| o1-2024-12-17 |
78.84% |
63.95% |
57.03% |
61.22% |
87.79% |
75.45% |
55.21% |
78.38% |
75.49% |
87.54% |
85.13% |
98.16% |
74.91% |
| gpt-4o |
87.17% |
63.37% |
52.86% |
67.95% |
81.2% |
58.79% |
43.06% |
69.97% |
57.52% |
85.2% |
77.51% |
96.91% |
69.25% |
| qwen2.5-vl-72b-instruct |
79.59% |
64.53% |
43.38% |
62.82% |
85.27% |
59.09% |
28.91% |
81.68% |
68.2% |
80.45% |
85.66% |
97.96% |
68.29% |
| qwen-vl-max-2025-01-25 |
82.4% |
65.12% |
41.99% |
61.56% |
84.33% |
57.88% |
27.89% |
78.98% |
69.66% |
81.0% |
86.2% |
97.96% |
67.91% |
| gemini-1.5-pro |
82.58% |
69.19% |
59.56% |
67.95% |
73.26% |
56.21% |
30.96% |
64.26% |
73.62% |
81.0% |
80.56% |
98.09% |
67.8% |
| gemini-1.5-flash |
79.12% |
71.22% |
47.55% |
68.11% |
77.62% |
57.42% |
30.63% |
51.95% |
73.95% |
78.74% |
72.13% |
95.77% |
65.5% |
| gpt-4-turbo |
77.62% |
61.34% |
48.94% |
54.25% |
82.17% |
63.48% |
43.11% |
50.15% |
51.62% |
80.92% |
75.81% |
98.75% |
65.23% |
| grok-2-vision-1212 |
80.52% |
69.19% |
36.27% |
67.63% |
73.26% |
53.64% |
37.34% |
50.15% |
71.12% |
79.67% |
58.15% |
99.21% |
63.69% |
| llava-video-72b-qwen2_multi_frame |
81.27% |
59.88% |
39.46% |
53.37% |
74.81% |
59.85% |
31.84% |
59.46% |
65.29% |
80.3% |
76.79% |
92.17% |
63.09% |
| gemini-1.5-flash-8b |
76.12% |
64.83% |
58.01% |
54.09% |
75.97% |
50.76% |
31.28% |
66.67% |
60.92% |
75.08% |
59.86% |
95.26% |
62.91% |
| qwen2.5-vl-7b-instruct |
82.3% |
59.59% |
41.42% |
63.78% |
68.6% |
55.15% |
32.87% |
65.17% |
62.38% |
76.4% |
63.71% |
96.78% |
62.69% |
| claude-3-5-sonnet-20240620 |
78.28% |
56.4% |
32.43% |
64.74% |
76.74% |
58.18% |
34.17% |
46.55% |
64.56% |
72.98% |
69.0% |
97.96% |
61.92% |
| qwen-vl-plus-2025-01-25 |
78.93% |
58.72% |
39.71% |
63.35% |
67.86% |
54.85% |
31.47% |
64.86% |
62.14% |
75.93% |
60.66% |
96.91% |
61.69% |
| claude-3-7-sonnet-20250219 |
82.87% |
60.76% |
32.19% |
55.29% |
75.0% |
52.42% |
34.78% |
47.45% |
71.36% |
73.83% |
69.0% |
95.46% |
61.44% |
| deepseek-vl2-small |
82.68% |
58.43% |
39.22% |
61.3% |
75.0% |
59.85% |
32.77% |
51.95% |
66.99% |
77.65% |
48.03% |
92.57% |
61.36% |
| qwen2-vl-72b-instruct |
80.34% |
71.51% |
43.14% |
35.02% |
80.81% |
58.48% |
27.42% |
72.97% |
74.68% |
87.46% |
81.81% |
46.6% |
61.12% |
| internvl2-40b |
81.55% |
70.06% |
39.46% |
50.0% |
71.51% |
58.48% |
28.68% |
36.04% |
73.22% |
81.0% |
67.11% |
95.79% |
60.98% |
| ovis1.6-gemma2-9b |
85.39% |
60.17% |
47.55% |
51.68% |
69.19% |
55.76% |
26.91% |
54.35% |
71.6% |
77.49% |
65.77% |
87.7% |
60.92% |
| gpt-4o-mini |
74.25% |
70.06% |
38.89% |
53.93% |
64.73% |
