Model comparison
Claude Sonnet 5 vs Llama 4 Scout
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 27.7 on the Noometry Index. Llama 4 Scout costs 27× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.
Last verified . 27 shared benchmarks.
MetaSummary
- They share 27 benchmarks with published results for both. Claude Sonnet 5 scores higher in 10 categories and Llama 4 Scout in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5 leads 66.2 to 19.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 94.7% for Claude Sonnet 5 and 7.8% for Llama 4 Scout.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.
- Claude Sonnet 5 accepts more context: 1M tokens versus 128K.
- Llama 4 Scout has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 5 | Llama 4 Scout | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 54.6 | 27.7 |
| Released | 2026-06-29 | 2025-04-05 |
| Weights | Proprietary | Open |
| Context window | 1M | 128K |
| Max output | 128K | 4K |
| Input $ / M tokens | $2 | $0.10 |
| Output $ / M tokens | $10 | $0.30 |
| Results tracked | 51 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 5 leads
Claude Sonnet 5: 55.5 (#26), Llama 4 Scout: 20.2 (#339)
| Benchmark | Claude Sonnet 5 | Llama 4 Scout |
|---|---|---|
| SciCode | 54.3% | 17% |
| LMArena Coding | 1483 | 1286 |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.7% | — |
| SWE-bench Verified (bash only) | — | 9.1% |
| CursorBench | 34.1% | — |
| LMArena WebDev | 1541 | — |
| GSO | 37.3% | — |
| WeirdML | 68.8% | — |
| BigCodeBench Complete | — | 43.1% |
| ALE-Bench | 1,463 | — |
Agentic & Tool Use Claude Sonnet 5 leads
Claude Sonnet 5: 42.8 (#18), Llama 4 Scout: 24.6 (#119)
| Benchmark | Claude Sonnet 5 | Llama 4 Scout |
|---|---|---|
| APEX-Agents | 54.5% | — |
| Berkeley Function Calling Leaderboard | — | 28.1% |
| GBAEval | 65.3% | — |
| LMArena Search | 1194 | — |
| Vending-Bench 2 | 6,378 | — |
Reasoning Claude Sonnet 5 leads
Claude Sonnet 5: 49.1 (#39), Llama 4 Scout: 9.1 (#345)
| Benchmark | Claude Sonnet 5 | Llama 4 Scout |
|---|---|---|
| CritPt | 16.9% | 0% |
| LMArena Hard Prompts | 1461 | 1266 |
| DTBench | 92.5% | 57.9% |
| LMCA | 50% | 12% |
| Epoch Capabilities Index | 156.21 | 129.64 |
| ForecastBench | 61.1 | 57.5 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | 60.6% | — |
| Kagi LLM Benchmark | — | 36.9% |
| NYT Connections (extended) | 75.1% | — |
| ARC-AGI-1 | — | 0.5% |
| Chess Puzzles | 35% | — |
| Mystery Game Puzzles | 35% | — |
| Surface Evolver Bench | 60% | — |
| Bench to the Future 3 | 0.14 | — |
Math Claude Sonnet 5 leads
Claude Sonnet 5: 66.2 (#27), Llama 4 Scout: 19.6 (#286)
| Benchmark | Claude Sonnet 5 | Llama 4 Scout |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 94.7% | 7.8% |
| LMArena Math | 1467 | 1287 |
| FrontierMath (Tiers 1-3) | 65.6% | — |
| FrontierMath Tier 4 | 29.3% | — |
| ProofBench | 77% | — |
| Omni-MATH | — | 37.3% |
| MATH Level 5 | — | 62.3% |
| FrontierMath (Feb 2025 set) | — | 0% |
Knowledge Claude Sonnet 5 leads
Claude Sonnet 5: 55.6 (#47), Llama 4 Scout: 31.9 (#217)
| Benchmark | Claude Sonnet 5 | Llama 4 Scout |
|---|---|---|
| GPQA Diamond | 90.5% | 51.8% |
| LMArena Expert | 1490 | 1235 |
| SimpleQA Verified | 33.7% | — |
| MMLU-Pro | — | 74.2% |
| Vectara Hallucination Rate | — | 7.7% |
| GPQA (HELM) | — | 50.7% |
Multimodal Claude Sonnet 5 leads
Claude Sonnet 5: 42.4 (#31), Llama 4 Scout: 32.2 (#102)
| Benchmark | Claude Sonnet 5 | Llama 4 Scout |
|---|---|---|
| LMArena Vision | 1274 | 1118 |
| Blueprint-Bench 2 | 24.9% | — |
| LMArena Document | 1466 | — |
| SpatialViz-Bench | — | 34.2% |
Multilingual Claude Sonnet 5 leads
Claude Sonnet 5: 53.8 (#55), Llama 4 Scout: 41.0 (#212)
| Benchmark | Claude Sonnet 5 | Llama 4 Scout |
|---|---|---|
| LMArena Non-English | 1431 | 1252 |
| LMArena Chinese | 1477 | 1255 |
| LMArena French | 1460 | 1282 |
| LMArena German | 1440 | 1272 |
| LMArena Japanese | 1422 | 1206 |
| LMArena Korean | 1411 | 1207 |
| LMArena Russian | 1451 | 1263 |
| LMArena Spanish | 1437 | 1278 |
Instruction Following Claude Sonnet 5 leads
Claude Sonnet 5: 76.3 (#41), Llama 4 Scout: 65.8 (#217)
| Benchmark | Claude Sonnet 5 | Llama 4 Scout |
|---|---|---|
| LMArena Instruction Following | 1452 | 1248 |
| IFEval | — | 81.8% |
Long Context Claude Sonnet 5 leads
Claude Sonnet 5: 44.8 (#55), Llama 4 Scout: 27.5 (#294)
| Benchmark | Claude Sonnet 5 | Llama 4 Scout |
|---|---|---|
| LMArena Longer Query | 1463 | 1265 |
| Fiction.LiveBench | — | 36% |
Writing & Preference Claude Sonnet 5 leads
Claude Sonnet 5: 69.2 (#25), Llama 4 Scout: 37.0 (#261)
| Benchmark | Claude Sonnet 5 | Llama 4 Scout |
|---|---|---|
| LMArena Text | 1442 | 1279 |
| LMArena Creative Writing | 1416 | 1249 |
| EQ-Bench Creative Writing | 1794 | 783 |
| LMArena Multi-Turn | 1454 | 1280 |
| WildBench | — | 78% |
| EQ-Bench 4 | 1236 | — |
Frequently asked questions
Is Claude Sonnet 5 better than Llama 4 Scout?
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 27.7 on the Noometry Index. Llama 4 Scout costs 27× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 5 or Llama 4 Scout?
Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Claude Sonnet 5 lists at $2 and $10.
Is Claude Sonnet 5 or Llama 4 Scout better for coding?
Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
Claude Sonnet 5 does, with 1M tokens against 128K.
How many benchmarks do Claude Sonnet 5 and Llama 4 Scout share?
27 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and Llama 4 Scout has 43.