# Multi-image context generation on MICON-Bench Source: [Multi-image context generation on MICON-Bench]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:54:09.335Z Evaluation of multi-image context generation capabilities using the MICON-Bench dataset, reporting performance across specific dimensions including Object, Spatial, Attribute, Component, FG/BG, Story, and an overall average 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 | Multi-image context generation | | Dataset (including any stated split) | MICON-Bench | | Metric | Object 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 - [Object Score](): Higher is better; unit: PERCENT. - [Spatial Score](): Higher is better; unit: PERCENT. - [Attribute Score](): Higher is better; unit: PERCENT. - [Component Score](): Higher is better; unit: PERCENT. - [FG/BG Score](): Higher is better; unit: PERCENT. - [Story Score](): Higher is better; unit: PERCENT. - [Overall Avg Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Object Score | Result date | Report paper | | --- | --- | --- | --- | | GPT-Image | 98.85 | Not recorded | 699d30c46017c4460ffab7e4 | | Qwen-Image-Edit-2507 | 98.03 | Not recorded | 699d30c46017c4460ffab7e4 | | Nano-Banana | 97.88 | Not recorded | 699d30c46017c4460ffab7e4 | | Qwen-Image-Edit-2507 | 96.52 | Not recorded | 699d30c46017c4460ffab7e4 | | GPT-Image | 96.45 | Not recorded | 699d30c46017c4460ffab7e4 | | Nano-Banana | 95.6 | Not recorded | 699d30c46017c4460ffab7e4 | | OmniGen2 + DAR | 89.84 | Not recorded | 699d30c46017c4460ffab7e4 | | BAGEL + DAR | 89.56 | Not recorded | 699d30c46017c4460ffab7e4 | | OmniGen2 | 89.52 | Not recorded | 699d30c46017c4460ffab7e4 | | OmniGen2 + DAR | 89.5 | Not recorded | 699d30c46017c4460ffab7e4 | | BAGEL | 89.08 | Not recorded | 699d30c46017c4460ffab7e4 | | DreamOmni2 | 88.95 | Not recorded | 699d30c46017c4460ffab7e4 | | OmniGen2 | 88.77 | Not recorded | 699d30c46017c4460ffab7e4 | | DreamOmni2 | 88.24 | Not recorded | 699d30c46017c4460ffab7e4 | | BAGEL + DAR | 88.04 | Not recorded | 699d30c46017c4460ffab7e4 | | BAGEL | 87.64 | Not recorded | 699d30c46017c4460ffab7e4 | | UNO | 62.3 | Not recorded | 699d30c46017c4460ffab7e4 | | UNO | 58.4 | Not recorded | 699d30c46017c4460ffab7e4 | ### GPT-Image Object Score: 98.85. Result ID: 699e4eb25698665ec40d7d73. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Verifier":"InternVL3.5-38B"}. This record does not assert independent reproduction. ### Qwen-Image-Edit-2507 Object Score: 98.03. Result ID: 699e4eb25698665ec40d7d76. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Verifier":"InternVL3.5-38B"}. This record does not assert independent reproduction. ### Nano-Banana Object Score: 97.88. Result ID: 699e4eb25698665ec40d7d72. [Reporting paper]() Recorded evaluation configuration: {"Verifier":"InternVL3.5-38B"}. This record does not assert independent reproduction. ### Qwen-Image-Edit-2507 Object Score: 96.52. Result ID: 699e4eb25698665ec40d7d51. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-Image Object Score: 96.45. Result ID: 699e4eb25698665ec40d7d4e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Nano-Banana Object Score: 95.6. Result ID: 699e4eb25698665ec40d7d4d. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### OmniGen2 + DAR Object Score: 89.84. Result ID: 699e4eb25698665ec40d7d55. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"DAR":"true"}. This record does not assert independent reproduction. ### BAGEL + DAR Object Score: 89.56. Result ID: 699e4eb25698665ec40d7d78. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Verifier":"InternVL3.5-38B"}. This record does not assert independent reproduction. ### OmniGen2 Object Score: 89.52. Result ID: 699e4eb25698665ec40d7d54. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"DAR":"false"}. This record does not assert independent reproduction. ### OmniGen2 + DAR Object Score: 89.5. Result ID: 699e4eb25698665ec40d7d7a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Verifier":"InternVL3.5-38B"}. This record does not assert independent reproduction. ### BAGEL Object Score: 89.08. Result ID: 699e4eb25698665ec40d7d77. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Verifier":"InternVL3.5-38B"}. This record does not assert independent reproduction. ### DreamOmni2 Object Score: 88.95. Result ID: 699e4eb25698665ec40d7d75. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Verifier":"InternVL3.5-38B"}. This record does not assert independent reproduction. ### OmniGen2 Object Score: 88.77. Result ID: 699e4eb25698665ec40d7d79. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Verifier":"InternVL3.5-38B"}. This record does not assert independent reproduction. ### DreamOmni2 Object Score: 88.24. Result ID: 699e4eb25698665ec40d7d50. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### BAGEL + DAR Object Score: 88.04. Result ID: 699e4eb25698665ec40d7d53. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"DAR":"true"}. This record does not assert independent reproduction. ### BAGEL Object Score: 87.64. Result ID: 699e4eb25698665ec40d7d52. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"DAR":"false"}. This record does not assert independent reproduction. ### UNO Object Score: 62.3. Result ID: 699e4eb25698665ec40d7d74. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Verifier":"InternVL3.5-38B"}. This record does not assert independent reproduction. ### UNO Object Score: 58.4. Result ID: 699e4eb25698665ec40d7d4f. [Reporting paper]() [Method origin 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.