59.39% |
41.01% |
42.04% |
58.66% |
76.01% |
69.35% |
96.12% |
60.89% |
| llava-video-7b-qwen2_multi_frame |
86.52% |
59.3% |
36.19% |
56.41% |
76.16% |
48.79% |
30.77% |
48.65% |
60.68% |
79.75% |
63.98% |
87.96% |
60.13% |
| mplug-owl3 |
76.5% |
59.01% |
39.95% |
48.96% |
62.21% |
44.09% |
33.8% |
71.47% |
70.63% |
77.1% |
60.22% |
92.89% |
59.92% |
| qwen2.5-vl-3b-instruct |
70.6% |
59.01% |
36.76% |
52.72% |
63.76% |
62.12% |
33.99% |
54.95% |
60.84% |
77.65% |
63.71% |
96.05% |
59.8% |
| internvl2-26b |
79.96% |
69.77% |
40.2% |
55.61% |
70.35% |
58.79% |
28.03% |
32.43% |
66.18% |
82.4% |
58.06% |
92.17% |
59.62% |
| gemma-3-27b-it |
78.18% |
50.0% |
35.05% |
49.86% |
60.47% |
51.52% |
35.01% |
53.75% |
69.74% |
77.55% |
70.53% |
97.52% |
59.38% |
| gemma-3-12b-it |
74.53% |
52.87% |
40.28% |
46.72% |
61.82% |
54.7% |
34.92% |
43.24% |
70.47% |
78.38% |
70.35% |
93.25% |
58.76% |
| xgen-mm-phi3-interleave-r-v1.5 |
79.87% |
68.31% |
46.16% |
48.72% |
77.33% |
56.36% |
33.29% |
47.75% |
61.17% |
74.07% |
50.54% |
72.87% |
58.72% |
| internvl-chat-v1-2 |
82.02% |
63.37% |
53.21% |
45.75% |
63.95% |
58.03% |
30.73% |
56.46% |
58.09% |
80.86% |
65.5% |
68.96% |
58.66% |
| llava-next-video-32b-qwen_multi_frame |
80.99% |
67.73% |
50.25% |
43.43% |
71.51% |
55.45% |
30.21% |
63.06% |
71.2% |
80.37% |
64.34% |
47.11% |
58.53% |
| aria |
79.78% |
56.4% |
35.95% |
37.98% |
71.9% |
56.52% |
33.43% |
58.56% |
60.28% |
73.36% |
56.72% |
91.91% |
58.4% |
| vila1.5-40b |
75.37% |
58.14% |
40.6% |
59.7% |
69.38% |
54.55% |
26.96% |
30.63% |
60.6% |
78.27% |
64.34% |
95.92% |
58.31% |
| internvl2-76b |
80.52% |
69.19% |
45.26% |
43.75% |
72.09% |
60.15% |
30.73% |
44.14% |
66.42% |
82.24% |
78.85% |
48.77% |
58.17% |
| deepseek-vl2 |
76.69% |
65.41% |
35.87% |
55.21% |
69.09% |
57.42% |
31.98% |
32.43% |
64.72% |
80.14% |
48.84% |
92.52% |
58.17% |
| qwen2-vl-7b-instruct |
83.99% |
63.95% |
40.77% |
42.15% |
70.35% |
61.82% |
29.8% |
60.66% |
75.08% |
75.78% |
64.78% |
49.76% |
57.93% |
| pixtral-12b-2409 |
72.28% |
55.52% |
44.28% |
49.84% |
66.86% |
51.97% |
25.19% |
58.26% |
59.06% |
70.87% |
58.42% |
96.91% |
57.78% |
| internvl2-8b-mpo |
81.09% |
69.77% |
38.97% |
36.7% |
69.96% |
47.27% |
25.14% |
52.55% |
57.85% |
73.36% |
61.38% |
89.34% |
56.83% |
| internvl2-8b-mpo-cot |
81.09% |
69.77% |
38.97% |
36.7% |
69.96% |
47.27% |
25.14% |
52.55% |
57.85% |
73.36% |
61.38% |
89.34% |
56.83% |
| ovis1.6-llama3.2-3b |
79.96% |
65.41% |
40.11% |
52.16% |
66.86% |
61.36% |
34.26% |
47.75% |
51.38% |
68.46% |
52.96% |
73.79% |
56.73% |
