# Wide-Baseline Correspondence Reasoning on ReasonMatch-Bench Overall 90-sample high-divergence subset Source: [Wide-Baseline Correspondence Reasoning on ReasonMatch-Bench Overall 90-sample high-divergence subset]() Collection index: [llms.txt]() Data updated: 2026-06-04T09:40:50.323Z Evaluation of model performance on the high-divergence subset (90 samples) of the ReasonMatch-Bench, focusing on wide-baseline correspondence reasoning, measured by F1 score. 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 Correspondence Reasoning | | Dataset (including any stated split) | ReasonMatch-Bench Overall 90-sample high-divergence subset | | Metric | F1 Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 - [F1 Score](): Higher is better; unit: PERCENT. - [Precision](): Higher is better; unit: PERCENT. - [Recall](): Higher is better; unit: PERCENT. ## Recorded results | Method | F1 Score | Result date | Report paper | | --- | --- | --- | --- | | Human | 94.7 | Not recorded | 6a2106a5c10484bac23f02fc | | Human | 84 | Not recorded | 6a2106a5c10484bac23f02fc | | Human | 84 | Not recorded | 6a2106a5c10484bac23f02fc | | DCRL | 70.6 | Not recorded | 6a2106a5c10484bac23f02fc | | DCRL | 52 | Not recorded | 6a2106a5c10484bac23f02fc | | DCRL | 52 | Not recorded | 6a2106a5c10484bac23f02fc | | GPT-5-mini | 49.7 | Not recorded | 6a2106a5c10484bac23f02fc | | Qwen3-VL-235B | 45.7 | Not recorded | 6a2106a5c10484bac23f02fc | | Gemini-2.5-Pro | 44.1 | Not recorded | 6a2106a5c10484bac23f02fc | | GPT-5-mini | 37.2 | Not recorded | 6a2106a5c10484bac23f02fc | | GPT-5-mini | 37.2 | Not recorded | 6a2106a5c10484bac23f02fc | | Claude-4.5-Sonnet | 30.5 | Not recorded | 6a2106a5c10484bac23f02fc | | Qwen3-VL-235B | 29.9 | Not recorded | 6a2106a5c10484bac23f02fc | | Qwen3-VL-235B | 29.9 | Not recorded | 6a2106a5c10484bac23f02fc | | Gemini-2.5-Pro | 29.5 | Not recorded | 6a2106a5c10484bac23f02fc | | Gemini-2.5-Pro | 29.5 | Not recorded | 6a2106a5c10484bac23f02fc | | Claude-4.5-Sonnet | 24 | Not recorded | 6a2106a5c10484bac23f02fc | | Claude-4.5-Sonnet | 24 | Not recorded | 6a2106a5c10484bac23f02fc | ### Human F1 Score: 94.7. Result ID: 6a214814fbc373592c1d47ad. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Human F1 Score: 84. Result ID: 6a214814fbc373592c1d47a1. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Human F1 Score: 84. Result ID: 6a214814fbc373592c1d47f6. [Reporting paper]() Recorded evaluation configuration: {"Annotator":"Human"}. This record does not assert independent reproduction. ### DCRL F1 Score: 70.6. Result ID: 6a214814fbc373592c1d47ac. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### DCRL F1 Score: 52. Result ID: 6a214814fbc373592c1d47a0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### DCRL F1 Score: 52. Result ID: 6a214814fbc373592c1d47f5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Open-Source Models"}. This record does not assert independent reproduction. ### GPT-5-mini F1 Score: 49.7. Result ID: 6a214814fbc373592c1d47a8. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen3-VL-235B F1 Score: 45.7. Result ID: 6a214814fbc373592c1d47ab. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Gemini-2.5-Pro F1 Score: 44.1. Result ID: 6a214814fbc373592c1d47a9. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-5-mini F1 Score: 37.2. Result ID: 6a214814fbc373592c1d479c. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-5-mini F1 Score: 37.2. Result ID: 6a214814fbc373592c1d47f1. [Reporting paper]() Recorded evaluation configuration: {"Model Category":"Closed-Source Models"}. This record does not assert independent reproduction. ### Claude-4.5-Sonnet F1 Score: 30.5. Result ID: 6a214814fbc373592c1d47aa. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen3-VL-235B F1 Score: 29.9. Result ID: 6a214814fbc373592c1d479f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen3-VL-235B F1 Score: 29.9. Result ID: 6a214814fbc373592c1d47f4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Open-Source Models"}. This record does not assert independent reproduction. ### Gemini-2.5-Pro F1 Score: 29.5. Result ID: 6a214814fbc373592c1d479d. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Gemini-2.5-Pro F1 Score: 29.5. Result ID: 6a214814fbc373592c1d47f2. [Reporting paper]() Recorded evaluation configuration: {"Model Category":"Closed-Source Models"}. This record does not assert independent reproduction. ### Claude-4.5-Sonnet F1 Score: 24. Result ID: 6a214814fbc373592c1d479e. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Claude-4.5-Sonnet F1 Score: 24. Result ID: 6a214814fbc373592c1d47f3. [Reporting paper]() Recorded evaluation configuration: {"Model Category":"Closed-Source Models"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.