# Llama 4 Maverick vs Phi-3.5-MoE

> Llama 4 Maverick has enough public results to be ranked (#276); Phi-3.5-MoE does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/llama-4-maverick-vs-phi-3-5-moe
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Snapshot

| | Llama 4 Maverick | Phi-3.5-MoE |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 30.6 | — |
| Rank | 276 | — |
| Context | 128K | — |
| Input $/M | $0.19 | — |
| Output $/M | $0.65 | — |
| Weights | Open | Open |

## Coding

- Llama 4 Maverick: 26.3 (#318)
- Phi-3.5-MoE: —

| Benchmark | Llama 4 Maverick | Phi-3.5-MoE |
|---|---|---|
| SWE-bench Verified (bash only) | 21% | — |
| Aider Polyglot | 15.6% | — |
| SciCode | 33.1% | — |
| WeirdML | 24.5% | — |
| BigCodeBench Instruct | 49.7% | — |
| LMArena Coding | 1302 | — |
| BigCodeBench Complete | 61.4% | — |
| ALE-Bench | 172.97 | — |

## Agentic & Tool Use

- Llama 4 Maverick: 27.9 (#86)
- Phi-3.5-MoE: —

| Benchmark | Llama 4 Maverick | Phi-3.5-MoE |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.3% | — |

## Reasoning

- Llama 4 Maverick: 10.1 (#337)
- Phi-3.5-MoE: —

| Benchmark | Llama 4 Maverick | Phi-3.5-MoE |
|---|---|---|
| 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% | — |
| LMArena Hard Prompts | 1281 | — |
| DTBench | 61.9% | — |
| LMCA | 15.9% | — |
| Epoch Capabilities Index | 132.2 | — |
| ForecastBench | 57.5 | — |
| PIQA | — | 88.6% |

## Math

- Llama 4 Maverick: 24.6 (#256)
- Phi-3.5-MoE: —

| Benchmark | Llama 4 Maverick | Phi-3.5-MoE |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 20.6% | — |
| Omni-MATH | 42.2% | — |
| LMArena Math | 1299 | — |
| MATH Level 5 | 73% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |
| GSM8K | — | 88.7% |

## Knowledge

- Llama 4 Maverick: 33.3 (#196)
- Phi-3.5-MoE: —

| Benchmark | Llama 4 Maverick | Phi-3.5-MoE |
|---|---|---|
| GPQA Diamond | 67% | — |
| Humanity's Last Exam | 5.7% | — |
| MMLU-Pro | 81% | — |
| Confabulations | 22.6% | — |
| Vectara Hallucination Rate | 8.2% | — |
| GPQA (HELM) | 65% | — |
| LMArena Expert | 1259 | — |
| BoolQ | — | 84.6% |

## Multimodal

- Llama 4 Maverick: 30.9 (#100)
- Phi-3.5-MoE: —

| Benchmark | Llama 4 Maverick | Phi-3.5-MoE |
|---|---|---|
| LMArena Vision | 1141 | — |
| GeoBench | 52% | — |
| SpatialViz-Bench | 31.8% | — |

## Multilingual

- Llama 4 Maverick: 42.4 (#190)
- Phi-3.5-MoE: —

| Benchmark | Llama 4 Maverick | Phi-3.5-MoE |
|---|---|---|
| LMArena Non-English | 1269 | — |
| LMArena Chinese | 1277 | — |
| LMArena French | 1258 | — |
| LMArena German | 1291 | — |
| LMArena Japanese | 1207 | — |
| LMArena Korean | 1203 | — |
| LMArena Russian | 1286 | — |
| LMArena Spanish | 1293 | — |

## Instruction Following

- Llama 4 Maverick: 71.9 (#140)
- Phi-3.5-MoE: —

| Benchmark | Llama 4 Maverick | Phi-3.5-MoE |
|---|---|---|
| IFEval | 90.8% | — |
| LMArena Instruction Following | 1267 | — |

## Long Context

- Llama 4 Maverick: 31.4 (#274)
- Phi-3.5-MoE: —

| Benchmark | Llama 4 Maverick | Phi-3.5-MoE |
|---|---|---|
| Fiction.LiveBench | 46.2% | — |
| LMArena Longer Query | 1280 | — |

## Writing & Preference

- Llama 4 Maverick: 39.0 (#247)
- Phi-3.5-MoE: —

| Benchmark | Llama 4 Maverick | Phi-3.5-MoE |
|---|---|---|
| LMArena Text | 1287 | — |
| LMArena Creative Writing | 1266 | — |
| Short-Story Creative Writing | 62% | — |
| EQ-Bench Creative Writing | 860 | — |
| WildBench | 80% | — |
| LMArena Multi-Turn | 1289 | — |

## FAQ

### Is Llama 4 Maverick better than Phi-3.5-MoE?

Llama 4 Maverick has enough public results to be ranked (#276); Phi-3.5-MoE does not yet, so treat this comparison as directional.

### How many benchmarks do Llama 4 Maverick and Phi-3.5-MoE share?

0 benchmarks have published results for both models. Llama 4 Maverick has 54 scored results on Noometry and Phi-3.5-MoE has 3.