# Jigsaw Puzzle Solving on MS COCO Jigsaw Source: [Jigsaw Puzzle Solving on MS COCO Jigsaw]() Collection index: [llms.txt]() Data updated: 2026-05-25T09:17:48.063Z Evaluation of model performance on solving Jigsaw Puzzles using the MS COCO Jigsaw dataset, measured by Pass@1. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Jigsaw Puzzle Solving | | Dataset (including any stated split) | MS COCO Jigsaw | | Metric | Pass@1 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 10 of 10 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Pass@1](): Higher is better; unit: PERCENT. ## Recorded results | Method | Pass@1 | Result date | Report paper | | --- | --- | --- | --- | | Kimi K2.5 + ETCHR | 70.5 | Not recorded | 6a13d7af6f71c5ae7dc9eadd | | Kimi K2.5 | 44.5 | Not recorded | 6a13d7af6f71c5ae7dc9eadd | | Gemini-3.1-Flash-Lite + ETCHR | 36 | Not recorded | 6a13d7af6f71c5ae7dc9eadd | | Gemini-3.1-Flash-Lite | 27.5 | Not recorded | 6a13d7af6f71c5ae7dc9eadd | | Qwen3-VL-8B + ETCHR | 13 | Not recorded | 6a13d7af6f71c5ae7dc9eadd | | ThinkMorph-7B | 10.5 | Not recorded | 6a13d7af6f71c5ae7dc9eadd | | Qwen3-VL-8B | 9.5 | Not recorded | 6a13d7af6f71c5ae7dc9eadd | | DeepEyesV2 | 6.5 | Not recorded | 6a13d7af6f71c5ae7dc9eadd | | Thyme | 6.5 | Not recorded | 6a13d7af6f71c5ae7dc9eadd | | Bagel-Zebra-CoT | 5.5 | Not recorded | 6a13d7af6f71c5ae7dc9eadd | ### Kimi K2.5 + ETCHR Pass@1: 70.5. Result ID: 6a141325fbc373592c0b8599. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Temperature":"0"}. This record does not assert independent reproduction. ### Kimi K2.5 Pass@1: 44.5. Result ID: 6a141325fbc373592c0b8598. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Temperature":"0"}. This record does not assert independent reproduction. ### Gemini-3.1-Flash-Lite + ETCHR Pass@1: 36. Result ID: 6a141325fbc373592c0b8597. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Temperature":"0"}. This record does not assert independent reproduction. ### Gemini-3.1-Flash-Lite Pass@1: 27.5. Result ID: 6a141325fbc373592c0b8596. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Temperature":"0"}. This record does not assert independent reproduction. ### Qwen3-VL-8B + ETCHR Pass@1: 13. Result ID: 6a141325fbc373592c0b8595. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Temperature":"0"}. This record does not assert independent reproduction. ### ThinkMorph-7B Pass@1: 10.5. Result ID: 6a141325fbc373592c0b8593. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Temperature":"0","Max image generations":"10"}. This record does not assert independent reproduction. ### Qwen3-VL-8B Pass@1: 9.5. Result ID: 6a141325fbc373592c0b8594. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Temperature":"0"}. This record does not assert independent reproduction. ### DeepEyesV2 Pass@1: 6.5. Result ID: 6a141325fbc373592c0b8590. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Temperature":"0","Max tool invocations":"10"}. This record does not assert independent reproduction. ### Thyme Pass@1: 6.5. Result ID: 6a141325fbc373592c0b8591. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Temperature":"0","Max tool invocations":"10"}. This record does not assert independent reproduction. ### Bagel-Zebra-CoT Pass@1: 5.5. Result ID: 6a141325fbc373592c0b8592. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Temperature":"0","Max image generations":"10"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.