Model comparison
Llama 3-8B vs Llama2 70b Steerlm Chat
Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.8 to 25.5 on the Noometry Index.
Last verified . 9 shared benchmarks.
Meta
NVIDIASummary
- They share 9 benchmarks with published results for both. Llama 3-8B scores higher in 5 categories and Llama2 70b Steerlm Chat in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Llama2 70b Steerlm Chat leads 31.3 to 8.8.
Side by side
| Llama 3-8B | Llama2 70b Steerlm Chat | |
|---|---|---|
| Provider | Meta | NVIDIA |
| Noometry Index | 25.5 | 31.8 |
| Released | 2024-04-18 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 34 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3-8B leads
Llama 3-8B: 31.0 (#289), Llama2 70b Steerlm Chat: 29.9 (#300)
| Benchmark | Llama 3-8B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Coding | 1152 | 1025 |
| BigCodeBench Instruct | 31.9% | — |
| BigCodeBench Complete | 36.9% | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 54.8% | — |
Reasoning Llama2 70b Steerlm Chat leads
Llama 3-8B: 14.3 (#326), Llama2 70b Steerlm Chat: 20.0 (#246)
| Benchmark | Llama 3-8B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Hard Prompts | 1133 | 1047 |
| Chess Puzzles | 0% | — |
| DTBench | 43.9% | — |
| Adversarial NLI | 57.3% | — |
| Epoch Capabilities Index | 116.45 | — |
| ForecastBench | 58.6 | — |
| WinoGrande | 75.7% | — |
Math Llama2 70b Steerlm Chat leads
Llama 3-8B: 8.8 (#323), Llama2 70b Steerlm Chat: 31.3 (#226)
| Benchmark | Llama 3-8B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Math | 1151 | 1072 |
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| MATH Level 5 | 6.1% | — |
Knowledge Not comparable
Llama 3-8B: 7.8 (#308), Llama2 70b Steerlm Chat: —
| Benchmark | Llama 3-8B | Llama2 70b Steerlm Chat |
|---|---|---|
| GPQA Diamond | 26.1% | — |
| LMArena Expert | 1113 | — |
| ARC (AI2) Challenge | 82.8% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |
Multilingual Llama 3-8B leads
Llama 3-8B: 30.8 (#261), Llama2 70b Steerlm Chat: 28.8 (#270)
| Benchmark | Llama 3-8B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Non-English | 1098 | 1063 |
| LMArena Chinese | 1076 | — |
| LMArena French | 1159 | — |
| LMArena German | 1104 | — |
| LMArena Japanese | 967 | — |
| LMArena Korean | 1004 | — |
| LMArena Russian | 1109 | — |
| LMArena Spanish | 1173 | — |
Instruction Following Llama 3-8B leads
Llama 3-8B: 58.4 (#260), Llama2 70b Steerlm Chat: 54.2 (#279)
| Benchmark | Llama 3-8B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Instruction Following | 1127 | 1060 |
Long Context Llama 3-8B leads
Llama 3-8B: 34.2 (#251), Llama2 70b Steerlm Chat: 30.4 (#288)
| Benchmark | Llama 3-8B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Longer Query | 1128 | 998 |
Writing & Preference Llama 3-8B leads
Llama 3-8B: 37.5 (#256), Llama2 70b Steerlm Chat: 31.6 (#283)
| Benchmark | Llama 3-8B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Text | 1166 | 1098 |
| LMArena Creative Writing | 1150 | 1091 |
| LMArena Multi-Turn | 1152 | 1058 |
Frequently asked questions
Is Llama 3-8B better than Llama2 70b Steerlm Chat?
Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.8 to 25.5 on the Noometry Index.
Is Llama 3-8B or Llama2 70b Steerlm Chat better for coding?
Llama 3-8B scores higher on coding benchmarks: 31.0 versus 29.9 in the Noometry coding category.
How many benchmarks do Llama 3-8B and Llama2 70b Steerlm Chat share?
9 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and Llama2 70b Steerlm Chat has 9.