| claude-3-opus-20240229 |
79.87% |
48.26% |
40.36% |
44.71% |
76.55% |
49.55% |
42.5% |
53.15% |
60.92% |
56.31% |
66.94% |
65.35% |
56.73% |
| ovis1.5-gemma2-9b |
72.38% |
62.21% |
41.01% |
48.08% |
66.28% |
50.45% |
25.37% |
63.06% |
61.57% |
77.26% |
67.56% |
67.28% |
56.73% |
| ovis1.5-llama3-8b |
81.46% |
65.12% |
44.44% |
45.11% |
66.86% |
57.73% |
29.56% |
58.56% |
61.97% |
71.88% |
63.08% |
57.04% |
56.73% |
| llama-3-vila1.5-8b-fix |
75.66% |
59.01% |
42.4% |
40.14% |
72.09% |
60.61% |
29.56% |
39.64% |
59.06% |
74.53% |
55.56% |
82.7% |
56.48% |
| xgen-mm-phi3-dpo-r-v1.5 |
77.43% |
70.93% |
50.25% |
41.19% |
77.13% |
56.67% |
35.66% |
47.75% |
61.81% |
73.91% |
48.3% |
46.91% |
56.32% |
| llava_next_72b |
79.21% |
65.12% |
61.03% |
47.84% |
68.6% |
52.27% |
30.12% |
38.44% |
60.11% |
77.65% |
70.07% |
46.21% |
56.25% |
| internvl2-8b |
69.38% |
67.44% |
42.65% |
39.26% |
68.6% |
53.18% |
27.09% |
36.94% |
60.19% |
74.77% |
69.53% |
84.61% |
56.21% |
| internvl-chat-v1-2-plus |
82.3% |
66.86% |
46.15% |
44.36% |
65.99% |
57.88% |
31.01% |
29.13% |
61.97% |
78.6% |
62.1% |
67.88% |
56.15% |
| minicpm-v-2_6 |
75.0% |
77.33% |
41.67% |
47.44% |
68.02% |
51.36% |
34.22% |
54.05% |
60.76% |
74.77% |
55.73% |
50.0% |
56.0% |
| llama-3-vila1.5-8b |
74.25% |
59.88% |
58.09% |
40.06% |
57.56% |
58.94% |
30.96% |
38.74% |
55.66% |
68.22% |
56.54% |
89.8% |
55.82% |
| llava_next_mistral_7b |
76.5% |
65.7% |
44.36% |
47.76% |
66.28% |
42.27% |
40.83% |
64.86% |
65.7% |
71.03% |
51.61% |
45.11% |
55.78% |
| minicpm-llama3-v-2_5 |
74.91% |
69.77% |
54.17% |
33.25% |
73.26% |
50.0% |
28.68% |
64.86% |
58.17% |
71.65% |
63.35% |
47.59% |
55.76% |
| internvl2-4b |
76.87% |
59.88% |
37.75% |
46.88% |
72.67% |
55.3% |
30.63% |
23.42% |
63.83% |
65.97% |
69.89% |
78.22% |
55.63% |
| mini-internvl-chat-4b-v1-5 |
73.03% |
56.4% |
51.47% |
46.55% |
65.89% |
60.0% |
31.66% |
48.65% |
69.82% |
64.64% |
64.61% |
48.38% |
55.25% |
| mmalaya2 |
77.81% |
66.86% |
48.28% |
42.47% |
72.67% |
59.39% |
28.12% |
28.83% |
65.94% |
81.07% |
64.25% |
46.86% |
55.19% |
| llava_next_110b |
73.03% |
58.43% |
45.1% |
41.59% |
65.41% |
57.27% |
29.89% |
43.24% |
65.94% |
82.87% |
66.67% |
49.32% |
54.88% |
| internvl-chat-v1-1 |
72.38% |
68.02% |
46.79% |
37.83% |
65.7% |
61.06% |
32.5% |
38.74% |
56.63% |
74.85% |
54.84% |
65.12% |
54.81% |
| internvl-chat-v1-5 |
77.81% |
66.86% |
46.32% |
41.83% |
72.09% |
58.33% |
28.72% |
26.13% |
65.05% |
79.44% |
60.13% |
51.05% |
54.6% |
| llava-onevision-qwen2-72b-ov-hf |
81.84% |
57.85% |
40.36% |
39.18% |
64.63% |
51.82% |
