Pricing and context window via OpenRouter, 2026-11-03.
Liquid AI released LFM2.5-2.6B, a 2.6B-parameter open-weight model trained via supervised fine-tuning, teacher specialization, on-policy distillation, and agentic RL for local tool-use agents. The model claims competitive performance with models up to 4x its size on instruction-following, tool-use, and agentic benchmarks while running at 220 tok/s on Apple M5 Max hardware.
| Benchmark | Score | Rank | Source |
|---|---|---|---|
| AA Intelligence Index | 8.4 index | 113 of 123 | Artificial Analysis, Oct 2026 ↗ |
| GPQA | 55.8% | 150 of 159 | Artificial Analysis, Aug 2026 ↗ |
| AA Coding Index | 7.7 index | 75 of 78 | Artificial Analysis, Oct 2026 ↗ |
| Speed (tok/s) | 207 tok/s | 19 of 126 | Artificial Analysis, Sep 2026 ↗ |
| LiveCodeBench | 59.4% | 36 of 47 | Hugging Face model card ↗ |
Rank is against every model in our database with a sourced score on that benchmark, each counted once with its best score.
Liquid AI has released LFM2.5-2.6B, a 2.6B-parameter model designed to run capable tool-calling agents locally on laptops and phones. The company claims it matches or beats models up to 4x its size on instruction-following and tool-use benchmarks while running under 2.5GB of memory.