# Wide Baseline Matching on ReasonMatch-Bench Outdoor (test) Source: [Wide Baseline Matching on ReasonMatch-Bench Outdoor (test)]() Collection index: [llms.txt]() Data updated: 2026-06-04T09:40:50.531Z Evaluation of Wide Baseline Matching performance on the test split of the ReasonMatch-Bench Outdoor dataset, reporting L1, L2, and L3 metrics. 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 | Wide Baseline Matching | | Dataset (including any stated split) | ReasonMatch-Bench Outdoor (test) | | Metric | L1 Score | | Unit | SCALAR | | 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 - [L1 Score](): Higher is better; unit: SCALAR. - [L2 Score](): Higher is better; unit: SCALAR. - [L3 Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | L1 Score | Result date | Report paper | | --- | --- | --- | --- | | Qwen3-VL-8B + DCRL | 90.9 | Not recorded | 6a2106a5c10484bac23f02fc | | GPT-5-mini | 75.8 | Not recorded | 6a2106a5c10484bac23f02fc | | Gemini-2.5-Pro | 63.4 | Not recorded | 6a2106a5c10484bac23f02fc | | GPT-5-Chat | 61.8 | Not recorded | 6a2106a5c10484bac23f02fc | | Qwen3-VL-235B | 58.8 | Not recorded | 6a2106a5c10484bac23f02fc | | Claude-4.5-Sonnet | 50.3 | Not recorded | 6a2106a5c10484bac23f02fc | | Claude-4.1-Opus | 45.1 | Not recorded | 6a2106a5c10484bac23f02fc | | Claude-4-Sonnet | 45 | Not recorded | 6a2106a5c10484bac23f02fc | | GPT-4o-241106 | 33.9 | Not recorded | 6a2106a5c10484bac23f02fc | | Qwen3-VL-8B-Instruct | 30.4 | Not recorded | 6a2106a5c10484bac23f02fc | ### Qwen3-VL-8B + DCRL L1 Score: 90.9. Result ID: 6a214814fbc373592c1d47e6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen3-VL-8B","Method":"DCRL"}. This record does not assert independent reproduction. ### GPT-5-mini L1 Score: 75.8. Result ID: 6a214814fbc373592c1d47dd. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Gemini-2.5-Pro L1 Score: 63.4. Result ID: 6a214814fbc373592c1d47e0. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-5-Chat L1 Score: 61.8. Result ID: 6a214814fbc373592c1d47de. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen3-VL-235B L1 Score: 58.8. Result ID: 6a214814fbc373592c1d47e4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"235B"}. This record does not assert independent reproduction. ### Claude-4.5-Sonnet L1 Score: 50.3. Result ID: 6a214814fbc373592c1d47e1. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Claude-4.1-Opus L1 Score: 45.1. Result ID: 6a214814fbc373592c1d47e2. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Claude-4-Sonnet L1 Score: 45. Result ID: 6a214814fbc373592c1d47e3. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-4o-241106 L1 Score: 33.9. Result ID: 6a214814fbc373592c1d47df. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen3-VL-8B-Instruct L1 Score: 30.4. Result ID: 6a214814fbc373592c1d47e5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"8B","Mode":"Instruct"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.