Model comparison
Claude 3 Opus vs Llama 3.1-405B
Llama 3.1-405B is the stronger model overall, scoring 30.7 to 29.5 on the Noometry Index.
Last verified . 29 shared benchmarks.
MetaSummary
- They share 29 benchmarks with published results for both. Claude 3 Opus scores higher in 3 categories and Llama 3.1-405B in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude 3 Opus leads 47.2 to 38.9.
- The biggest single-benchmark swing is MATH Level 5: 37.5% for Claude 3 Opus and 49.8% for Llama 3.1-405B.
- Llama 3.1-405B has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Opus | Llama 3.1-405B | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 29.5 | 30.7 |
| Released | 2024-02-29 | 2024-07-23 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 46 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Claude 3 Opus: 32.9 (#267), Llama 3.1-405B: 33.1 (#262)
| Benchmark | Claude 3 Opus | Llama 3.1-405B |
|---|---|---|
| WeirdML | 19.2% | 21.4% |
| LMArena Coding | 1264 | 1291 |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 38.6% | — |
| BigCodeBench Complete | 57.4% | — |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Claude 3 Opus leads
Claude 3 Opus: 24.6 (#116), Llama 3.1-405B: 21.0 (#140)
| Benchmark | Claude 3 Opus | Llama 3.1-405B |
|---|---|---|
| Cybench | 10% | 7.5% |
| TheAgentCompany | — | 7.4% |
| METR Time Horizons | 29.5% | — |
Reasoning Llama 3.1-405B leads
Claude 3 Opus: 14.6 (#324), Llama 3.1-405B: 16.8 (#300)
| Benchmark | Claude 3 Opus | Llama 3.1-405B |
|---|---|---|
| SimpleBench | 23.5% | 23% |
| LMArena Hard Prompts | 1245 | 1269 |
| DTBench | 61.6% | 61.4% |
| Epoch Capabilities Index | 126.91 | 128.75 |
| ForecastBench | 58.4 | 59.9 |
| WinoGrande | 88.5% | 89.2% |
| Kagi LLM Benchmark | — | 45% |
| Chess Puzzles | 5% | — |
| EnigmaEval | 0.8% | — |
| LiveBench Reasoning | 40.6% | — |
| LiveBench Data Analysis | 57.9% | — |
| LMCA | 17% | — |
| BIG-Bench Hard | — | 82.9% |
| HellaSwag | — | 89.2% |
| LiveBench | 49.2% | — |
| PIQA | — | 85.9% |
Math Llama 3.1-405B leads
Claude 3 Opus: 14.8 (#299), Llama 3.1-405B: 18.4 (#290)
| Benchmark | Claude 3 Opus | Llama 3.1-405B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 9.7% |
| LMArena Math | 1273 | 1281 |
| MATH Level 5 | 37.5% | 49.8% |
| Omni-MATH | — | 24.9% |
| LiveBench Math | 43.6% | — |
Knowledge Llama 3.1-405B leads
Claude 3 Opus: 24.5 (#267), Llama 3.1-405B: 30.4 (#227)
| Benchmark | Claude 3 Opus | Llama 3.1-405B |
|---|---|---|
| GPQA Diamond | 47.2% | 50.9% |
| Confabulations | 22.7% | 17.6% |
| LMArena Expert | 1223 | 1243 |
| MMLU | 84.6% | 84.5% |
| SimpleQA Verified | 12.6% | — |
| MMLU-Pro | — | 72.3% |
| GPQA (HELM) | — | 52.2% |
| ARC (AI2) Challenge | — | 95.3% |
| TriviaQA | — | 82.7% |
Multimodal Not comparable
Claude 3 Opus: 27.1 (#116), Llama 3.1-405B: —
| Benchmark | Claude 3 Opus | Llama 3.1-405B |
|---|---|---|
| LMArena Vision | 1023 | — |
Multilingual Too close to call
Claude 3 Opus: 41.4 (#207), Llama 3.1-405B: 40.7 (#214)
| Benchmark | Claude 3 Opus | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 1258 | 1248 |
| LMArena Chinese | 1248 | 1242 |
| LMArena French | 1275 | 1279 |
| LMArena German | 1258 | 1252 |
| LMArena Japanese | 1204 | 1208 |
| LMArena Korean | 1187 | 1184 |
| LMArena Russian | 1280 | 1265 |
| LMArena Spanish | 1246 | 1260 |
Instruction Following Llama 3.1-405B leads
Claude 3 Opus: 64.1 (#228), Llama 3.1-405B: 65.9 (#214)
| Benchmark | Claude 3 Opus | Llama 3.1-405B |
|---|---|---|
| LMArena Instruction Following | 1248 | 1259 |
| LiveBench Instruction Following | 63.9% | — |
| IFEval | — | 81.1% |
Long Context Too close to call
Claude 3 Opus: 38.2 (#202), Llama 3.1-405B: 38.4 (#197)
| Benchmark | Claude 3 Opus | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 1259 | 1266 |
Writing & Preference Claude 3 Opus leads
Claude 3 Opus: 47.2 (#213), Llama 3.1-405B: 38.9 (#251)
| Benchmark | Claude 3 Opus | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1262 | 1284 |
| LMArena Creative Writing | 1235 | 1262 |
| LMArena Multi-Turn | 1275 | 1297 |
| EQ-Bench Creative Writing | — | 870 |
| WildBench | — | 78.3% |
| LiveBench Language | 50.4% | — |
Frequently asked questions
Is Claude 3 Opus better than Llama 3.1-405B?
Llama 3.1-405B is the stronger model overall, scoring 30.7 to 29.5 on the Noometry Index.
Is Claude 3 Opus or Llama 3.1-405B better for coding?
They score almost the same on coding (32.9 vs 33.1); test both on your own repository before choosing.
How many benchmarks do Claude 3 Opus and Llama 3.1-405B share?
29 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Llama 3.1-405B has 42.