Skip to main content

Compare Leaderboards Agents Insights

Loading...

Compare LLM models by quality, speed, and price. Find the right model for your use case.

Product

Explore Models
Compare
Leaderboards
LLM Selector
Cost Calculator
Provider Finder

Resources

Insights
FAQ
About
Methodology

Data Sources

Data from Artificial Analysis, OpenRouter, HuggingFace, and other public sources.

© 2026 FindLLM. All rights reserved.

Phi-4 Multimodal Instruct — Microsoft | FindLLM

Home
Explore
Phi-4 Multimodal Instruct

Back to Explore

Phi-4 Multimodal Instruct

Microsoft·Released 2025-02-26

Open Source

Related Models

Microsoft: Phi 4 Mini Instruct2025-10-17 Phi tiny MoE instruct2025-06-23 Microsoft: Phi 42025-01-10 Phi 3.5 vision instruct2024-08-16 Phi 3.5 mini instruct2024-08-16 Phi-3 Mini Instruct 3.8B2024-04-23 Phi 3 mini 4k instruct2024-04-22 phi 22023-12-13

Performance

16

tokens/sec

Faster than 0% of models

1.22

seconds

Faster than 41% of models

1.22

seconds

Faster than 60% of models

Market Median

86 tok/s

81% slower

Median TTFT

1.07s

14% slower

Speed Comparison

MoonshotAI: Kimi K2 0905

17 tok/s+6%

Nova Premier

18 tok/s+6%

OpenAI: o3 Pro

21 tok/s+28%

Benchmarks

MMLU-Pro

48.5%

GPQA Diamond

31.5%

HLE

4.4%

LiveCodeBench

13.1%

SciCode

11.0%

TerminalBench HardNot evaluated

MATH-500

69.3%

AIME

9.3%

AIME 2025Not evaluated

IFBenchNot evaluated

Long Context RecallNot evaluated

Tau2Not evaluated

Market AverageTop Score

Open Source

Quick Compare

Similar Models

Qwen2.5 Coder 7B Instruct

Alibaba

Q: 10.0$0.04/1M33K ctx

Mistral Large

Mistral

Q: 9.9$3.00/1M128K ctx

NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)

NVIDIA

Q: 10.1$0.30/1M

Qwen3.5 0.8B (Non-reasoning)

Alibaba

Gemini 1.0 Ultra

Google

Gemma 3n E4B Instruct Preview (May '25)

Google

Compare all 7 models

Quality Index

10.0

428th of 507

Top 85%

Speed

16 tok/s

TTFT

1.22s