# Fine-grained Visual Reasoning on V\* (Avg@8) Source: [Fine-grained Visual Reasoning on V\* (Avg@8)]() Collection index: [llms.txt]() Data updated: 2026-04-10T00:19:54.009Z Evaluation of fine-grained visual reasoning capabilities on the V\* dataset, reporting performance using Avg@8 scores for attribute, relative, and overall comparisons. 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 | Fine-grained visual reasoning | | Dataset (including any stated split) | V\* | | Metric | Avg@8 Overall | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | 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 - [Avg@8 Overall](): Higher is better; unit: PERCENT. - [Avg@8 Attribute](): Higher is better; unit: PERCENT. - [Avg@8 Relative](): Higher is better; unit: PERCENT. ## Recorded results | Method | Avg@8 Overall | Result date | Report paper | | --- | --- | --- | --- | | MAPO | 89.5 | Not recorded | 69d732b77d0172140ec76cda | | Mini-o3 | 89.3 | Not recorded | 69d732b77d0172140ec76cda | | Ovis2.5-9B + GSPO | 89.1 | Not recorded | 69d732b77d0172140ec76cda | | Ovis2.5-9B + DAPO | 88.8 | Not recorded | 69d732b77d0172140ec76cda | | Ovis2.5-9B + GRPO | 88.6 | Not recorded | 69d732b77d0172140ec76cda | | DeepEyes | 88 | Not recorded | 69d732b77d0172140ec76cda | | Ovis2.5-9B + PPO | 82.8 | Not recorded | 69d732b77d0172140ec76cda | | Thyme | 82.2 | Not recorded | 69d732b77d0172140ec76cda | | DeepEyesv2 | 81.8 | Not recorded | 69d732b77d0172140ec76cda | | Ovis2.5-9B | 81.8 | Not recorded | 69d732b77d0172140ec76cda | | Gemini 2.5 Pro | 81.4 | Not recorded | 69d732b77d0172140ec76cda | | Ovis2.5-9B + Coldstart SFT | 77.5 | Not recorded | 69d732b77d0172140ec76cda | | GPT-5 | 71.3 | Not recorded | 69d732b77d0172140ec76cda | ### MAPO Avg@8 Overall: 89.5. Result ID: 69d8421447f34ce924c04b57. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"backbone":"Ovis2.5-9B"}. This record does not assert independent reproduction. ### Mini-o3 Avg@8 Overall: 89.3. Result ID: 69d8421447f34ce924c04b4f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"reproduced\_by\_authors":"true"}. This record does not assert independent reproduction. ### Ovis2.5-9B + GSPO Avg@8 Overall: 89.1. Result ID: 69d8421447f34ce924c04b56. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training":"GSPO"}. This record does not assert independent reproduction. ### Ovis2.5-9B + DAPO Avg@8 Overall: 88.8. Result ID: 69d8421447f34ce924c04b55. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training":"DAPO"}. This record does not assert independent reproduction. ### Ovis2.5-9B + GRPO Avg@8 Overall: 88.6. Result ID: 69d8421447f34ce924c04b54. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"training":"GRPO"}. This record does not assert independent reproduction. ### DeepEyes Avg@8 Overall: 88. Result ID: 69d8421447f34ce924c04b4d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"reproduced\_by\_authors":"true"}. This record does not assert independent reproduction. ### Ovis2.5-9B + PPO Avg@8 Overall: 82.8. Result ID: 69d8421447f34ce924c04b53. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training":"PPO"}. This record does not assert independent reproduction. ### Thyme Avg@8 Overall: 82.2. Result ID: 69d8421447f34ce924c04b4e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"results\_source":"original paper"}. This record does not assert independent reproduction. ### DeepEyesv2 Avg@8 Overall: 81.8. Result ID: 69d8421447f34ce924c04b50. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"results\_source":"original paper"}. This record does not assert independent reproduction. ### Ovis2.5-9B Avg@8 Overall: 81.8. Result ID: 69d8421447f34ce924c04b51. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Gemini 2.5 Pro Avg@8 Overall: 81.4. Result ID: 69d8421447f34ce924c04b4c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Ovis2.5-9B + Coldstart SFT Avg@8 Overall: 77.5. Result ID: 69d8421447f34ce924c04b52. [Reporting paper]() Recorded evaluation configuration: {"training":"Supervised Fine-Tuning"}. This record does not assert independent reproduction. ### GPT-5 Avg@8 Overall: 71.3. Result ID: 69d8421447f34ce924c04b4b. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.