Model comparison
Llama 4 Maverick vs Phi 3 Mini 4k Instruct
Llama 4 Maverick is the stronger model overall, scoring 30.9 to 27.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Meta
MicrosoftSummary
- They share 17 benchmarks with published results for both. Llama 4 Maverick scores higher in 4 categories and Phi 3 Mini 4k Instruct in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Llama 4 Maverick leads 71.7 to 47.7.
Side by side
| Llama 4 Maverick | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 30.9 | 27.9 |
| Released | 2025-04-05 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.19 | — |
| Output $ / M tokens | $0.65 | — |
| Results tracked | 54 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Llama 4 Maverick: 26.6 (#324), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | Llama 4 Maverick | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1302 | 1093 |
| SWE-bench Verified (bash only) | 21% | — |
| Aider Polyglot | 15.6% | — |
| SciCode | 33.1% | — |
| WeirdML | 24.5% | — |
| BigCodeBench Instruct | 49.7% | — |
| LiveBench Coding | — | 15.5% |
| BigCodeBench Complete | 61.4% | — |
| ALE-Bench | 172.97 | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Agentic & Tool Use Not comparable
Llama 4 Maverick: 28.2 (#91), Phi 3 Mini 4k Instruct: —
| Benchmark | Llama 4 Maverick | Phi 3 Mini 4k Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.3% | — |
Reasoning Phi 3 Mini 4k Instruct leads
Llama 4 Maverick: 10.1 (#342), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | Llama 4 Maverick | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1281 | 1072 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 27.7% | — |
| Kagi LLM Benchmark | 55.9% | — |
| NYT Connections (extended) | 8% | — |
| ARC-AGI-1 | 4.4% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 0% |
| EnigmaEval | 0.6% | — |
| LiveBench Reasoning | — | 26.8% |
| DTBench | 61.9% | — |
| LiveBench Data Analysis | — | 34.7% |
| LMCA | 15.9% | — |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 132.2 | — |
| ForecastBench | 57.5 | — |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |
Math Too close to call
Llama 4 Maverick: 26.0 (#262), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | Llama 4 Maverick | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1299 | 1111 |
| OTIS Mock AIME 2024-2025 | 20.6% | — |
| Omni-MATH | 42.2% | — |
| LiveBench Math | — | 15.7% |
| MATH Level 5 | 73% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |
Knowledge Llama 4 Maverick leads
Llama 4 Maverick: 33.4 (#204), Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | Llama 4 Maverick | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1259 | 1045 |
| GPQA Diamond | 67% | — |
| Humanity's Last Exam | 5.7% | — |
| MMLU-Pro | 81% | — |
| Confabulations | 22.6% | — |
| Vectara Hallucination Rate | 8.2% | — |
| GPQA (HELM) | 65% | — |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multimodal Not comparable
Llama 4 Maverick: 31.6 (#105), Phi 3 Mini 4k Instruct: —
| Benchmark | Llama 4 Maverick | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Vision | 1142 | — |
| GeoBench | 52% | — |
| SpatialViz-Bench | 31.8% | — |
Multilingual Llama 4 Maverick leads
Llama 4 Maverick: 42.2 (#195), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | Llama 4 Maverick | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1269 | 1021 |
| LMArena Chinese | 1277 | 1021 |
| LMArena French | 1259 | 1076 |
| LMArena German | 1291 | 1044 |
| LMArena Japanese | 1207 | 935 |
| LMArena Korean | 1203 | 905 |
| LMArena Russian | 1286 | 1022 |
| LMArena Spanish | 1293 | 1085 |
Instruction Following Llama 4 Maverick leads
Llama 4 Maverick: 71.7 (#146), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | Llama 4 Maverick | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1267 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
| IFEval | 90.8% | — |
Long Context Too close to call
Llama 4 Maverick: 31.4 (#279), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | Llama 4 Maverick | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1280 | 1044 |
| Fiction.LiveBench | 46.2% | — |
Writing & Preference Llama 4 Maverick leads
Llama 4 Maverick: 38.8 (#252), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | Llama 4 Maverick | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1287 | 1073 |
| LMArena Creative Writing | 1267 | 1037 |
| LMArena Multi-Turn | 1289 | 1018 |
| Short-Story Creative Writing | 62% | — |
| EQ-Bench Creative Writing | 860 | — |
| WildBench | 80% | — |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is Llama 4 Maverick better than Phi 3 Mini 4k Instruct?
Llama 4 Maverick is the stronger model overall, scoring 30.9 to 27.9 on the Noometry Index.
Is Llama 4 Maverick or Phi 3 Mini 4k Instruct better for coding?
They score almost the same on coding (26.6 vs 26.6); test both on your own repository before choosing.
How many benchmarks do Llama 4 Maverick and Phi 3 Mini 4k Instruct share?
17 benchmarks have published results for both models. Llama 4 Maverick has 54 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.