29.05% |
48.35% |
63.27% |
78.04% |
66.31% |
54.69% |
54.46% |
| llava-onevision-qwen2-72b-si-hf |
79.12% |
54.07% |
43.14% |
38.62% |
65.7% |
51.21% |
33.47% |
51.05% |
58.9% |
82.4% |
67.47% |
45.83% |
54.43% |
| llava-onevision-qwen2-72b-ov-chat-hf |
79.4% |
57.27% |
32.76% |
41.75% |
66.67% |
50.0% |
25.79% |
52.85% |
63.67% |
81.93% |
64.61% |
54.96% |
54.19% |
| vila1.5-13b |
63.86% |
56.98% |
37.75% |
41.11% |
62.21% |
60.76% |
32.31% |
30.63% |
58.17% |
74.14% |
54.66% |
87.92% |
54.11% |
| phi-4-multimodal-instruct |
78.57% |
52.59% |
31.6% |
36.02% |
63.57% |
53.64% |
25.75% |
51.95% |
60.42% |
67.29% |
65.77% |
75.46% |
53.55% |
| mantis-8b-siglip-llama3 |
72.19% |
54.36% |
47.3% |
37.42% |
62.79% |
52.27% |
40.46% |
15.02% |
55.58% |
72.74% |
55.47% |
73.22% |
52.63% |
| gemma-3-4b-it |
65.82% |
47.13% |
58.66% |
37.3% |
44.19% |
55.15% |
32.12% |
50.45% |
53.4% |
63.44% |
58.07% |
83.85% |
52.51% |
| claude-3-sonnet-20240229 |
71.16% |
50.0% |
34.4% |
42.55% |
62.69% |
54.24% |
42.88% |
36.34% |
52.43% |
49.69% |
57.17% |
79.61% |
52.51% |
| xinyuan-vl-2b-instruct |
72.19% |
72.38% |
37.83% |
37.02% |
65.7% |
55.61% |
30.73% |
60.66% |
56.23% |
64.8% |
45.79% |
47.52% |
52.42% |
| mantis-8b-idefics2 |
77.72% |
73.26% |
45.34% |
36.06% |
68.02% |
46.82% |
29.61% |
36.34% |
50.24% |
73.6% |
55.82% |
52.68% |
52.25% |
| llava-llama-3-8b |
85.11% |
56.69% |
44.12% |
38.14% |
62.79% |
48.94% |
31.56% |
61.26% |
53.48% |
65.5% |
53.76% |
43.51% |
52.19% |
| phi-3.5-vision |
76.78% |
52.03% |
37.75% |
34.21% |
68.02% |
60.61% |
34.78% |
39.34% |
54.61% |
63.94% |
56.45% |
56.86% |
52.08% |
| internlm-xcomposer2d5-7b |
79.78% |
62.5% |
53.1% |
34.21% |
48.84% |
40.76% |
34.87% |
51.95% |
49.76% |
74.53% |
56.81% |
58.44% |
51.87% |
| claude-3-haiku-20240307 |
72.28% |
50.87% |
33.74% |
42.39% |
65.5% |
58.18% |
41.71% |
38.44% |
46.76% |
51.09% |
55.02% |
67.61% |
51.75% |
| qwen2-vl-2b-instruct |
72.38% |
69.19% |
34.23% |
38.54% |
70.93% |
60.45% |
30.63% |
38.14% |
46.28% |
66.9% |
54.93% |
50.68% |
51.66% |
| llava_next_interleave_7b_dpo |
72.38% |
59.01% |
41.58% |
39.1% |
58.72% |
50.15% |
30.59% |
45.05% |
58.9% |
71.03% |
49.91% |
59.45% |
51.58% |
| mantis-8b-clip-llama3 |
67.32% |
50.29% |
44.53% |
34.05% |
58.14% |
55.45% |
35.52% |
29.13% |
51.94% |
70.4% |
50.0% |
79.21% |
51.41% |
| vintern-3b-beta |
60.12% |
68.97% |
38.89% |
34.32% |
59.98% |
53.94% |
37.85% |
31.23% |
60.16% |
63.47% |
52.42% |
66.73% |
51.4% |
| h2ovl-mississippi-1b |
63.76% |
41.57% |
43.95% |
46.15% |
74.03% |
54.7% |
38.22% |
61.26% |
