Agentic benchmark
PinchBench leaderboard
Every model the catalog carries a published PinchBench value for, ranked by that value.
CategoryAgentic
MeasureAverage success rate from official runs
Tasks23 OpenClaw agent tasks
DifficultyLong-horizon agent workflows
Published byAbout PinchBench
An OpenClaw agent benchmark from Kilo that measures successful task completion across standardized real-world agent workflows.
PinchBench ranking
6 models with a published PinchBench value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Average success rate from official runs |
|---|---|---|---|
| 1 | PAPokee-Isaac 28B | Pokee AI | 95.7 |
| 2 |  Nemotron 3 Ultra | NVIDIA | 90.0 |
| 3 | Nemotron 3.5 Lightning 30B A3B NVFP4 | NVIDIA | 83.4 |
| 4 |  LLaDA2.2-flash | InclusionAI | 81.7 |
| 5 |  LFM2.5-2.6B | LiquidAI | 68.2 |
| 6 | LLaDA2.2-mini | InclusionAI | 62.3 |
Evidence key: Observed
Rows are ordered by the value About PinchBench published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.