# PinchBench leaderboard

Agentic benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/leaderboards/benchmarks/agentic-pinch-bench

Every model the catalog carries a published PinchBench value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Agentic |
| Measure | Average success rate from official runs |
| Tasks | 23 OpenClaw agent tasks |
| Difficulty | Long-horizon agent workflows |
| Published by | [About PinchBench](https://pinchbench.com/about) |

An OpenClaw agent benchmark from Kilo that measures successful task completion across standardized real-world agent workflows.

## PinchBench ranking

10 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 | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Pokee-Isaac 28B](https://modelscale.dev/models/pokee-isaac-28b) | Pokee AI | 95.7 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Nemotron 3.5 Bolt 74B-A9B BF16](https://modelscale.dev/models/nemotron-3-5-bolt-74b-a9b-bf16) | NVIDIA | 90.3 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Nemotron 3 Ultra](https://modelscale.dev/models/nemotron-3-ultra-500b) | NVIDIA | 90.0 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Sage-A1.5](https://modelscale.dev/models/sage-a1-5) | InternScience | 90.0 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Nemotron 3.5 Bolt 74B-A9B](https://modelscale.dev/models/nemotron-3-5-bolt-74b-a9b) | NVIDIA | 87.8 | Observed 2026-11-21 · source benchlm:models |
| 6 | [Nemotron 3.5 Lightning 30B A3B NVFP4](https://modelscale.dev/models/nemotron-3-5-lightning-30b-a3b-nvfp4) | NVIDIA | 83.4 | Observed 2026-11-21 · source benchlm:models |
| 7 | [LFM2.5-24B-A2B](https://modelscale.dev/models/lfm2-5-24b-a2b) | LiquidAI | 83.2 | Observed 2026-11-21 · source benchlm:models |
| 8 | [LLaDA2.2-flash](https://modelscale.dev/models/llada2-2-flash) | InclusionAI | 81.7 | Observed 2026-11-21 · source benchlm:models |
| 9 | [LFM2.5-2.6B](https://modelscale.dev/models/lfm2-5-2-6b) | LiquidAI | 68.2 | Observed 2026-11-21 · source benchlm:models |
| 10 | [LLaDA2.2-mini](https://modelscale.dev/models/llada2-2-mini) | InclusionAI | 62.3 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