45.87% |
54.44% |
45.97% |
41.62% |
51.2% |
| idefics3-8b-llama3 |
74.06% |
58.43% |
27.7% |
35.5% |
68.6% |
65.3% |
29.42% |
45.05% |
47.65% |
65.26% |
59.05% |
52.06% |
51.18% |
| llava-onevision-qwen2-7b-si-hf |
71.72% |
55.52% |
41.91% |
42.39% |
62.21% |
51.52% |
31.52% |
42.64% |
54.29% |
77.02% |
49.01% |
44.01% |
50.84% |
| llava-onevision-qwen2-7b-ov-hf |
64.14% |
54.65% |
43.3% |
36.3% |
67.15% |
47.42% |
31.47% |
51.65% |
55.18% |
70.09% |
56.9% |
43.0% |
50.82% |
| internvl2-2b |
62.73% |
61.92% |
36.76% |
45.75% |
57.27% |
47.42% |
42.46% |
41.44% |
43.45% |
63.63% |
45.97% |
61.56% |
50.47% |
| llava-onevision-qwen2-7b-ov-chat-hf |
73.6% |
53.2% |
31.37% |
33.89% |
59.3% |
47.12% |
30.87% |
51.95% |
59.39% |
77.34% |
56.18% |
47.5% |
50.37% |
| llava_next_interleave_7b |
68.63% |
60.47% |
35.05% |
41.43% |
59.3% |
52.42% |
32.64% |
27.03% |
59.95% |
70.48% |
48.03% |
58.36% |
50.06% |
| deepseek-vl2-tiny |
75.09% |
63.37% |
46.24% |
44.95% |
71.51% |
59.55% |
34.22% |
31.53% |
37.62% |
58.1% |
43.82% |
41.18% |
50.05% |
| hunyuan-vision |
79.12% |
60.76% |
26.72% |
30.05% |
68.22% |
54.39% |
26.49% |
36.94% |
51.78% |
69.39% |
53.67% |
55.92% |
49.76% |
| h2ovl-mississippi-2b |
72.0% |
55.52% |
45.67% |
44.15% |
45.35% |
48.64% |
27.51% |
70.27% |
56.07% |
63.71% |
43.73% |
46.89% |
49.67% |
| llama-3-longvila-8b-256frames |
72.0% |
54.36% |
54.41% |
34.54% |
51.94% |
45.91% |
23.56% |
61.86% |
51.29% |
60.9% |
52.24% |
51.07% |
49.2% |
| internlm-xcomposer2-7b |
75.56% |
56.4% |
36.93% |
35.1% |
67.25% |
52.12% |
37.8% |
18.32% |
41.34% |
63.63% |
48.92% |
59.8% |
49.05% |
| llama-3-longvila-8b-1024frames |
69.29% |
50.29% |
55.88% |
35.42% |
54.65% |
42.42% |
25.98% |
65.17% |
51.38% |
59.27% |
47.85% |
48.03% |
48.92% |
| idefics_80b_instruct |
65.82% |
47.38% |
35.7% |
44.31% |
59.59% |
59.85% |
44.37% |
30.03% |
36.97% |
60.67% |
46.95% |
54.17% |
48.89% |
| llava-video-7b-qwen2-video-only_multi_frame |
82.49% |
55.52% |
34.56% |
43.43% |
52.33% |
55.91% |
34.82% |
36.04% |
34.87% |
66.36% |
56.81% |
47.92% |
48.72% |
| qwen_chat |
65.64% |
54.65% |
31.78% |
37.18% |
60.17% |
53.94% |
41.67% |
44.74% |
46.04% |
67.52% |
42.56% |
41.78% |
48.62% |
| llama-3-longvila-8b-128frames |
71.63% |
52.62% |
50.98% |
39.98% |
61.82% |
50.0% |
33.19% |
18.62% |
51.29% |
60.83% |
50.18% |
51.01% |
48.53% |
| vila1.5-3b |
73.03% |
47.97% |
48.28% |
41.03% |
57.85% |
52.12% |
37.15% |
26.73% |
43.85% |
66.04% |
47.22% |
45.94% |
48.28% |
| mini-internvl-chat-2b-v1-5 |
74.44% |
49.71% |
39.79% |
41.59% |
48.84% |
50.45% |
