Model comparison
Llama 4 Maverick vs Phi 3 Mini 128k Instruct
Llama 4 Maverick is the stronger model overall, scoring 30.9 to 29.7 on the Noometry Index.
Last verified . 19 shared benchmarks.
Meta
MicrosoftSummary
- They share 19 benchmarks with published results for both. Llama 4 Maverick scores higher in 5 categories and Phi 3 Mini 128k Instruct in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Llama 4 Maverick leads 71.7 to 51.8.
- The biggest single-benchmark swing is BigCodeBench Complete: 61.4% for Llama 4 Maverick and 40.6% for Phi 3 Mini 128k Instruct.
Side by side
| Llama 4 Maverick | Phi 3 Mini 128k Instruct | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 30.9 | 29.7 |
| 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 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Phi 3 Mini 128k Instruct leads
Llama 4 Maverick: 26.6 (#324), Phi 3 Mini 128k Instruct: 28.8 (#312)
| Benchmark | Llama 4 Maverick | Phi 3 Mini 128k Instruct |
|---|---|---|
| BigCodeBench Instruct | 49.7% | 29.6% |
| LMArena Coding | 1302 | 1039 |
| BigCodeBench Complete | 61.4% | 40.6% |
| SWE-bench Verified (bash only) | 21% | — |
| Aider Polyglot | 15.6% | — |
| SciCode | 33.1% | — |
| WeirdML | 24.5% | — |
| ALE-Bench | 172.97 | — |
Agentic & Tool Use Not comparable
Llama 4 Maverick: 28.2 (#91), Phi 3 Mini 128k Instruct: —
| Benchmark | Llama 4 Maverick | Phi 3 Mini 128k Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.3% | — |
Reasoning Phi 3 Mini 128k Instruct leads
Llama 4 Maverick: 10.1 (#342), Phi 3 Mini 128k Instruct: 19.6 (#256)
| Benchmark | Llama 4 Maverick | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1281 | 1028 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 27.7% | — |
| Kagi LLM Benchmark | 55.9% | — |
| NYT Connections (extended) | 8% | — |
| ARC-AGI-1 | 4.4% | — |
| CritPt | 0% | — |
| EnigmaEval | 0.6% | — |
| DTBench | 61.9% | — |
| LMCA | 15.9% | — |
| Epoch Capabilities Index | 132.2 | — |
| ForecastBench | 57.5 | — |
Math Phi 3 Mini 128k Instruct leads
Llama 4 Maverick: 26.0 (#262), Phi 3 Mini 128k Instruct: 31.6 (#222)
| Benchmark | Llama 4 Maverick | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Math | 1299 | 1089 |
| OTIS Mock AIME 2024-2025 | 20.6% | — |
| Omni-MATH | 42.2% | — |
| MATH Level 5 | 73% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |
Knowledge Llama 4 Maverick leads
Llama 4 Maverick: 33.4 (#204), Phi 3 Mini 128k Instruct: 26.8 (#254)
| Benchmark | Llama 4 Maverick | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Expert | 1259 | 984 |
| GPQA Diamond | 67% | — |
| Humanity's Last Exam | 5.7% | — |
| MMLU-Pro | 81% | — |
| Confabulations | 22.6% | — |
| Vectara Hallucination Rate | 8.2% | — |
| GPQA (HELM) | 65% | — |
Multimodal Not comparable
Llama 4 Maverick: 31.6 (#105), Phi 3 Mini 128k Instruct: —
| Benchmark | Llama 4 Maverick | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Vision | 1142 | — |
| GeoBench | 52% | — |
| SpatialViz-Bench | 31.8% | — |
Multilingual Llama 4 Maverick leads
Llama 4 Maverick: 42.2 (#195), Phi 3 Mini 128k Instruct: 25.2 (#285)
| Benchmark | Llama 4 Maverick | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Non-English | 1269 | 1000 |
| LMArena Chinese | 1277 | 1016 |
| LMArena French | 1259 | 1039 |
| LMArena German | 1291 | 1006 |
| LMArena Japanese | 1207 | 899 |
| LMArena Korean | 1203 | 856 |
| LMArena Russian | 1286 | 1004 |
| LMArena Spanish | 1293 | 1059 |
Instruction Following Llama 4 Maverick leads
Llama 4 Maverick: 71.7 (#146), Phi 3 Mini 128k Instruct: 51.8 (#294)
| Benchmark | Llama 4 Maverick | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Instruction Following | 1267 | 1023 |
| IFEval | 90.8% | — |
Long Context Llama 4 Maverick leads
Llama 4 Maverick: 31.4 (#279), Phi 3 Mini 128k Instruct: 30.4 (#289)
| Benchmark | Llama 4 Maverick | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Longer Query | 1280 | 996 |
| Fiction.LiveBench | 46.2% | — |
Writing & Preference Llama 4 Maverick leads
Llama 4 Maverick: 38.8 (#252), Phi 3 Mini 128k Instruct: 27.1 (#301)
| Benchmark | Llama 4 Maverick | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Text | 1287 | 1050 |
| LMArena Creative Writing | 1267 | 1024 |
| LMArena Multi-Turn | 1289 | 989 |
| Short-Story Creative Writing | 62% | — |
| EQ-Bench Creative Writing | 860 | — |
| WildBench | 80% | — |
Frequently asked questions
Is Llama 4 Maverick better than Phi 3 Mini 128k Instruct?
Llama 4 Maverick is the stronger model overall, scoring 30.9 to 29.7 on the Noometry Index.
Is Llama 4 Maverick or Phi 3 Mini 128k Instruct better for coding?
Phi 3 Mini 128k Instruct scores higher on coding benchmarks: 28.8 versus 26.6 in the Noometry coding category.
How many benchmarks do Llama 4 Maverick and Phi 3 Mini 128k Instruct share?
19 benchmarks have published results for both models. Llama 4 Maverick has 54 scored results on Noometry and Phi 3 Mini 128k Instruct has 19.