# Image Captioning on MS-COCO 200 images (test) Source: [Image Captioning on MS-COCO 200 images (test)]() Collection index: [llms.txt]() Data updated: 2026-03-31T09:10:40.783Z Evaluation of Image Captioning performance specifically on a 200-image subset of the MS-COCO test set, reporting efficiency metrics like Energy consumption and Latency alongside token counts. 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) | MS-COCO 200 images (test) | | Metric | Tokens | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 - [Tokens](): Higher is better; unit: SCALAR. - [Energy (J)](): Lower is better; unit: OTHER. - [Latency (s)](): Lower is better; unit: TIME. ## Recorded results | Method | Tokens | Result date | Report paper | | --- | --- | --- | --- | | LingoLoop | 1020.38 | Not recorded | 68fa79891e209131cea7e18a | | LingoLoop | 1002.08 | Not recorded | 68fa79891e209131cea7e18a | | LingoLoop | 797.55 | Not recorded | 68fa79891e209131cea7e18a | | LingoLoop | 554.41 | Not recorded | 68fa79891e209131cea7e18a | | Verbose images | 394.74 | Not recorded | 68fa79891e209131cea7e18a | | Verbose images | 362.38 | Not recorded | 68fa79891e209131cea7e18a | | Verbose images | 345.59 | Not recorded | 68fa79891e209131cea7e18a | | Verbose images | 332.29 | Not recorded | 68fa79891e209131cea7e18a | | None | 88.86 | Not recorded | 68fa79891e209131cea7e18a | | Noise | 88.24 | Not recorded | 68fa79891e209131cea7e18a | | None | 86.11 | Not recorded | 68fa79891e209131cea7e18a | | Noise | 85.78 | Not recorded | 68fa79891e209131cea7e18a | | None | 76.31 | Not recorded | 68fa79891e209131cea7e18a | | Noise | 74.89 | Not recorded | 68fa79891e209131cea7e18a | | Noise | 68.07 | Not recorded | 68fa79891e209131cea7e18a | | None | 66.64 | Not recorded | 68fa79891e209131cea7e18a | ### LingoLoop Tokens: 1020.38. Result ID: 69cb8ddd47f34ce924b40a32. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MLLM":"Qwen2.5-VL-3B"}. This record does not assert independent reproduction. ### LingoLoop Tokens: 1002.08. Result ID: 69cb8ddd47f34ce924b40a2e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MLLM":"InstructBLIP"}. This record does not assert independent reproduction. ### LingoLoop Tokens: 797.55. Result ID: 69cb8ddd47f34ce924b40a36. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MLLM":"Qwen2.5-VL-7B"}. This record does not assert independent reproduction. ### LingoLoop Tokens: 554.41. Result ID: 69cb8ddd47f34ce924b40a3a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MLLM":"InternVL3-8B"}. This record does not assert independent reproduction. ### Verbose images Tokens: 394.74. Result ID: 69cb8ddd47f34ce924b40a31. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MLLM":"Qwen2.5-VL-3B"}. This record does not assert independent reproduction. ### Verbose images Tokens: 362.38. Result ID: 69cb8ddd47f34ce924b40a39. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MLLM":"InternVL3-8B"}. This record does not assert independent reproduction. ### Verbose images Tokens: 345.59. Result ID: 69cb8ddd47f34ce924b40a35. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MLLM":"Qwen2.5-VL-7B"}. This record does not assert independent reproduction. ### Verbose images Tokens: 332.29. Result ID: 69cb8ddd47f34ce924b40a2d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MLLM":"InstructBLIP"}. This record does not assert independent reproduction. ### None Tokens: 88.86. Result ID: 69cb8ddd47f34ce924b40a33. [Reporting paper]() Recorded evaluation configuration: {"MLLM":"Qwen2.5-VL-7B"}. This record does not assert independent reproduction. ### Noise Tokens: 88.24. Result ID: 69cb8ddd47f34ce924b40a34. [Reporting paper]() Recorded evaluation configuration: {"MLLM":"Qwen2.5-VL-7B"}. This record does not assert independent reproduction. ### None Tokens: 86.11. Result ID: 69cb8ddd47f34ce924b40a2b. [Reporting paper]() Recorded evaluation configuration: {"MLLM":"InstructBLIP"}. This record does not assert independent reproduction. ### Noise Tokens: 85.78. Result ID: 69cb8ddd47f34ce924b40a2c. [Reporting paper]() Recorded evaluation configuration: {"MLLM":"InstructBLIP"}. This record does not assert independent reproduction. ### None Tokens: 76.31. Result ID: 69cb8ddd47f34ce924b40a37. [Reporting paper]() Recorded evaluation configuration: {"MLLM":"InternVL3-8B"}. This record does not assert independent reproduction. ### Noise Tokens: 74.89. Result ID: 69cb8ddd47f34ce924b40a38. [Reporting paper]() Recorded evaluation configuration: {"MLLM":"InternVL3-8B"}. This record does not assert independent reproduction. ### Noise Tokens: 68.07. Result ID: 69cb8ddd47f34ce924b40a30. [Reporting paper]() Recorded evaluation configuration: {"MLLM":"Qwen2.5-VL-3B"}. This record does not assert independent reproduction. ### None Tokens: 66.64. Result ID: 69cb8ddd47f34ce924b40a2f. [Reporting paper]() Recorded evaluation configuration: {"MLLM":"Qwen2.5-VL-3B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.