The AI arena is free today

Open Superagent

Claude 3.7 Sonnet vs LFM2.5-2.6B

Claude 3.7 Sonnet and LFM2.5-2.6B are closely matched at 23.9 and 19.0 on the LLM Stats Score.

Anthropic · Liquid AI · Updated for 2026

Which is better?

Claude 3.7 Sonnet and LFM2.5-2.6B are closely matched on the overall LLM Stats Score at 23.9 and 19.0.

In the 1 individual benchmarks reported for both models, Claude 3.7 Sonnet 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 Claude 3.7 Sonnet

  • you value its reported benchmark strengths — it wins 1 of 1 exact shared results

Choose LFM2.5-2.6B

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

At a glance

The differences that matter most.

Claude 3.7 Sonnet
Anthropic
LFM2.5-2.6B
Liquid AI
Core performance indexes
LLM Stats Score
23.9
#169
19.0
#208
Reasoning
23.1
#165
14.7
#229
Coding
13.6
#136
17.4
#121
Agents
4.9
#149
7.9
#135
Cost, coverage & limits
Benchmark wins
1 of 1
0 of 1
Input price
$3.00 / M
— / M
Output price
$15.00 / M
— / M
Context window
200,000
—

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
Claude 3.7 Sonnet
LFM2.5-2.6B
Tool use
17.9#70
2.0#170
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

11 reported for Claude 3.7 Sonnet · 9 for LFM2.5-2.6B

1 shared

Claude 3.7 Sonnet outperforms in 1 benchmarks (AIME 2025), while LFM2.5-2.6B is better at 0 benchmarks.

Claude 3.7 Sonnet significantly outperforms across most benchmarks.

Sun Sep 20 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Context Window

Maximum input and output token capacity

Only Claude 3.7 Sonnet specifies input context (200,000 tokens). Only Claude 3.7 Sonnet specifies output context (128,000 tokens).

Anthropic
Claude 3.7 Sonnet
Input200,000 tokens
Output128,000 tokens
Liquid AI
LFM2.5-2.6B
Input- tokens
Output- tokens
Sun Sep 20 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Claude 3.7 Sonnet supports multimodal inputs, whereas LFM2.5-2.6B does not.

Claude 3.7 Sonnet can handle both text and other forms of data like images, making it suitable for multimodal applications.

Claude 3.7 Sonnet

Text
Images
Audio
Video

LFM2.5-2.6B

Text
Images
Audio
Video

License

Usage and distribution terms

Claude 3.7 Sonnet is licensed under a proprietary license, while LFM2.5-2.6B uses LFM Open License v1.0.

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

Claude 3.7 Sonnet

Proprietary

Closed source

LFM2.5-2.6B

LFM Open License v1.0

Open weights

Release Timeline

When each model was launched

Claude 3.7 Sonnet was released on 2025-02-24, while LFM2.5-2.6B was released on 2026-08-04.

LFM2.5-2.6B is 18 months newer than Claude 3.7 Sonnet.

Claude 3.7 Sonnet

Feb 24, 2025

1.6 years ago

LFM2.5-2.6B

Aug 4, 2026

1 months ago

1.4yr 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?Start an Issue discussion→

Judge for yourself.

Run your own prompts against Claude 3.7 Sonnet and LFM2.5-2.6B side-by-side, then vote on the output you prefer.

Claude 3.7 Sonnet
✓ Preferred
LFM2.5-2.6B
Open in Playground

FAQ

Common questions about Claude 3.7 Sonnet vs LFM2.5-2.6B.

Which is better, Claude 3.7 Sonnet or LFM2.5-2.6B?

Claude 3.7 Sonnet and LFM2.5-2.6B are closely matched on the LLM Stats Score at 23.9 and 19.0. Claude 3.7 Sonnet is made by Anthropic and LFM2.5-2.6B 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 Claude 3.7 Sonnet compare to LFM2.5-2.6B in benchmarks?

Claude 3.7 Sonnet scores MATH-500: 96.2%, IFEval: 93.2%, MMMLU: 86.1%, GPQA: 84.8%, TAU-bench Retail: 81.2%. LFM2.5-2.6B scores Multi-IF: 80.1%, PinchBench: 68.2%, Claw-Eval: 62.8%, LiveCodeBench v6: 59.4%, IFBench: 59.2%.

What are the context window sizes for Claude 3.7 Sonnet and LFM2.5-2.6B?

Claude 3.7 Sonnet supports 200K tokens and LFM2.5-2.6B 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 Claude 3.7 Sonnet and LFM2.5-2.6B?

Key differences include LLM Stats Score (23.9 vs 19.0), multimodal support (yes vs no), licensing (Proprietary vs LFM Open License v1.0). See the full comparison above for benchmark-by-benchmark results.

Who makes Claude 3.7 Sonnet and LFM2.5-2.6B?

Claude 3.7 Sonnet is developed by Anthropic and LFM2.5-2.6B is developed by Liquid AI.

Related comparisons