1302 |
| BigCodeBench Complete | 58.6% | 61.4% |
| SWE-bench Verified (bash only) | — | 21% |
| SciCode | — | 33.1% |
| GSO | 4.6% | — |
| LiveBench Coding | 67.1% | — |
| CadEval | 48% | — |
| ALE-Bench | — | 172.97 |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 32.3 (#67), Llama 4 Maverick: 28.2 (#91)
| Benchmark | Claude 3.5 Sonnet | Llama 4 Maverick |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.3% |
| TheAgentCompany | 24% | — |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
| METR Time Horizons | 45.2% | — |
Reasoning Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 23.1 (#183), Llama 4 Maverick: 10.1 (#342)
| Benchmark | Claude 3.5 Sonnet | Llama 4 Maverick |
|---|---|---|
| SimpleBench | 41.4% | 27.7% |
| EnigmaEval | 0.9% | 0.6% |
| LMArena Hard Prompts | 1305 | 1281 |
| DTBench | 67.8% | 61.9% |
| Epoch Capabilities Index | 133.55 | 132.2 |
| ForecastBench | 60.7 | 57.5 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 55.9% |
| NYT Connections (extended) | — | 8% |
| ARC-AGI-1 | — | 4.4% |
| CritPt | — | 0% |
| LiveBench Reasoning | 56.7% | — |
| LiveBench Data Analysis | 55% | — |
| LMCA | — | 15.9% |
| LiveBench | 59% | — |
Math Llama 4 Maverick leads
Claude 3.5 Sonnet: 19.2 (#288), Llama 4 Maverick: 26.0 (#262)
| Benchmark | Claude 3.5 Sonnet | Llama 4 Maverick |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 20.6% |
| Omni-MATH | 27.6% | 42.2% |
| LMArena Math | 1307 | 1299 |
| MATH Level 5 | 56.9% | 73% |
| FrontierMath (Feb 2025 set) | 2.1% | 0.7% |
| LiveBench Math | 52.3% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Llama 4 Maverick leads
Claude 3.5 Sonnet: 28.6 (#245), Llama 4 Maverick: 33.4 (#204)
| Benchmark | Claude 3.5 Sonnet | Llama 4 Maverick |
|---|---|---|
| GPQA Diamond | 55.3% | 67% |
| Humanity's Last Exam | 4.1% | 5.7% |
| MMLU-Pro | 77.7% | 81% |
| Confabulations | 19.9% | 22.6% |
| GPQA (HELM) | 56.5% | 65% |
| LMArena Expert | 1265 | 1259 |
| Vectara Hallucination Rate | — | 8.2% |
| MMLU | 87.3% | — |
Multimodal Llama 4 Maverick leads
Claude 3.5 Sonnet: 26.5 (#120), Llama 4 Maverick: 31.6 (#105)
| Benchmark | Claude 3.5 Sonnet | Llama 4 Maverick |
|---|---|---|
| LMArena Vision | 1125 | 1142 |
| GeoBench | 62% | 52% |
| Video-MME | 60% | — |
| VPCT | 33% | — |
| SpatialViz-Bench | — | 31.8% |
Multilingual Too close to call
Claude 3.5 Sonnet: 43.2 (#185), Llama 4 Maverick: 42.2 (#195)
| Benchmark | Claude 3.5 Sonnet | Llama 4 Maverick |
|---|---|---|
| LMArena Non-English | 1283 | 1269 |
| LMArena Chinese | 1272 | 1277 |
| LMArena French | 1305 | 1259 |
| LMArena German | 1297 | 1291 |
| LMArena Japanese | 1234 | 1207 |
| LMArena Korean | 1200 | 1203 |
| LMArena Russian | 1306 | 1286 |
| LMArena Spanish | 1290 | 1293 |
Instruction Following Llama 4 Maverick leads
Claude 3.5 Sonnet: 68.8 (#182), Llama 4 Maverick: 71.7 (#146)
| Benchmark | Claude 3.5 Sonnet | Llama 4 Maverick |
|---|---|---|
| IFEval | 85.5% | 90.8% |
| LMArena Instruction Following | 1297 | 1267 |
| LiveBench Instruction Following | 69.3% | — |
Long Context Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 39.9 (#167), Llama 4 Maverick: 31.4 (#279)
| Benchmark | Claude 3.5 Sonnet | Llama 4 Maverick |
|---|---|---|
| LMArena Longer Query | 1311 | 1280 |
| Fiction.LiveBench | — | 46.2% |
Writing & Preference Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 52.9 (#164), Llama 4 Maverick: 38.8 (#252)
| Benchmark | Claude 3.5 Sonnet | Llama 4 Maverick |
|---|---|---|
| LMArena Text | 1298 | 1287 |
| LMArena Creative Writing | 1292 | 1267 |
| Short-Story Creative Writing | 80.3% | 62% |
| EQ-Bench Creative Writing | 1451 | 860 |
| WildBench | 79.2% | 80% |
| LMArena Multi-Turn | 1326 | 1289 |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than Llama 4 Maverick?
Claude 3.5 Sonnet is the stronger model overall, scoring 34.6 to 30.9 on the Noometry Index.
Is Claude 3.5 Sonnet or Llama 4 Maverick better for coding?
Claude 3.5 Sonnet scores higher on coding benchmarks: 39.0 versus 26.6 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and Llama 4 Maverick share?
41 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Llama 4 Maverick has 54.