| ,"-, clemscore","all, Average % Played","all, Average Quality Score","matchit, % Played","matchit, Quality Score","matchit, Quality Score (std)","mm_mapworld, % Played","mm_mapworld, Quality Score","mm_mapworld, Quality Score (std)","mm_mapworld_graphs, % Played","mm_mapworld_graphs, Quality Score","mm_mapworld_graphs, Quality Score (std)","mm_mapworld_specificroom, % Played","mm_mapworld_specificroom, Quality Score","mm_mapworld_specificroom, Quality Score (std)","multimodal_referencegame, % Played","multimodal_referencegame, Quality Score","multimodal_referencegame, Quality Score (std)" | |
| Idefics3-8B-Llama3-t0.0--Idefics3-8B-Llama3-t0.0,17.52,32.59,53.76,40.0,79.17,41.49,14.0,4.76,12.6,0.0,,,10.0,100.0,0.0,98.97,31.09,46.35 | |
| InternVL2-26B-t0.0--InternVL2-26B-t0.0,37.45,66.76,56.09,100.0,93.33,25.15,52.0,58.47,20.73,16.67,69.33,16.91,80.0,25.0,44.23,85.13,34.34,47.56 | |
| InternVL2-40B-t0.0--InternVL2-40B-t0.0,32.23,56.27,57.28,96.67,79.31,40.86,28.0,23.29,35.09,33.33,76.2,20.56,23.33,71.43,48.8,100.0,36.15,48.11 | |
| InternVL2-8B-t0.0--InternVL2-8B-t0.0,23.17,46.61,49.7,100.0,68.33,46.91,0.0,,,3.33,85.71,,43.33,7.69,27.74,86.41,37.09,48.38 | |
| InternVL2-Llama3-76B-t0.0--InternVL2-Llama3-76B-t0.0,33.84,54.8,61.76,100.0,90.0,30.25,34.0,57.15,18.59,3.33,54.55,,36.67,72.73,46.71,100.0,34.36,47.55 | |
| Phi-3-vision-128k-instruct-t0.0--Phi-3-vision-128k-instruct-t0.0,3.34,5.06,65.98,0.0,,,4.0,45.0,7.07,3.33,52.94,,0.0,,,17.95,100.0,0.0 | |
| Phi-3.5-vision-instruct-t0.0--Phi-3.5-vision-instruct-t0.0,15.64,40.67,38.46,100.0,0.0,0.0,0.0,,,3.33,100.0,,0.0,,,100.0,15.38,36.13 | |
| Pixtral-12B-2409-t0.0--Pixtral-12B-2409-t0.0,28.64,49.98,57.3,100.0,63.33,48.6,24.0,58.01,29.16,3.33,66.67,,43.33,53.85,51.89,79.23,44.66,49.79 | |
| claude-3-5-sonnet-20240620-t0.0--claude-3-5-sonnet-20240620-t0.0,80.77,95.33,84.73,100.0,85.0,36.01,100.0,82.41,11.7,76.67,85.23,15.36,100.0,90.0,30.51,100.0,81.03,39.26 | |
| claude-3-opus-20240229-t0.0--claude-3-opus-20240229-t0.0,68.16,99.33,68.62,100.0,81.67,39.02,100.0,75.79,14.43,96.67,85.12,13.27,100.0,53.33,50.74,100.0,47.18,49.98 | |
| dolphin-vision-72b-t0.0--dolphin-vision-72b-t0.0,4.65,7.88,58.95,16.67,90.0,31.62,4.0,60.61,8.57,3.33,0.0,,6.67,100.0,0.0,8.72,44.12,50.4 | |
| gemini-1.5-flash-latest-t0.0--gemini-1.5-flash-latest-t0.0,47.73,85.0,56.15,85.0,84.31,36.73,100.0,60.05,20.46,46.67,62.72,13.21,93.33,32.14,47.56,100.0,41.54,49.34 | |
| gpt-4-1106-vision-preview-t0.0--gpt-4-1106-vision-preview-t0.0,73.55,97.79,75.21,100.0,80.0,40.34,100.0,73.74,13.24,90.0,77.25,10.74,100.0,76.67,43.02,98.97,68.39,46.55 | |
| gpt-4o-2024-05-13-t0.0--gpt-4o-2024-05-13-t0.0,69.56,87.73,79.29,100.0,78.33,41.55,52.0,73.58,12.43,90.0,76.06,16.67,96.67,93.1,25.79,100.0,75.38,43.13 | |
| gpt-4o-2024-08-06-t0.0--gpt-4o-2024-08-06-t0.0,80.04,96.93,82.57,93.33,80.36,40.09,98.0,81.59,12.0,96.67,82.93,11.51,96.67,93.1,25.79,100.0,74.87,43.43 | |
| gpt-4o-mini-2024-07-18-t0.0--gpt-4o-mini-2024-07-18-t0.0,58.46,90.04,64.93,100.0,86.67,34.28,92.0,64.65,16.71,73.33,59.93,16.17,86.67,65.38,48.52,98.21,48.04,50.03 | |
| idefics-80b-instruct-t0.0--idefics-80b-instruct-t0.0,29.55,58.29,50.7,88.14,55.77,50.15,20.0,32.78,29.72,50.0,81.36,,33.33,50.0,52.7,100.0,33.59,47.29 | |
| idefics-9b-instruct-t0.0--idefics-9b-instruct-t0.0,12.29,38.0,32.34,100.0,33.33,47.54,0.0,,,0.0,,,0.0,,,90.0,31.34,46.45 | |
| internlm-xcomposer2d5-7b-t0.0--internlm-xcomposer2d5-7b-t0.0,16.95,20.18,83.98,98.33,77.97,41.8,0.0,,,0.0,,,0.0,,,2.56,90.0,31.62 | |