Model comparison
Claude Opus 4.1 vs Llama 3-70B
Claude Opus 4.1 is the stronger model overall, scoring 41.0 to 28.8 on the Noometry Index.
Last verified . 23 shared benchmarks.
MetaSummary
- They share 23 benchmarks with published results for both. Claude Opus 4.1 scores higher in 9 categories and Llama 3-70B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude Opus 4.1 leads 42.0 to 20.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 68.9% for Claude Opus 4.1 and 4.3% for Llama 3-70B.
- Llama 3-70B has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 4.1 | Llama 3-70B | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 41.0 | 28.8 |
| Released | 2025-08-05 | 2024-04-18 |
| Weights | Proprietary | Open |
| Context window | 200K | — |
| Max output | 32K | — |
| Input $ / M tokens | $15 | — |
| Output $ / M tokens | $75 | — |
| Results tracked | 48 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4.1 leads
Claude Opus 4.1: 44.4 (#73), Llama 3-70B: 35.8 (#218)
| Benchmark | Claude Opus 4.1 | Llama 3-70B |
|---|---|---|
| LMArena Coding | 1479 | 1206 |
| SWE-bench Verified | 73.3% | — |
| LMArena WebDev | 1390 | — |
| WeirdML | 45.9% | — |
| BigCodeBench Instruct | — | 43.6% |
| BigCodeBench Complete | — | 54.5% |
| ALE-Bench | 674.77 | — |
| AlgoTune | 1.34 | — |
| HumanEval+ | — | 72% |
| MBPP+ | — | 69% |
Agentic & Tool Use Claude Opus 4.1 leads
Claude Opus 4.1: 35.0 (#41), Llama 3-70B: 21.1 (#139)
| Benchmark | Claude Opus 4.1 | Llama 3-70B |
|---|---|---|
| Cybench | 42% | 5% |
| Terminal-Bench | 38% | — |
| GDPval | 43.6% | — |
| DeepResearch Bench | 48.3% | — |
| LMArena Search | 1148 | — |
| METR Time Horizons | 66.8% | — |
Reasoning Claude Opus 4.1 leads
Claude Opus 4.1: 32.2 (#76), Llama 3-70B: 18.0 (#288)
| Benchmark | Claude Opus 4.1 | Llama 3-70B |
|---|---|---|
| LMArena Hard Prompts | 1443 | 1195 |
| DTBench | 80% | 54.2% |
| Epoch Capabilities Index | 144.12 | 122.93 |
| ForecastBench | 62 | 57.1 |
| SimpleBench | 60% | — |
| Kagi LLM Benchmark | — | 35.1% |
| Chess Puzzles | 7% | — |
| EnigmaEval | 7.2% | — |
| EBR-Bench | 7.9% | — |
| Mystery Game Puzzles | 21% | — |
| LMCA | 37.1% | — |
| WinoGrande | — | 83.5% |
Math Claude Opus 4.1 leads
Claude Opus 4.1: 22.3 (#277), Llama 3-70B: 12.8 (#305)
| Benchmark | Claude Opus 4.1 | Llama 3-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 68.9% | 4.3% |
| LMArena Math | 1431 | 1218 |
| FrontierMath (Tiers 1-3) | 12.6% | — |
| FrontierMath Tier 4 | 2.4% | — |
| MATH Level 5 | — | 22.6% |
| FrontierMath (Feb 2025 set) | 7.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Claude Opus 4.1 leads
Claude Opus 4.1: 42.0 (#101), Llama 3-70B: 20.8 (#277)
| Benchmark | Claude Opus 4.1 | Llama 3-70B |
|---|---|---|
| GPQA Diamond | 77.3% | 40.6% |
| LMArena Expert | 1439 | 1149 |
| Humanity's Last Exam | 11.5% | — |
| Confabulations | 17.1% | — |
| Vectara Hallucination Rate | 11.8% | — |
| MMLU | — | 79.3% |
Multimodal Not comparable
Claude Opus 4.1: 26.8 (#119), Llama 3-70B: —
| Benchmark | Claude Opus 4.1 | Llama 3-70B |
|---|---|---|
| VPCT | 35% | — |
Multilingual Claude Opus 4.1 leads
Claude Opus 4.1: 52.0 (#95), Llama 3-70B: 33.6 (#251)
| Benchmark | Claude Opus 4.1 | Llama 3-70B |
|---|---|---|
| LMArena Non-English | 1405 | 1142 |
| LMArena Chinese | 1427 | 1114 |
| LMArena French | 1431 | 1232 |
| LMArena German | 1413 | 1169 |
| LMArena Japanese | 1378 | 1017 |
| LMArena Korean | 1380 | 1017 |
| LMArena Russian | 1422 | 1159 |
| LMArena Spanish | 1448 | 1241 |
Instruction Following Claude Opus 4.1 leads
Claude Opus 4.1: 75.6 (#58), Llama 3-70B: 62.5 (#238)
| Benchmark | Claude Opus 4.1 | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | 1435 | 1194 |
Long Context Claude Opus 4.1 leads
Claude Opus 4.1: 44.5 (#63), Llama 3-70B: 35.6 (#240)
| Benchmark | Claude Opus 4.1 | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | 1455 | 1174 |
Writing & Preference Claude Opus 4.1 leads
Claude Opus 4.1: 62.4 (#74), Llama 3-70B: 42.8 (#231)
| Benchmark | Claude Opus 4.1 | Llama 3-70B |
|---|---|---|
| LMArena Text | 1419 | 1221 |
| LMArena Creative Writing | 1412 | 1210 |
| LMArena Multi-Turn | 1444 | 1223 |
| Short-Story Creative Writing | 84.7% | — |
Frequently asked questions
Is Claude Opus 4.1 better than Llama 3-70B?
Claude Opus 4.1 is the stronger model overall, scoring 41.0 to 28.8 on the Noometry Index.
Is Claude Opus 4.1 or Llama 3-70B better for coding?
Claude Opus 4.1 scores higher on coding benchmarks: 44.4 versus 35.8 in the Noometry coding category.
How many benchmarks do Claude Opus 4.1 and Llama 3-70B share?
23 benchmarks have published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and Llama 3-70B has 31.