# Image Captioning on DID-Bench GT-{GPT4-V} Source: [Image Captioning on DID-Bench GT-{GPT4-V}]() Collection index: [llms.txt]() Data updated: 2026-02-27T10:20:06.992Z Evaluation of Image Captioning performance on the DID-Bench GT-{GPT4-V} dataset, assessed using standard captioning metrics including BLEU scores, CIDEr, METEOR, ROUGE, SPICE, and WMD. 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 | Image Captioning | | Dataset (including any stated split) | DID-Bench GT-{GPT4-V} | | Metric | BLEU-1 | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 19 of 19 | | 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 - [BLEU-1](): Higher is better; unit: SCALAR. - [BLEU-2](): Higher is better; unit: SCALAR. - [BLEU-3](): Higher is better; unit: SCALAR. - [BLEU-4](): Higher is better; unit: SCALAR. - [CIDEr](): Higher is better; unit: SCALAR. - [METEOR](): Higher is better; unit: SCALAR. - [ROUGE](): Higher is better; unit: SCALAR. - [SPICE](): Higher is better; unit: SCALAR. - [WMD](): Lower is better; unit: SCALAR. ## Recorded results | Method | BLEU-1 | Result date | Report paper | | --- | --- | --- | --- | | Ours | 40.3 | Not recorded | 68fa77df1e209131cea75b6b | | Synthesized | 37.4 | Not recorded | 68fa77df1e209131cea75b6b | | Ours | 37.3 | Not recorded | 68fa77df1e209131cea75b6b | | IT | 33.53 | Not recorded | 68fa77df1e209131cea75b6b | | ShareCaptioner | 33.42 | Not recorded | 68fa77df1e209131cea75b6b | | IT | 30.38 | Not recorded | 68fa77df1e209131cea75b6b | | Global | 30.18 | Not recorded | 68fa77df1e209131cea75b6b | | Patch Matters | 29.36 | Not recorded | 68fa77df1e209131cea75b6b | | Ours | 29.36 | Not recorded | 68fa77df1e209131cea75b6b | | Synthesized | 28.79 | Not recorded | 68fa77df1e209131cea75b6b | | ALLaVA | 26.27 | Not recorded | 68fa77df1e209131cea75b6b | | Global | 19.98 | Not recorded | 68fa77df1e209131cea75b6b | | IT | 19.19 | Not recorded | 68fa77df1e209131cea75b6b | | Synthesized | 18.78 | Not recorded | 68fa77df1e209131cea75b6b | | LLaVA-1.5 | 7.5 | Not recorded | 68fa77df1e209131cea75b6b | | Global | 7.5 | Not recorded | 68fa77df1e209131cea75b6b | | PoCa | 3.09 | Not recorded | 68fa77df1e209131cea75b6b | | PoCa | 2.65 | Not recorded | 68fa77df1e209131cea75b6b | | PoCa | 0.36 | Not recorded | 68fa77df1e209131cea75b6b | ### Ours BLEU-1: 40.3. Result ID: 69a16fba35dfcabb00e7053b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Mini-Gemini-7B"}. This record does not assert independent reproduction. ### Synthesized BLEU-1: 37.4. Result ID: 69a16fba35dfcabb00e7053a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Mini-Gemini-7B"}. This record does not assert independent reproduction. ### Ours BLEU-1: 37.3. Result ID: 69a16fba35dfcabb00e70536. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"LLaVA-1.6-7B"}. This record does not assert independent reproduction. ### IT BLEU-1: 33.53. Result ID: 69a16fba35dfcabb00e70538. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Mini-Gemini-7B"}. This record does not assert independent reproduction. ### ShareCaptioner BLEU-1: 33.42. Result ID: 69a16fba35dfcabb00e704cf. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### IT BLEU-1: 30.38. Result ID: 69a16fba35dfcabb00e70533. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LLaVA-1.6-7B"}. This record does not assert independent reproduction. ### Global BLEU-1: 30.18. Result ID: 69a16fba35dfcabb00e70537. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Mini-Gemini-7B"}. This record does not assert independent reproduction. ### Patch Matters BLEU-1: 29.36. Result ID: 69a16fba35dfcabb00e704d1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"LLaVA-1.5"}. This record does not assert independent reproduction. ### Ours BLEU-1: 29.36. Result ID: 69a16fba35dfcabb00e70531. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"LLaVA-1.5-7B"}. This record does not assert independent reproduction. ### Synthesized BLEU-1: 28.79. Result ID: 69a16fba35dfcabb00e70535. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LLaVA-1.6-7B"}. This record does not assert independent reproduction. ### ALLaVA BLEU-1: 26.27. Result ID: 69a16fba35dfcabb00e704d0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Global BLEU-1: 19.98. Result ID: 69a16fba35dfcabb00e70532. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"LLaVA-1.6-7B"}. This record does not assert independent reproduction. ### IT BLEU-1: 19.19. Result ID: 69a16fba35dfcabb00e7052e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LLaVA-1.5-7B"}. This record does not assert independent reproduction. ### Synthesized BLEU-1: 18.78. Result ID: 69a16fba35dfcabb00e70530. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LLaVA-1.5-7B"}. This record does not assert independent reproduction. ### LLaVA-1.5 BLEU-1: 7.5. Result ID: 69a16fba35dfcabb00e704ce. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Global BLEU-1: 7.5. Result ID: 69a16fba35dfcabb00e7052d. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"LLaVA-1.5-7B"}. This record does not assert independent reproduction. ### PoCa BLEU-1: 3.09. Result ID: 69a16fba35dfcabb00e70534. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LLaVA-1.6-7B"}. This record does not assert independent reproduction. ### PoCa BLEU-1: 2.65. Result ID: 69a16fba35dfcabb00e70539. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Mini-Gemini-7B"}. This record does not assert independent reproduction. ### PoCa BLEU-1: 0.36. Result ID: 69a16fba35dfcabb00e7052f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LLaVA-1.5-7B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.