Liquid AI's compact 2.6B reasoning model for agent workflows, data extraction, RAG, and long-context processing. It supports tool calling and structured output, but Liquid advises against using it for agentic coding. Warning: prompts and responses may be logged and used for model training or service improvement; do not send sensitive data.
Added Aug 12, 2026
Model weightsContext Window
128.0K
Max Output
32.8K
Avg output tokens (7d)
1.9K tokens
Input Price (Auto)
$0.10/1M
Output Price (Auto)
$0.20/1M
Capabilities
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
8.4
Coding Index
7.7
Agentic work
GDPval-AA v2
Economically valuable tasks (Elo)
-22 Elo
Better than 9% of models compared
Document reasoning
AA-LCR v1.1
Long context reasoning with updated grading
5.7%
Better than 12% of models compared
Reasoning
HLE
Humanity's Last Exam
6.2%
Better than 37% of models compared
Coding
SciCode
Python programming for scientific computing
14.4%
Better than 0% of models compared
Legacy benchmarks
GPQA Diamond (legacy)
Graduate-level scientific reasoning
55.8%
Better than 30% of models compared
AA-LCR (unversioned / legacy)
Long context reasoning evaluation
5.7%
Better than 12% of models compared
Last updated Oct 2, 2026
Artificial AnalysisProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Related text models
Compare LFM2.5 2.6B with similar models from the same provider or model family.
LightOnOCR 2
lightonai/LightOnOCR-2-1BLightOnOCR 2 hosted by IONOS in Berlin, Germany. Zero data retention.
EVA-LLaMA-3.33-70B-v0.1
EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1A RP/storywriting specialist model, full-parameter finetune of Llama-3.3-70B-Instruct on mixture of synthetic and natural data. It uses Celeste 70B 0.1 data mixture, greatly expanding it to improve versatility, creativity and flavor of the resulting model.
EVA-Qwen2.5-72B-v0.2
EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2A RP/storywriting specialist model, full-parameter finetune of Qwen2.5-72B on mixture of synthetic and natural data. It uses Celeste 70B 0.1 data mixture, greatly expanding it to improve versatility, creativity and flavor of the resulting model.
MythoMax 13B
Gryphe/MythoMax-L2-13bOne of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay.
EVA-Qwen2.5-32B-v0.2
EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2A RP/storywriting specialist model, full-parameter finetune of Qwen2.5-32B on mixture of synthetic and natural data. It uses Celeste 70B 0.1 data mixture, greatly expanding it to improve versatility, creativity and flavor of the resulting model.
Magnum V2 72B
anthracite-org/magnum-v2-72bMagnum V2 72B