LFM2.5-2.6B places in the top three on ToolSandbox.
Open weights Small
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AIME 2025 | 51.9% | #130 of 143 | Model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LiveCodeBench v6 | 59.4% | #65 of 76 | Model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ToolSandbox | 77.8% | #3 of 5 | Model card | |
| Claw-Eval | 62.9% | #10 of 14 | Model card | |
| BFCL V4 | 56.9% | #20 of 24 | Model card | |
| τ³-bench Banking | 5.67% | #20 of 20 | Model card | |
| PinchBench | 68.2% | #13 of 13 | Model card | |
| BrowseComp-Plus | 26.9% | #4 of 4 | Model card |
The benchmarks the lab chose to headline, with the scores it gave.