Model comparison
Claude 3 Opus vs Llama 3.1-70B
Claude 3 Opus and Llama 3.1-70B score almost the same on the Noometry Index (29.5 vs 29.6), so choose on price, context window or the category you care about most.
Last verified . 27 shared benchmarks.
MetaSummary
- They share 27 benchmarks with published results for both. Claude 3 Opus scores higher in 6 categories and Llama 3.1-70B in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude 3 Opus leads 47.2 to 35.4.
- The biggest single-benchmark swing is WeirdML: 19.2% for Claude 3 Opus and 9% for Llama 3.1-70B.
- Llama 3.1-70B has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Opus | Llama 3.1-70B | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 29.5 | 29.6 |
| Released | 2024-02-29 | 2024-07-23 |
| Weights | Proprietary | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.40 |
| Output $ / M tokens | — | $0.40 |
| Results tracked | 46 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3 Opus leads
Claude 3 Opus: 32.9 (#267), Llama 3.1-70B: 30.3 (#296)
| Benchmark | Claude 3 Opus | Llama 3.1-70B |
|---|---|---|
| WeirdML | 19.2% | 9% |
| BigCodeBench Instruct | 45.5% | 46.1% |
| LMArena Coding | 1264 | 1260 |
| BigCodeBench Complete | 57.4% | 54.8% |
| LiveBench Coding | 38.6% | — |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Too close to call
Claude 3 Opus: 24.6 (#116), Llama 3.1-70B: 25.1 (#112)
| Benchmark | Claude 3 Opus | Llama 3.1-70B |
|---|---|---|
| TheAgentCompany | — | 6.9% |
| Cybench | 10% | — |
| BALROG | — | 27.9% |
| METR Time Horizons | 29.5% | — |
Reasoning Llama 3.1-70B leads
Claude 3 Opus: 14.6 (#324), Llama 3.1-70B: 21.6 (#220)
| Benchmark | Claude 3 Opus | Llama 3.1-70B |
|---|---|---|
| LMArena Hard Prompts | 1245 | 1241 |
| DTBench | 61.6% | 60% |
| LMCA | 17% | 14.8% |
| Epoch Capabilities Index | 126.91 | 125.92 |
| SimpleBench | 23.5% | — |
| Chess Puzzles | 5% | — |
| EnigmaEval | 0.8% | — |
| LiveBench Reasoning | 40.6% | — |
| LiveBench Data Analysis | 57.9% | — |
| ForecastBench | 58.4 | — |
| LiveBench | 49.2% | — |
| WinoGrande | 88.5% | — |
Math Claude 3 Opus leads
Claude 3 Opus: 14.8 (#299), Llama 3.1-70B: 13.5 (#304)
| Benchmark | Claude 3 Opus | Llama 3.1-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 3.6% |
| LMArena Math | 1273 | 1252 |
| MATH Level 5 | 37.5% | 36.7% |
| Omni-MATH | — | 21% |
| LiveBench Math | 43.6% | — |
Knowledge Too close to call
Claude 3 Opus: 24.5 (#267), Llama 3.1-70B: 24.2 (#269)
| Benchmark | Claude 3 Opus | Llama 3.1-70B |
|---|---|---|
| GPQA Diamond | 47.2% | 44.2% |
| LMArena Expert | 1223 | 1209 |
| MMLU | 84.6% | 80.1% |
| SimpleQA Verified | 12.6% | — |
| MMLU-Pro | — | 65.3% |
| Confabulations | 22.7% | — |
| GPQA (HELM) | — | 42.6% |
Multimodal Not comparable
Claude 3 Opus: 27.1 (#116), Llama 3.1-70B: —
| Benchmark | Claude 3 Opus | Llama 3.1-70B |
|---|---|---|
| LMArena Vision | 1023 | — |
Multilingual Claude 3 Opus leads
Claude 3 Opus: 41.4 (#207), Llama 3.1-70B: 38.8 (#225)
| Benchmark | Claude 3 Opus | Llama 3.1-70B |
|---|---|---|
| LMArena Non-English | 1258 | 1219 |
| LMArena Chinese | 1248 | 1215 |
| LMArena French | 1275 | 1261 |
| LMArena German | 1258 | 1222 |
| LMArena Japanese | 1204 | 1132 |
| LMArena Korean | 1187 | 1140 |
| LMArena Russian | 1280 | 1234 |
| LMArena Spanish | 1246 | 1253 |
Instruction Following Llama 3.1-70B leads
Claude 3 Opus: 64.1 (#228), Llama 3.1-70B: 65.3 (#223)
| Benchmark | Claude 3 Opus | Llama 3.1-70B |
|---|---|---|
| LMArena Instruction Following | 1248 | 1231 |
| LiveBench Instruction Following | 63.9% | — |
| IFEval | — | 82.1% |
Long Context Too close to call
Claude 3 Opus: 38.2 (#202), Llama 3.1-70B: 37.6 (#214)
| Benchmark | Claude 3 Opus | Llama 3.1-70B |
|---|---|---|
| LMArena Longer Query | 1259 | 1241 |
Writing & Preference Claude 3 Opus leads
Claude 3 Opus: 47.2 (#213), Llama 3.1-70B: 35.4 (#267)
| Benchmark | Claude 3 Opus | Llama 3.1-70B |
|---|---|---|
| LMArena Text | 1262 | 1261 |
| LMArena Creative Writing | 1235 | 1232 |
| LMArena Multi-Turn | 1275 | 1256 |
| EQ-Bench Creative Writing | — | 784 |
| WildBench | — | 75.8% |
| LiveBench Language | 50.4% | — |
Frequently asked questions
Is Claude 3 Opus better than Llama 3.1-70B?
Claude 3 Opus and Llama 3.1-70B score almost the same on the Noometry Index (29.5 vs 29.6), so choose on price, context window or the category you care about most.
Is Claude 3 Opus or Llama 3.1-70B better for coding?
Claude 3 Opus scores higher on coding benchmarks: 32.9 versus 30.3 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and Llama 3.1-70B share?
27 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Llama 3.1-70B has 35.