The AI arena is free today

Open Superagent

LFM3-1.7B vs SWE-2

SWE-2 leads the LLM Stats Score 47.9 to 25.0.

Liquid AI · Cognition · Updated for 2026

Which is better?

SWE-2 leads the overall LLM Stats Score 47.9 to 25.0, ranking #34 overall.

In the 1 individual benchmarks reported for both models, SWE-2 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 LFM3-1.7B

  • you want the most recent training data — it shipped Oct 2026
  • you need open weights you can self-host or fine-tune

Choose SWE-2

  • overall performance matters — it scores 47.9 and ranks #34 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 1 of 1 exact shared results

At a glance

The differences that matter most.

LFM3-1.7B
Liquid AI
SWE-2
Cognition
Core performance indexes
LLM Stats Score
25.0
#191
47.9
#34
Reasoning
20.8
#216
45.5
#37
Coding
7.4
#218
38.7
#26
Agents
18.1
#97
35.6
#27
Cost, coverage & limits
Benchmark wins
0 of 1
1 of 1
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
SWE-2
Tool use
14.3#119
26.2#38
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

20 reported for LFM3-1.7B · 4 for SWE-2

1 shared

LFM3-1.7B outperforms in 0 benchmarks, while SWE-2 is better at 1 benchmark (Terminal-Bench 2.1).

SWE-2 significantly outperforms across most benchmarks.

Fri Nov 06 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

License

Usage and distribution terms

LFM3-1.7B is licensed under LFM Open License v1.0, while SWE-2 uses a proprietary license.

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

SWE-2

Proprietary

Closed source

Release Timeline

When each model was launched

LFM3-1.7B was released on 2026-10-27, while SWE-2 was released on 2026-09-10.

LFM3-1.7B is 2 months newer than SWE-2.

LFM3-1.7B

Oct 27, 2026

1 weeks ago

1mo newer
SWE-2

Sep 10, 2026

1 months ago

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 LFM3-1.7B and SWE-2 side-by-side, then vote on the output you prefer.

LFM3-1.7B
✓ Preferred
SWE-2
Open in Playground

FAQ

Common questions about LFM3-1.7B vs SWE-2.

Which is better, LFM3-1.7B or SWE-2?

SWE-2 leads the LLM Stats Score 47.9 to 25.0. LFM3-1.7B is made by Liquid AI and SWE-2 is made by Cognition. 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 SWE-2 in benchmarks?

LFM3-1.7B scores IFEval: 96.7%, Multi-IF: 89.1%, LiveCodeBench v6: 73.5%, IFBench: 73.0%, BFCL-V4: 71.4%. SWE-2 scores Terminal-Bench 2.1: 92.8%, DeepSWE 1.1: 73.0%, FrontierCode 1.1: 50.0%, Terminal-Bench 4.0: 27.3%.

What are the main differences between LFM3-1.7B and SWE-2?

Key differences include LLM Stats Score (25.0 vs 47.9), licensing (LFM Open License v1.0 vs Proprietary). See the full comparison above for benchmark-by-benchmark results.

Who makes LFM3-1.7B and SWE-2?

LFM3-1.7B is developed by Liquid AI and SWE-2 is developed by Cognition.

Related comparisons