# ZeroBench w/ Python leaderboard

Multimodal & Grounded 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/multimodal-grounded-zero-bench-python

ZeroBench_main with Python. Every model the catalog carries a published ZeroBench w/ Python value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Multimodal & Grounded |
| Measure | Pass@5 |
| Tasks | Visual reasoning questions with Python |
| Difficulty | Tool-augmented visual reasoning |
| Published by | [Kimi K3: Open Frontier Intelligence](https://www.kimi.com/blog/kimi-k3) |

A Python-assisted ZeroBench_main evaluation reported as pass@5.

## ZeroBench w/ Python ranking

7 models with a published ZeroBench w/ Python 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 | Pass@5 | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Kimi K3.1 Pro](https://modelscale.dev/models/kimi-3-1-pro) | Moonshot AI | 63.0 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Hy4](https://modelscale.dev/models/hy4) | Tencent | 55.4 | Observed 2026-11-21 · source benchlm:models |
| 3 | [DeepSeek V4.1 Flash 1017](https://modelscale.dev/models/deepseek-v4-1-flash) | DeepSeek | 51.0 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Qwen3.8 Max](https://modelscale.dev/models/qwen3-8-max) | Alibaba | 49.0 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Hy4 flash](https://modelscale.dev/models/hy4-flash) | Tencent | 45.8 | Observed 2026-11-21 · source benchlm:models |
| 6 | [Kimi K3](https://modelscale.dev/models/kimi-3) | Moonshot AI | 41.0 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Inkling 2 Mini](https://modelscale.dev/models/inkling-2-mini) | Thinking Machines Lab | 34.0 | 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.
