Model comparison
Llama 3-70B vs Phi 3 Mini 4k Instruct
Llama 3-70B and Phi 3 Mini 4k Instruct score almost the same on the Noometry Index (28.8 vs 27.9), so choose on price, context window or the category you care about most.
Last verified . 21 shared benchmarks.
Meta
MicrosoftSummary
- They share 21 benchmarks with published results for both. Llama 3-70B scores higher in 6 categories and Phi 3 Mini 4k Instruct 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 27.6.
Side by side
| Llama 3-70B | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 28.8 | 27.9 |
| Released | 2024-04-18 | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 31 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3-70B leads
Llama 3-70B: 35.8 (#218), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | Llama 3-70B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1206 | 1093 |
| HumanEval+ | 72% | 59.1% |
| MBPP+ | 69% | 54.2% |
| BigCodeBench Instruct | 43.6% | — |
| LiveBench Coding | — | 15.5% |
| BigCodeBench Complete | 54.5% | — |
Agentic & Tool Use Not comparable
Llama 3-70B: 21.1 (#139), Phi 3 Mini 4k Instruct: —
| Benchmark | Llama 3-70B | Phi 3 Mini 4k Instruct |
|---|---|---|
| Cybench | 5% | — |
Reasoning Llama 3-70B leads
Llama 3-70B: 18.0 (#288), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | Llama 3-70B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1195 | 1072 |
| WinoGrande | 83.5% | 70.8% |
| Kagi LLM Benchmark | 35.1% | — |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 26.8% |
| DTBench | 54.2% | — |
| LiveBench Data Analysis | — | 34.7% |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 122.93 | — |
| ForecastBench | 57.1 | — |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
Math Phi 3 Mini 4k Instruct leads
Llama 3-70B: 12.8 (#305), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | Llama 3-70B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1218 | 1111 |
| OTIS Mock AIME 2024-2025 | 4.3% | — |
| LiveBench Math | — | 15.7% |
| MATH Level 5 | 22.6% | — |
Knowledge Phi 3 Mini 4k Instruct leads
Llama 3-70B: 20.8 (#277), Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | Llama 3-70B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1149 | 1045 |
| MMLU | 79.3% | 68.8% |
| GPQA Diamond | 40.6% | — |
| ARC (AI2) Challenge | — | 84.9% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multilingual Llama 3-70B leads
Llama 3-70B: 33.6 (#251), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | Llama 3-70B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1142 | 1021 |
| LMArena Chinese | 1114 | 1021 |
| LMArena French | 1232 | 1076 |
| LMArena German | 1169 | 1044 |
| LMArena Japanese | 1017 | 935 |
| LMArena Korean | 1017 | 905 |
| LMArena Russian | 1159 | 1022 |
| LMArena Spanish | 1241 | 1085 |
Instruction Following Llama 3-70B leads
Llama 3-70B: 62.5 (#238), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | Llama 3-70B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1194 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
Long Context Llama 3-70B leads
Llama 3-70B: 35.6 (#240), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | Llama 3-70B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1174 | 1044 |
Writing & Preference Llama 3-70B leads
Llama 3-70B: 42.8 (#231), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | Llama 3-70B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1221 | 1073 |
| LMArena Creative Writing | 1210 | 1037 |
| LMArena Multi-Turn | 1223 | 1018 |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is Llama 3-70B better than Phi 3 Mini 4k Instruct?
Llama 3-70B and Phi 3 Mini 4k Instruct score almost the same on the Noometry Index (28.8 vs 27.9), so choose on price, context window or the category you care about most.
Is Llama 3-70B or Phi 3 Mini 4k Instruct better for coding?
Llama 3-70B scores higher on coding benchmarks: 35.8 versus 26.6 in the Noometry coding category.
How many benchmarks do Llama 3-70B and Phi 3 Mini 4k Instruct share?
21 benchmarks have published results for both models. Llama 3-70B has 31 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.