Model comparison
Claude 3.5 Sonnet vs Llama 3.1-8B
Claude 3.5 Sonnet is the stronger model overall, scoring 34.4 to 22.8 on the Noometry Index.
Last verified . 35 shared benchmarks.
MetaSummary
- They share 35 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 9 categories and Llama 3.1-8B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude 3.5 Sonnet leads 53.0 to 29.9.
- The biggest single-benchmark swing is WeirdML: 40% for Claude 3.5 Sonnet and 1.7% for Llama 3.1-8B.
- Llama 3.1-8B has downloadable open weights; the other is API-only.
Side by side
| Claude 3.5 Sonnet | Llama 3.1-8B | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 34.4 | 22.8 |
| Released | 2024-06-20 | 2024-07-23 |
| Weights | Proprietary | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.05 |
| Output $ / M tokens | — | $0.08 |
| 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: 39.5 (#145), Llama 3.1-8B: 19.9 (#335)
| Benchmark | Claude 3.5 Sonnet | Llama 3.1-8B |
|---|---|---|
| WeirdML | 40% | 1.7% |
| BigCodeBench Instruct | 46.8% | 32.8% |
| LMArena Coding | 1343 | 1195 |
| BigCodeBench Complete | 58.6% | 40.5% |
| HumanEval+ | 81.7% | 62.8% |
| MBPP+ | 74.3% | 55.6% |
| Aider Polyglot | 51.6% | — |
| SciCode | — | 13.2% |
| GSO | 4.6% | — |
| LiveBench Coding | 67.1% | — |
| CadEval | 48% | — |
Agentic & Tool Use Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 32.1 (#61), Llama 3.1-8B: 22.3 (#123)
| Benchmark | Claude 3.5 Sonnet | Llama 3.1-8B |
|---|---|---|
| BALROG | 32.6% | 15.1% |
| Berkeley Function Calling Leaderboard | — | 25.8% |
| TheAgentCompany | 24% | — |
| Cybench | 17.5% | — |
| METR Time Horizons | 45.2% | — |
Reasoning Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 22.5 (#176), Llama 3.1-8B: 14.5 (#316)
| Benchmark | Claude 3.5 Sonnet | Llama 3.1-8B |
|---|---|---|
| LMArena Hard Prompts | 1305 | 1175 |
| DTBench | 67.8% | 50.9% |
| Epoch Capabilities Index | 133.55 | 116.48 |
| SimpleBench | 41.4% | — |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |
| EnigmaEval | 0.9% | — |
| LiveBench Reasoning | 56.7% | — |
| LiveBench Data Analysis | 55% | — |
| LMCA | — | 5.4% |
| ForecastBench | 60.7 | — |
| LiveBench | 59% | — |
| PIQA | — | 81.2% |
Math Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 18.0 (#282), Llama 3.1-8B: 9.5 (#311)
| Benchmark | Claude 3.5 Sonnet | Llama 3.1-8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 1.7% |
| Omni-MATH | 27.6% | 13.7% |
| LMArena Math | 1306 | 1179 |
| MATH Level 5 | 56.9% | 22.9% |
| LiveBench Math | 52.3% | — |
| FrontierMath (Feb 2025 set) | 2.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
| GSM8K | — | 82.4% |
Knowledge Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 28.5 (#236), Llama 3.1-8B: 8.0 (#302)
| Benchmark | Claude 3.5 Sonnet | Llama 3.1-8B |
|---|---|---|
| GPQA Diamond | 55.3% | 27% |
| MMLU-Pro | 77.7% | 40.6% |
| GPQA (HELM) | 56.5% | 24.7% |
| LMArena Expert | 1264 | 1144 |
| MMLU | 87.3% | 56.1% |
| Humanity's Last Exam | 4.1% | — |
| Confabulations | 19.9% | — |
| BoolQ | — | 82.8% |
Multimodal Not comparable
Claude 3.5 Sonnet: 26.0 (#115), Llama 3.1-8B: —
| Benchmark | Claude 3.5 Sonnet | Llama 3.1-8B |
|---|---|---|
| LMArena Vision | 1125 | — |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
Multilingual Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 43.4 (#180), Llama 3.1-8B: 34.2 (#244)
| Benchmark | Claude 3.5 Sonnet | Llama 3.1-8B |
|---|---|---|
| LMArena Non-English | 1283 | 1148 |
| LMArena Chinese | 1271 | 1151 |
| LMArena French | 1304 | 1176 |
| LMArena German | 1297 | 1144 |
| LMArena Japanese | 1234 | 1061 |
| LMArena Korean | 1200 | 1053 |
| LMArena Russian | 1305 | 1158 |
| LMArena Spanish | 1289 | 1169 |
Instruction Following Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 69.0 (#177), Llama 3.1-8B: 59.1 (#253)
| Benchmark | Claude 3.5 Sonnet | Llama 3.1-8B |
|---|---|---|
| IFEval | 85.5% | 74.3% |
| LMArena Instruction Following | 1297 | 1159 |
| LiveBench Instruction Following | 69.3% | — |
Long Context Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 39.9 (#162), Llama 3.1-8B: 35.8 (#233)
| Benchmark | Claude 3.5 Sonnet | Llama 3.1-8B |
|---|---|---|
| LMArena Longer Query | 1311 | 1182 |
Writing & Preference Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 53.0 (#159), Llama 3.1-8B: 29.9 (#285)
| Benchmark | Claude 3.5 Sonnet | Llama 3.1-8B |
|---|---|---|
| LMArena Text | 1298 | 1187 |
| LMArena Creative Writing | 1292 | 1154 |
| EQ-Bench Creative Writing | 1451 | 713 |
| WildBench | 79.2% | 68.7% |
| LMArena Multi-Turn | 1326 | 1172 |
| Short-Story Creative Writing | 80.3% | — |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than Llama 3.1-8B?
Claude 3.5 Sonnet is the stronger model overall, scoring 34.4 to 22.8 on the Noometry Index.
Is Claude 3.5 Sonnet or Llama 3.1-8B better for coding?
Claude 3.5 Sonnet scores higher on coding benchmarks: 39.5 versus 19.9 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and Llama 3.1-8B share?
35 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Llama 3.1-8B has 43.