Model comparison
Claude 3.5 Sonnet vs Llama 4 Scout
Claude 3.5 Sonnet is the stronger model overall, scoring 34.6 to 27.7 on the Noometry Index.
Last verified . 32 shared benchmarks.
MetaSummary
- They share 32 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 7 categories and Llama 4 Scout in 3 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where Claude 3.5 Sonnet leads 39.0 to 20.2.
- The biggest single-benchmark swing is BigCodeBench Complete: 58.6% for Claude 3.5 Sonnet and 43.1% for Llama 4 Scout.
- Llama 4 Scout has downloadable open weights; the other is API-only.
Side by side
| Claude 3.5 Sonnet | Llama 4 Scout | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 34.6 | 27.7 |
| Released | 2024-06-20 | 2025-04-05 |
| Weights | Proprietary | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 60 | 43 |
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 Scout: 20.2 (#339)
| Benchmark | Claude 3.5 Sonnet | Llama 4 Scout |
|---|---|---|
| LMArena Coding | 1342 | 1286 |
| BigCodeBench Complete | 58.6% | 43.1% |
| SWE-bench Verified (bash only) | — | 9.1% |
| Aider Polyglot | 51.6% | — |
| SciCode | — | 17% |
| GSO | 4.6% | — |
| WeirdML | 40% | — |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| CadEval | 48% | — |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 32.3 (#67), Llama 4 Scout: 24.6 (#119)
| Benchmark | Claude 3.5 Sonnet | Llama 4 Scout |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.1% |
| 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 Scout: 9.1 (#345)
| Benchmark | Claude 3.5 Sonnet | Llama 4 Scout |
|---|---|---|
| LMArena Hard Prompts | 1305 | 1266 |
| DTBench | 67.8% | 57.9% |
| Epoch Capabilities Index | 133.55 | 129.64 |
| ForecastBench | 60.7 | 57.5 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | 41.4% | — |
| Kagi LLM Benchmark | — | 36.9% |
| ARC-AGI-1 | — | 0.5% |
| CritPt | — | 0% |
| EnigmaEval | 0.9% | — |
| LiveBench Reasoning | 56.7% | — |
| LiveBench Data Analysis | 55% | — |
| LMCA | — | 12% |
| LiveBench | 59% | — |
Math Too close to call
Claude 3.5 Sonnet: 19.2 (#288), Llama 4 Scout: 19.6 (#286)
| Benchmark | Claude 3.5 Sonnet | Llama 4 Scout |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 7.8% |
| Omni-MATH | 27.6% | 37.3% |
| LMArena Math | 1307 | 1287 |
| MATH Level 5 | 56.9% | 62.3% |
| FrontierMath (Feb 2025 set) | 2.1% | 0% |
| LiveBench Math | 52.3% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Llama 4 Scout leads
Claude 3.5 Sonnet: 28.6 (#245), Llama 4 Scout: 31.9 (#217)
| Benchmark | Claude 3.5 Sonnet | Llama 4 Scout |
|---|---|---|
| GPQA Diamond | 55.3% | 51.8% |
| MMLU-Pro | 77.7% | 74.2% |
| GPQA (HELM) | 56.5% | 50.7% |
| LMArena Expert | 1265 | 1235 |
| Humanity's Last Exam | 4.1% | — |
| Confabulations | 19.9% | — |
| Vectara Hallucination Rate | — | 7.7% |
| MMLU | 87.3% | — |
Multimodal Llama 4 Scout leads
Claude 3.5 Sonnet: 26.5 (#120), Llama 4 Scout: 32.2 (#102)
| Benchmark | Claude 3.5 Sonnet | Llama 4 Scout |
|---|---|---|
| LMArena Vision | 1125 | 1118 |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
| SpatialViz-Bench | — | 34.2% |
Multilingual Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 43.2 (#185), Llama 4 Scout: 41.0 (#212)
| Benchmark | Claude 3.5 Sonnet | Llama 4 Scout |
|---|---|---|
| LMArena Non-English | 1283 | 1252 |
| LMArena Chinese | 1272 | 1255 |
| LMArena French | 1305 | 1282 |
| LMArena German | 1297 | 1272 |
| LMArena Japanese | 1234 | 1206 |
| LMArena Korean | 1200 | 1207 |
| LMArena Russian | 1306 | 1263 |
| LMArena Spanish | 1290 | 1278 |
Instruction Following Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 68.8 (#182), Llama 4 Scout: 65.8 (#217)
| Benchmark | Claude 3.5 Sonnet | Llama 4 Scout |
|---|---|---|
| IFEval | 85.5% | 81.8% |
| LMArena Instruction Following | 1297 | 1248 |
| LiveBench Instruction Following | 69.3% | — |
Long Context Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 39.9 (#167), Llama 4 Scout: 27.5 (#294)
| Benchmark | Claude 3.5 Sonnet | Llama 4 Scout |
|---|---|---|
| LMArena Longer Query | 1311 | 1265 |
| Fiction.LiveBench | — | 36% |
Writing & Preference Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 52.9 (#164), Llama 4 Scout: 37.0 (#261)
| Benchmark | Claude 3.5 Sonnet | Llama 4 Scout |
|---|---|---|
| LMArena Text | 1298 | 1279 |
| LMArena Creative Writing | 1292 | 1249 |
| EQ-Bench Creative Writing | 1451 | 783 |
| WildBench | 79.2% | 78% |
| LMArena Multi-Turn | 1326 | 1280 |
| Short-Story Creative Writing | 80.3% | — |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than Llama 4 Scout?
Claude 3.5 Sonnet is the stronger model overall, scoring 34.6 to 27.7 on the Noometry Index.
Is Claude 3.5 Sonnet or Llama 4 Scout better for coding?
Claude 3.5 Sonnet scores higher on coding benchmarks: 39.0 versus 20.2 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and Llama 4 Scout share?
32 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Llama 4 Scout has 43.