The AI arena is free today

Open Superagent

DeepSeek-V2.5 vs LFM3-1.7B

LFM3-1.7B leads the LLM Stats Score 25.0 to 7.6.

DeepSeek · Liquid AI · Updated for 2026

Which is better?

LFM3-1.7B leads the overall LLM Stats Score 25.0 to 7.6, ranking #192 overall.

In the 1 individual benchmarks reported for both models, LFM3-1.7B wins 1; this is a narrower head-to-head signal than the composite indexes.

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

Choose DeepSeek-V2.5

  • you want predictable pricing at $0.14/M input and $0.28/M output

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 value its reported benchmark strengths — it wins 1 of 1 exact shared results
  • you want the most recent training data — it shipped Oct 2026

At a glance

The differences that matter most.

DeepSeek-V2.5
DeepSeek
LFM3-1.7B
Liquid AI
Core performance indexes
LLM Stats Score
7.6
#321
25.0
#192
Reasoning
7.6
#317
20.8
#216
Coding
6.0
#225
7.4
#218
Cost, coverage & limits
Benchmark wins
0 of 1
1 of 1
Input price
$0.14 / M
— / M
Output price
$0.28 / M
— / M
Context window
8,192
—

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
DeepSeek-V2.5
LFM3-1.7B
Math
13.9#241
7.6#285
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

15 reported for DeepSeek-V2.5 · 20 for LFM3-1.7B

1 shared

DeepSeek-V2.5 outperforms in 0 benchmarks, while LFM3-1.7B is better at 1 benchmark (SWE-Bench Verified).

LFM3-1.7B significantly outperforms across most benchmarks.

Mon Nov 02 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

234.3B diff

DeepSeek-V2.5 has 234.3B more parameters than LFM3-1.7B, making it 13541.6% larger.

DeepSeek
DeepSeek-V2.5
236.0Bparameters
Liquid AI
LFM3-1.7B
1.7Bparameters
236.0B
DeepSeek-V2.5
1.7B
LFM3-1.7B

Context Window

Maximum input and output token capacity

Only DeepSeek-V2.5 specifies input context (8,192 tokens). Only DeepSeek-V2.5 specifies output context (8,192 tokens).

DeepSeek
DeepSeek-V2.5
Input8,192 tokens
Output8,192 tokens
Liquid AI
LFM3-1.7B
Input- tokens
Output- tokens
Mon Nov 02 2026 • llm-stats.com

License

Usage and distribution terms

DeepSeek-V2.5 is licensed under deepseek, while LFM3-1.7B uses LFM Open License v1.0.

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

DeepSeek-V2.5

deepseek

Open weights

LFM3-1.7B

LFM Open License v1.0

Open weights

Release Timeline

When each model was launched

DeepSeek-V2.5 was released on 2024-05-08, while LFM3-1.7B was released on 2026-10-27.

LFM3-1.7B is 30 months newer than DeepSeek-V2.5.

DeepSeek-V2.5

May 8, 2024

2.5 years ago

LFM3-1.7B

Oct 27, 2026

6 days ago

2.5yr newer

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against DeepSeek-V2.5 and LFM3-1.7B side-by-side, then vote on the output you prefer.

DeepSeek-V2.5
✓ Preferred
LFM3-1.7B
Open in Playground

FAQ

Common questions about DeepSeek-V2.5 vs LFM3-1.7B.

Which is better, DeepSeek-V2.5 or LFM3-1.7B?

LFM3-1.7B leads the LLM Stats Score 25.0 to 7.6. DeepSeek-V2.5 is made by DeepSeek and LFM3-1.7B is made by Liquid AI. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does DeepSeek-V2.5 compare to LFM3-1.7B in benchmarks?

DeepSeek-V2.5 scores GSM8k: 95.1%, MT-Bench: 90.2%, HumanEval: 89.0%, BBH: 84.3%, AlignBench: 80.4%. LFM3-1.7B scores IFEval: 96.7%, Multi-IF: 89.1%, LiveCodeBench v6: 73.5%, IFBench: 73.0%, BFCL-V4: 71.4%.

What are the context window sizes for DeepSeek-V2.5 and LFM3-1.7B?

DeepSeek-V2.5 supports 8K tokens and LFM3-1.7B supports an unknown number of tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between DeepSeek-V2.5 and LFM3-1.7B?

Key differences include LLM Stats Score (7.6 vs 25.0), licensing (deepseek vs LFM Open License v1.0). See the full comparison above for benchmark-by-benchmark results.

Who makes DeepSeek-V2.5 and LFM3-1.7B?

DeepSeek-V2.5 is developed by DeepSeek and LFM3-1.7B is developed by Liquid AI.

Related comparisons