Model comparison
Claude Sonnet 4.6 vs Llama 3.1-405B
Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 30.7 on the Noometry Index.
Last verified . 24 shared benchmarks.
MetaSummary
- They share 24 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 9 categories and Llama 3.1-405B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 4.6 leads 52.9 to 18.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 85.8% for Claude Sonnet 4.6 and 9.7% for Llama 3.1-405B.
- Llama 3.1-405B has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4.6 | Llama 3.1-405B | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 50.3 | 30.7 |
| Released | 2026-02-17 | 2024-07-23 |
| Weights | Proprietary | Open |
| Context window | 1M | — |
| Max output | 128K | — |
| Input $ / M tokens | $3 | — |
| Output $ / M tokens | $15 | — |
| Results tracked | 57 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 46.3 (#67), Llama 3.1-405B: 33.1 (#262)
| Benchmark | Claude Sonnet 4.6 | Llama 3.1-405B |
|---|---|---|
| WeirdML | 66.1% | 21.4% |
| LMArena Coding | 1504 | 1291 |
| SWE-bench Verified | 75.2% | — |
| DeepSWE | 29.9% | — |
| FrontierCode | 24.3% | — |
| LMArena WebDev | 1522 | — |
| SciCode | 46.8% | — |
| ALE-Bench | 1,327 | — |
Agentic & Tool Use Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 39.1 (#28), Llama 3.1-405B: 21.0 (#140)
| Benchmark | Claude Sonnet 4.6 | Llama 3.1-405B |
|---|---|---|
| Terminal-Bench | 53.4% | — |
| APEX-Agents | 43% | — |
| OSWorld 2.0 | 9.3% | — |
| TheAgentCompany | — | 7.4% |
| Cybench | — | 7.5% |
| DeepResearch Bench | 54.9% | — |
| OSWorld | 72.1% | — |
| ExploitBench | 23.6% | — |
| GBAEval | 48.8% | — |
| GDP.pdf | 18% | — |
| LMArena Search | 1221 | — |
| Vending-Bench 2 | 7,204 | — |
Reasoning Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 46.1 (#45), Llama 3.1-405B: 16.8 (#300)
| Benchmark | Claude Sonnet 4.6 | Llama 3.1-405B |
|---|---|---|
| LMArena Hard Prompts | 1484 | 1269 |
| DTBench | 89.9% | 61.4% |
| Epoch Capabilities Index | 152.24 | 128.75 |
| ForecastBench | 62 | 59.9 |
| ARC-AGI-2 | 60.4% | — |
| SimpleBench | — | 23% |
| Kagi LLM Benchmark | — | 45% |
| NYT Connections (extended) | 80.9% | — |
| ARC-AGI-1 | 86.5% | — |
| CritPt | 3.1% | — |
| Chess Puzzles | 13% | — |
| Thematic Generalization | 76.3% | — |
| Mystery Game Puzzles | 16% | — |
| LMCA | 46.5% | — |
| BIG-Bench Hard | — | 82.9% |
| HellaSwag | — | 89.2% |
| PIQA | — | 85.9% |
| WinoGrande | — | 89.2% |
Math Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 52.9 (#49), Llama 3.1-405B: 18.4 (#290)
| Benchmark | Claude Sonnet 4.6 | Llama 3.1-405B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 85.8% | 9.7% |
| LMArena Math | 1462 | 1281 |
| ProofBench | 45% | — |
| Omni-MATH | — | 24.9% |
| MATH Level 5 | — | 49.8% |
| FrontierMath (Feb 2025 set) | 32.4% | — |
| FrontierMath Tier 4 (v1) | 8.3% | — |
Knowledge Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 51.7 (#65), Llama 3.1-405B: 30.4 (#227)
| Benchmark | Claude Sonnet 4.6 | Llama 3.1-405B |
|---|---|---|
| GPQA Diamond | 87.4% | 50.9% |
| LMArena Expert | 1500 | 1243 |
| SimpleQA Verified | 35.5% | — |
| MMLU-Pro | — | 72.3% |
| Confabulations | — | 17.6% |
| Vectara Hallucination Rate | 10.6% | — |
| GPQA (HELM) | — | 52.2% |
| ARC (AI2) Challenge | — | 95.3% |
| MMLU | — | 84.5% |
| TriviaQA | — | 82.7% |
Multimodal Not comparable
Claude Sonnet 4.6: 38.0 (#68), Llama 3.1-405B: —
| Benchmark | Claude Sonnet 4.6 | Llama 3.1-405B |
|---|---|---|
| LMArena Vision | 1283 | — |
| Blueprint-Bench 2 | 6.7% | — |
| LMArena Document | 1482 | — |
Multilingual Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 54.4 (#41), Llama 3.1-405B: 40.7 (#214)
| Benchmark | Claude Sonnet 4.6 | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 1440 | 1248 |
| LMArena Chinese | 1491 | 1242 |
| LMArena French | 1465 | 1279 |
| LMArena German | 1428 | 1252 |
| LMArena Japanese | 1420 | 1208 |
| LMArena Korean | 1411 | 1184 |
| LMArena Russian | 1440 | 1265 |
| LMArena Spanish | 1464 | 1260 |
Instruction Following Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 77.4 (#25), Llama 3.1-405B: 65.9 (#214)
| Benchmark | Claude Sonnet 4.6 | Llama 3.1-405B |
|---|---|---|
| LMArena Instruction Following | 1475 | 1259 |
| IFEval | — | 81.1% |
Long Context Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 45.3 (#44), Llama 3.1-405B: 38.4 (#197)
| Benchmark | Claude Sonnet 4.6 | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 1479 | 1266 |
Writing & Preference Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 70.2 (#22), Llama 3.1-405B: 38.9 (#251)
| Benchmark | Claude Sonnet 4.6 | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1458 | 1284 |
| LMArena Creative Writing | 1435 | 1262 |
| EQ-Bench Creative Writing | 1810 | 870 |
| LMArena Multi-Turn | 1464 | 1297 |
| WildBench | — | 78.3% |
| EQ-Bench 4 | 1207 | — |
Frequently asked questions
Is Claude Sonnet 4.6 better than Llama 3.1-405B?
Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 30.7 on the Noometry Index.
Is Claude Sonnet 4.6 or Llama 3.1-405B better for coding?
Claude Sonnet 4.6 scores higher on coding benchmarks: 46.3 versus 33.1 in the Noometry coding category.
How many benchmarks do Claude Sonnet 4.6 and Llama 3.1-405B share?
24 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Llama 3.1-405B has 42.