The AI arena is free today

Open Superagent

LFM3-1.7B vs Phi 4 Reasoning

LFM3-1.7B leads the LLM Stats Score 25.0 to 11.5.

Liquid AI · Microsoft · Updated for 2026

Which is better?

LFM3-1.7B leads the overall LLM Stats Score 25.0 to 11.5, ranking #192 overall.

The models split the 2 individual benchmarks reported for both models evenly.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose LFM3-1.7B

  • overall performance matters — it scores 25.0 and ranks #192 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you want the most recent training data — it shipped Oct 2026

Choose Phi 4 Reasoning

  • you are already invested in the Microsoft ecosystem

At a glance

The differences that matter most.

LFM3-1.7B
Liquid AI
Phi 4 Reasoning
Microsoft
Core performance indexes
LLM Stats Score
25.0
#192
11.5
#295
Reasoning
20.8
#216
12.1
#282
Coding
7.4
#218
6.3
#223
Cost, coverage & limits
Benchmark wins
1 of 2
1 of 2
Input price
— / M
— / M
Output price
— / M
— / M
Context window
—
—

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
LFM3-1.7B
Phi 4 Reasoning
Math
7.6#285
13.6#244
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

20 reported for LFM3-1.7B · 11 for Phi 4 Reasoning

2 shared

LFM3-1.7B outperforms in 1 benchmarks (IFEval), while Phi 4 Reasoning is better at 1 benchmark (GPQA).

Both models are evenly matched across the benchmarks.

Tue Nov 03 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

12.3B diff

Phi 4 Reasoning has 12.3B more parameters than LFM3-1.7B, making it 709.2% larger.

Liquid AI
LFM3-1.7B
1.7Bparameters
Microsoft
Phi 4 Reasoning
14.0Bparameters
1.7B
LFM3-1.7B
14.0B
Phi 4 Reasoning

License

Usage and distribution terms

LFM3-1.7B is licensed under LFM Open License v1.0, while Phi 4 Reasoning uses MIT.

License differences may affect how you can use these models in commercial or open-source projects.

LFM3-1.7B

LFM Open License v1.0

Open weights

Phi 4 Reasoning

MIT

Open weights

Release Timeline

When each model was launched

LFM3-1.7B was released on 2026-10-27, while Phi 4 Reasoning was released on 2025-04-30.

LFM3-1.7B is 18 months newer than Phi 4 Reasoning.

LFM3-1.7B

Oct 27, 2026

5 days ago

1.5yr newer
Phi 4 Reasoning

Apr 30, 2025

1.5 years ago

Knowledge Cutoff

When training data ends

Phi 4 Reasoning has a documented knowledge cutoff of 2025-03-01, while LFM3-1.7B's cutoff date is not specified.

We can confirm Phi 4 Reasoning's training data extends to 2025-03-01, but cannot make a direct comparison without LFM3-1.7B's cutoff date.

LFM3-1.7B

—

Phi 4 Reasoning

Mar 2025

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against LFM3-1.7B and Phi 4 Reasoning side-by-side, then vote on the output you prefer.

LFM3-1.7B
✓ Preferred
Phi 4 Reasoning
Open in Playground

FAQ

Common questions about LFM3-1.7B vs Phi 4 Reasoning.

Which is better, LFM3-1.7B or Phi 4 Reasoning?

LFM3-1.7B leads the LLM Stats Score 25.0 to 11.5. LFM3-1.7B is made by Liquid AI and Phi 4 Reasoning is made by Microsoft. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does LFM3-1.7B compare to Phi 4 Reasoning in benchmarks?

LFM3-1.7B scores IFEval: 96.7%, Multi-IF: 89.1%, LiveCodeBench v6: 73.5%, IFBench: 73.0%, BFCL-V4: 71.4%. Phi 4 Reasoning scores FlenQA: 97.7%, HumanEval+: 92.9%, IFEval: 83.4%, OmniMath: 76.6%, AIME 2024: 75.3%.

What are the main differences between LFM3-1.7B and Phi 4 Reasoning?

Key differences include LLM Stats Score (25.0 vs 11.5), licensing (LFM Open License v1.0 vs MIT). See the full comparison above for benchmark-by-benchmark results.

Who makes LFM3-1.7B and Phi 4 Reasoning?

LFM3-1.7B is developed by Liquid AI and Phi 4 Reasoning is developed by Microsoft.

Related comparisons