Model comparison
Llama 3.1-70B vs Phi 3 Mini 4k Instruct
Llama 3.1-70B is the stronger model overall, scoring 29.6 to 27.9 on the Noometry Index.
Last verified . 18 shared benchmarks.
Meta
MicrosoftSummary
- They share 18 benchmarks with published results for both. Llama 3.1-70B 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 instruction following, where Llama 3.1-70B leads 65.3 to 47.7.
Side by side
| Llama 3.1-70B | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 29.6 | 27.9 |
| Released | 2024-07-23 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.40 | — |
| Output $ / M tokens | $0.40 | — |
| Results tracked | 35 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3.1-70B leads
Llama 3.1-70B: 30.3 (#296), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | Llama 3.1-70B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1260 | 1093 |
| WeirdML | 9% | — |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | — | 15.5% |
| BigCodeBench Complete | 54.8% | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Agentic & Tool Use Not comparable
Llama 3.1-70B: 25.1 (#112), Phi 3 Mini 4k Instruct: —
| Benchmark | Llama 3.1-70B | Phi 3 Mini 4k Instruct |
|---|---|---|
| TheAgentCompany | 6.9% | — |
| BALROG | 27.9% | — |
Reasoning Llama 3.1-70B leads
Llama 3.1-70B: 21.6 (#220), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | Llama 3.1-70B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1072 |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 26.8% |
| DTBench | 60% | — |
| LiveBench Data Analysis | — | 34.7% |
| LMCA | 14.8% | — |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 125.92 | — |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |
Math Phi 3 Mini 4k Instruct leads
Llama 3.1-70B: 13.5 (#304), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | Llama 3.1-70B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1252 | 1111 |
| OTIS Mock AIME 2024-2025 | 3.6% | — |
| Omni-MATH | 21% | — |
| LiveBench Math | — | 15.7% |
| MATH Level 5 | 36.7% | — |
Knowledge Phi 3 Mini 4k Instruct leads
Llama 3.1-70B: 24.2 (#269), Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | Llama 3.1-70B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1209 | 1045 |
| MMLU | 80.1% | 68.8% |
| GPQA Diamond | 44.2% | — |
| MMLU-Pro | 65.3% | — |
| GPQA (HELM) | 42.6% | — |
| ARC (AI2) Challenge | — | 84.9% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multilingual Llama 3.1-70B leads
Llama 3.1-70B: 38.8 (#225), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | Llama 3.1-70B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1219 | 1021 |
| LMArena Chinese | 1215 | 1021 |
| LMArena French | 1261 | 1076 |
| LMArena German | 1222 | 1044 |
| LMArena Japanese | 1132 | 935 |
| LMArena Korean | 1140 | 905 |
| LMArena Russian | 1234 | 1022 |
| LMArena Spanish | 1253 | 1085 |
Instruction Following Llama 3.1-70B leads
Llama 3.1-70B: 65.3 (#223), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | Llama 3.1-70B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1231 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
| IFEval | 82.1% | — |
Long Context Llama 3.1-70B leads
Llama 3.1-70B: 37.6 (#214), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | Llama 3.1-70B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1241 | 1044 |
Writing & Preference Llama 3.1-70B leads
Llama 3.1-70B: 35.4 (#267), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | Llama 3.1-70B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1261 | 1073 |
| LMArena Creative Writing | 1232 | 1037 |
| LMArena Multi-Turn | 1256 | 1018 |
| EQ-Bench Creative Writing | 784 | — |
| WildBench | 75.8% | — |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is Llama 3.1-70B better than Phi 3 Mini 4k Instruct?
Llama 3.1-70B is the stronger model overall, scoring 29.6 to 27.9 on the Noometry Index.
Is Llama 3.1-70B or Phi 3 Mini 4k Instruct better for coding?
Llama 3.1-70B scores higher on coding benchmarks: 30.3 versus 26.6 in the Noometry coding category.
How many benchmarks do Llama 3.1-70B and Phi 3 Mini 4k Instruct share?
18 benchmarks have published results for both models. Llama 3.1-70B has 35 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.