Model comparison
Llama 3.1-70B vs Llama 3-70B
Llama 3.1-70B and Llama 3-70B score almost the same on the Noometry Index (29.6 vs 28.8), so choose on price, context window or the category you care about most.
Last verified . 25 shared benchmarks.
MetaSummary
- They share 25 benchmarks with published results for both. Llama 3.1-70B scores higher in 7 categories and Llama 3-70B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Llama 3-70B leads 42.8 to 35.4.
- The biggest single-benchmark swing is MATH Level 5: 36.7% for Llama 3.1-70B and 22.6% for Llama 3-70B.
Side by side
| Llama 3.1-70B | Llama 3-70B | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 29.6 | 28.8 |
| Released | 2024-07-23 | 2024-04-18 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.40 | — |
| Output $ / M tokens | $0.40 | — |
| Results tracked | 35 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3-70B leads
Llama 3.1-70B: 30.3 (#296), Llama 3-70B: 35.8 (#218)
| Benchmark | Llama 3.1-70B | Llama 3-70B |
|---|---|---|
| BigCodeBench Instruct | 46.1% | 43.6% |
| LMArena Coding | 1260 | 1206 |
| BigCodeBench Complete | 54.8% | 54.5% |
| WeirdML | 9% | — |
| HumanEval+ | — | 72% |
| MBPP+ | — | 69% |
Agentic & Tool Use Llama 3.1-70B leads
Llama 3.1-70B: 25.1 (#112), Llama 3-70B: 21.1 (#139)
| Benchmark | Llama 3.1-70B | Llama 3-70B |
|---|---|---|
| TheAgentCompany | 6.9% | — |
| Cybench | — | 5% |
| BALROG | 27.9% | — |
Reasoning Llama 3.1-70B leads
Llama 3.1-70B: 21.6 (#220), Llama 3-70B: 18.0 (#288)
| Benchmark | Llama 3.1-70B | Llama 3-70B |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1195 |
| DTBench | 60% | 54.2% |
| Epoch Capabilities Index | 125.92 | 122.93 |
| Kagi LLM Benchmark | — | 35.1% |
| LMCA | 14.8% | — |
| ForecastBench | — | 57.1 |
| WinoGrande | — | 83.5% |
Math Too close to call
Llama 3.1-70B: 13.5 (#304), Llama 3-70B: 12.8 (#305)
| Benchmark | Llama 3.1-70B | Llama 3-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 3.6% | 4.3% |
| LMArena Math | 1252 | 1218 |
| MATH Level 5 | 36.7% | 22.6% |
| Omni-MATH | 21% | — |
Knowledge Llama 3.1-70B leads
Llama 3.1-70B: 24.2 (#269), Llama 3-70B: 20.8 (#277)
| Benchmark | Llama 3.1-70B | Llama 3-70B |
|---|---|---|
| GPQA Diamond | 44.2% | 40.6% |
| LMArena Expert | 1209 | 1149 |
| MMLU | 80.1% | 79.3% |
| MMLU-Pro | 65.3% | — |
| GPQA (HELM) | 42.6% | — |
Multilingual Llama 3.1-70B leads
Llama 3.1-70B: 38.8 (#225), Llama 3-70B: 33.6 (#251)
| Benchmark | Llama 3.1-70B | Llama 3-70B |
|---|---|---|
| LMArena Non-English | 1219 | 1142 |
| LMArena Chinese | 1215 | 1114 |
| LMArena French | 1261 | 1232 |
| LMArena German | 1222 | 1169 |
| LMArena Japanese | 1132 | 1017 |
| LMArena Korean | 1140 | 1017 |
| LMArena Russian | 1234 | 1159 |
| LMArena Spanish | 1253 | 1241 |
Instruction Following Llama 3.1-70B leads
Llama 3.1-70B: 65.3 (#223), Llama 3-70B: 62.5 (#238)
| Benchmark | Llama 3.1-70B | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | 1231 | 1194 |
| IFEval | 82.1% | — |
Long Context Llama 3.1-70B leads
Llama 3.1-70B: 37.6 (#214), Llama 3-70B: 35.6 (#240)
| Benchmark | Llama 3.1-70B | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | 1241 | 1174 |
Writing & Preference Llama 3-70B leads
Llama 3.1-70B: 35.4 (#267), Llama 3-70B: 42.8 (#231)
| Benchmark | Llama 3.1-70B | Llama 3-70B |
|---|---|---|
| LMArena Text | 1261 | 1221 |
| LMArena Creative Writing | 1232 | 1210 |
| LMArena Multi-Turn | 1256 | 1223 |
| EQ-Bench Creative Writing | 784 | — |
| WildBench | 75.8% | — |
Frequently asked questions
Is Llama 3.1-70B better than Llama 3-70B?
Llama 3.1-70B and Llama 3-70B score almost the same on the Noometry Index (29.6 vs 28.8), so choose on price, context window or the category you care about most.
Is Llama 3.1-70B or Llama 3-70B better for coding?
Llama 3-70B scores higher on coding benchmarks: 35.8 versus 30.3 in the Noometry coding category.
How many benchmarks do Llama 3.1-70B and Llama 3-70B share?
25 benchmarks have published results for both models. Llama 3.1-70B has 35 scored results on Noometry and Llama 3-70B has 31.