Model comparison
Llama 3-70B vs Phi-2
Llama 3-70B has enough public results to be ranked (#323); Phi-2 does not yet, so treat this comparison as directional.
Last verified . 5 shared benchmarks.
Meta
MicrosoftSummary
- They share 5 benchmarks with published results for both.
Side by side
| Llama 3-70B | Phi-2 | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 28.8 | — |
| Released | 2024-04-18 | 2023-12-12 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 31 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3-70B: 35.8 (#218), Phi-2: —
| Benchmark | Llama 3-70B | Phi-2 |
|---|---|---|
| HumanEval+ | 72% | 45.1% |
| MBPP+ | 69% | 54.2% |
| BigCodeBench Instruct | 43.6% | — |
| LMArena Coding | 1206 | — |
| BigCodeBench Complete | 54.5% | — |
Agentic & Tool Use Not comparable
Llama 3-70B: 21.1 (#139), Phi-2: —
| Benchmark | Llama 3-70B | Phi-2 |
|---|---|---|
| Cybench | 5% | — |
Reasoning Not comparable
Llama 3-70B: 18.0 (#288), Phi-2: —
| Benchmark | Llama 3-70B | Phi-2 |
|---|---|---|
| Epoch Capabilities Index | 122.93 | 107.94 |
| WinoGrande | 83.5% | 54.7% |
| Kagi LLM Benchmark | 35.1% | — |
| LMArena Hard Prompts | 1195 | — |
| DTBench | 54.2% | — |
| Adversarial NLI | — | 42.5% |
| BIG-Bench Hard | — | 59.4% |
| ForecastBench | 57.1 | — |
| HellaSwag | — | 53.6% |
Math Not comparable
Llama 3-70B: 12.8 (#305), Phi-2: —
| Benchmark | Llama 3-70B | Phi-2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | — |
| LMArena Math | 1218 | — |
| MATH Level 5 | 22.6% | — |
Knowledge Not comparable
Llama 3-70B: 20.8 (#277), Phi-2: —
| Benchmark | Llama 3-70B | Phi-2 |
|---|---|---|
| MMLU | 79.3% | 58.4% |
| GPQA Diamond | 40.6% | — |
| LMArena Expert | 1149 | — |
| ARC (AI2) Challenge | — | 75.9% |
| OpenBookQA | — | 73.6% |
| TriviaQA | — | 45.2% |
Multilingual Not comparable
Llama 3-70B: 33.6 (#251), Phi-2: —
| Benchmark | Llama 3-70B | Phi-2 |
|---|---|---|
| LMArena Non-English | 1142 | — |
| LMArena Chinese | 1114 | — |
| LMArena French | 1232 | — |
| LMArena German | 1169 | — |
| LMArena Japanese | 1017 | — |
| LMArena Korean | 1017 | — |
| LMArena Russian | 1159 | — |
| LMArena Spanish | 1241 | — |
Instruction Following Not comparable
Llama 3-70B: 62.5 (#238), Phi-2: —
| Benchmark | Llama 3-70B | Phi-2 |
|---|---|---|
| LMArena Instruction Following | 1194 | — |
Long Context Not comparable
Llama 3-70B: 35.6 (#240), Phi-2: —
| Benchmark | Llama 3-70B | Phi-2 |
|---|---|---|
| LMArena Longer Query | 1174 | — |
Writing & Preference Not comparable
Llama 3-70B: 42.8 (#231), Phi-2: —
| Benchmark | Llama 3-70B | Phi-2 |
|---|---|---|
| LMArena Text | 1221 | — |
| LMArena Creative Writing | 1210 | — |
| LMArena Multi-Turn | 1223 | — |
Frequently asked questions
Is Llama 3-70B better than Phi-2?
Llama 3-70B has enough public results to be ranked (#323); Phi-2 does not yet, so treat this comparison as directional.
How many benchmarks do Llama 3-70B and Phi-2 share?
5 benchmarks have published results for both models. Llama 3-70B has 31 scored results on Noometry and Phi-2 has 11.