Context
33K tokens (~16 books)
Input $/1M
Free
Output $/1M
Free
Type
text
License
Open Source
Benchmarks
3 tested
Data updated today
About
LFM2.5-1.2B-Thinking is a lightweight reasoning-focused model optimized for agentic tasks, data extraction, and RAG—while still running comfortably on edge devices. It supports long context (up to 32K tokens) and is...
Tested on 3 benchmarks with 0.0% average. Top scores: Artificial Analysis — Quality Index (8.1%), Artificial Analysis — Agentic Index (6.5%), Artificial Analysis — Coding Index (1.4%).
Capabilities
speed
8.9
#66 globally
Benchmark Scores
Compare AllTested on 3 benchmarks · Ranked across 1 categories
Score Distribution (all 233 models)
0255075100
speedCompare speed →
Artificial Analysis — Quality Index
8.1—Artificial Analysis Quality Index. Composite quality score combining multiple benchmark results into a single metric.
Artificial Analysis — Agentic Index
6.5—Artificial Analysis Agentic Index. Composite score measuring agent capability across tool use and planning tasks.
Artificial Analysis — Coding Index
1.4—Artificial Analysis Coding Index. Composite coding quality score from multiple code benchmarks.
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Research
Documentation
Community
Source Code
BenchGecko API
lfm-2-5-1-2b-thinking-free
Specifications
- Typetext
- Context33K tokens (~16 books)
- ReleasedJan 2026
- LicenseOpen Source
- StatusActive
- Cost / Message~$0.000
Available On
Categories
Learn More
Share & Export
Frequently Asked Questions
LFM2.5-1.2B-Thinking (free) is an open-source text AI model by liquid, released in January 2026. Context window: 33K tokens.