Model comparison
Llama-3.3-70B-Instruct vs Phi 3 Mini 4k Instruct
Llama-3.3-70B-Instruct is the stronger model overall, scoring 30.6 to 27.9 on the Noometry Index.
Last verified . 25 shared benchmarks.
Meta
MicrosoftSummary
- They share 25 benchmarks with published results for both. Llama-3.3-70B-Instruct scores higher in 6 categories and Phi 3 Mini 4k Instruct in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Llama-3.3-70B-Instruct leads 71.1 to 47.7.
- The biggest single-benchmark swing is LiveBench Instruction Following: 82.7% for Llama-3.3-70B-Instruct and 39.1% for Phi 3 Mini 4k Instruct.
Side by side
| Llama-3.3-70B-Instruct | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 30.6 | 27.9 |
| Released | 2024-12-06 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.32 | — |
| Results tracked | 43 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 31.0 (#290), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | Llama-3.3-70B-Instruct | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Coding | 36.6% | 15.5% |
| LMArena Coding | 1268 | 1093 |
| SciCode | 26% | — |
| WeirdML | 14.4% | — |
| BigCodeBench Instruct | 46.9% | — |
| BigCodeBench Complete | 57.5% | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Agentic & Tool Use Not comparable
Llama-3.3-70B-Instruct: 25.8 (#105), Phi 3 Mini 4k Instruct: —
| Benchmark | Llama-3.3-70B-Instruct | Phi 3 Mini 4k Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 31.9% | — |
| BALROG | 23% | — |
Reasoning Too close to call
Llama-3.3-70B-Instruct: 14.1 (#327), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | Llama-3.3-70B-Instruct | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Reasoning | 50.8% | 26.8% |
| LMArena Hard Prompts | 1257 | 1072 |
| LiveBench Data Analysis | 49.5% | 34.7% |
| LiveBench | 50.2% | 22.4% |
| SimpleBench | 19.9% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 0% |
| DTBench | 59.5% | — |
| LMCA | 17.5% | — |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 127.33 | — |
| ForecastBench | 58.6 | — |
| HellaSwag | — | 76.7% |
| WinoGrande | — | 70.8% |
Math Phi 3 Mini 4k Instruct leads
Llama-3.3-70B-Instruct: 15.3 (#298), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | Llama-3.3-70B-Instruct | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Math | 42.2% | 15.7% |
| LMArena Math | 1267 | 1111 |
| OTIS Mock AIME 2024-2025 | 5.1% | — |
| MATH Level 5 | 41.6% | — |
Knowledge Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 30.6 (#226), Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | Llama-3.3-70B-Instruct | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1225 | 1045 |
| MMLU | 86.3% | 68.8% |
| GPQA Diamond | 47.4% | — |
| Confabulations | 22.8% | — |
| Vectara Hallucination Rate | 4.1% | — |
| ARC (AI2) Challenge | — | 84.9% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multilingual Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 39.9 (#220), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | Llama-3.3-70B-Instruct | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1236 | 1021 |
| LMArena Chinese | 1217 | 1021 |
| LMArena French | 1281 | 1076 |
| LMArena German | 1251 | 1044 |
| LMArena Japanese | 1150 | 935 |
| LMArena Korean | 1143 | 905 |
| LMArena Russian | 1252 | 1022 |
| LMArena Spanish | 1270 | 1085 |
Instruction Following Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 71.1 (#157), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | Llama-3.3-70B-Instruct | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Instruction Following | 82.7% | 39.1% |
| LMArena Instruction Following | 1242 | 1053 |
Long Context Phi 3 Mini 4k Instruct leads
Llama-3.3-70B-Instruct: 26.4 (#295), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | Llama-3.3-70B-Instruct | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1256 | 1044 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 47.6 (#207), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | Llama-3.3-70B-Instruct | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1274 | 1073 |
| LMArena Creative Writing | 1250 | 1037 |
| LMArena Multi-Turn | 1280 | 1018 |
| LiveBench Language | 39.2% | 9.2% |
Frequently asked questions
Is Llama-3.3-70B-Instruct better than Phi 3 Mini 4k Instruct?
Llama-3.3-70B-Instruct is the stronger model overall, scoring 30.6 to 27.9 on the Noometry Index.
Is Llama-3.3-70B-Instruct or Phi 3 Mini 4k Instruct better for coding?
Llama-3.3-70B-Instruct scores higher on coding benchmarks: 31.0 versus 26.6 in the Noometry coding category.
How many benchmarks do Llama-3.3-70B-Instruct and Phi 3 Mini 4k Instruct share?
25 benchmarks have published results for both models. Llama-3.3-70B-Instruct has 43 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.