Language Open Weights
- Params
- 8B
- Context
- 128K
- Released
- May 2026
On-device Mixture-of-Experts model for tool calling and reasoning..
Full LFM2.5-8B-A1B specs →
🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// COMPARISON
LFM2.5-8B-A1B
A head-to-head benchmark comparison of LFM2.5-8B-A1B across 3 evaluations.
The models
Benchmark comparison
| Benchmark | LFM2.5-8B-A1B |
|---|---|
| general | |
| IFEval | 91.84% |
| math | |
| MATH-500 | 88.76% |
| tool-use | |
| BFCL v3 | 64.36% |
Best result per row highlighted in cyan. Each benchmark links to its definition and sources; each model links to its full scorecard.
Frequently asked questions
How many benchmarks are compared? ▶
This comparison covers 3 benchmarks on which at least one of the selected models has a published score.
Where do the benchmark scores come from? ▶
Scores are aggregated from official model cards, technical reports and standard public evaluations, and link back to each benchmark's source. They are updated as new results are published.
Explore further
Build a different comparison
Models (0 selected)
Benchmarks (auto)
Select at least two models.