37.99% |
57.06% |
51.54% |
53.04% |
42.83% |
42.59% |
48.08% |
| vila1.5-3b-s2 |
62.73% |
53.49% |
37.09% |
40.22% |
59.01% |
55.0% |
41.11% |
30.03% |
40.78% |
68.61% |
41.58% |
47.92% |
47.94% |
| llama-3-longvila-8b-512frames |
69.66% |
42.44% |
54.17% |
35.02% |
44.48% |
41.06% |
22.77% |
67.57% |
56.72% |
59.35% |
51.16% |
53.6% |
47.83% |
| vintern-1b-v2 |
58.15% |
53.78% |
34.23% |
44.55% |
59.88% |
54.39% |
43.62% |
29.73% |
40.78% |
52.1% |
43.46% |
40.48% |
46.4% |
| eagle-x4-13b-plus |
79.59% |
55.23% |
5.15% |
32.13% |
55.23% |
28.03% |
25.0% |
75.98% |
58.58% |
73.83% |
52.24% |
35.09% |
46.16% |
| eagle-x5-34b-chat |
80.34% |
48.26% |
4.9% |
27.0% |
56.78% |
30.45% |
24.72% |
61.26% |
68.04% |
78.12% |
58.06% |
38.03% |
46.16% |
| deepseek-vl-7b-chat |
81.84% |
50.87% |
4.41% |
34.05% |
57.56% |
28.33% |
31.05% |
30.03% |
52.67% |
66.51% |
51.88% |
74.21% |
46.01% |
| internvl2-1b |
62.92% |
55.23% |
35.95% |
35.9% |
56.4% |
57.27% |
43.62% |
22.82% |
42.15% |
60.51% |
44.53% |
37.72% |
45.99% |
| smolvlm |
72.57% |
59.59% |
22.39% |
31.57% |
67.05% |
51.97% |
33.85% |
52.85% |
39.24% |
47.59% |
44.71% |
33.0% |
45.77% |
| emu2-chat |
64.61% |
54.94% |
43.79% |
39.58% |
57.27% |
45.76% |
33.24% |
24.92% |
52.99% |
51.64% |
44.71% |
43.66% |
45.67% |
| eagle-x5-13b-chat |
82.49% |
54.36% |
1.23% |
30.05% |
60.47% |
28.79% |
25.23% |
64.56% |
57.2% |
73.13% |
49.73% |
34.17% |
45.23% |
| janus-pro-7b |
78.28% |
39.24% |
3.43% |
40.46% |
59.3% |
28.64% |
33.57% |
45.05% |
47.09% |
59.74% |
48.39% |
48.64% |
43.93% |
| eagle-x4-8b-plus |
65.64% |
50.58% |
7.11% |
29.49% |
49.61% |
30.76% |
25.19% |
74.77% |
56.23% |
65.97% |
39.25% |
42.13% |
43.34% |
| llava-onevision-qwen2-0.5b-ov-hf |
60.11% |
47.67% |
27.12% |
36.46% |
56.59% |
43.33% |
38.04% |
38.44% |
34.87% |
53.04% |
38.17% |
37.96% |
42.65% |
| eagle-x5-34b-plus |
67.7% |
52.62% |
7.11% |
26.84% |
47.29% |
31.21% |
22.02% |
29.73% |
70.95% |
78.5% |
53.14% |
44.82% |
42.39% |
| llava-onevision-qwen2-0.5b-si-hf |
52.15% |
39.53% |
32.68% |
28.37% |
48.64% |
51.52% |
38.69% |
49.55% |
33.66% |
51.56% |
42.47% |
38.14% |
42.08% |
| openflamingo-9b-vitl-mpt7b |
44.29% |
32.27% |
29.74% |
36.86% |
57.07% |
58.64% |
44.13% |
56.46% |
35.44% |
31.15% |
40.68% |
27.11% |
41.96% |
| mantis-8b-fuyu |
58.05% |
48.84% |
39.22% |
35.9% |
52.81% |
44.09% |
38.73% |
31.53% |
36.89% |
42.52% |
41.31% |
32.63% |
41.7% |
| deepseek-vl-1.3b-chat |
68.26% |
42.44% |
13.89% |
41.75% |
53.49% |
37.12% |
35.94% |
28.53% |
35.19% |
55.3% |
42.29% |
40.75% |
41.1% |
| qwen2.5-omni-7b |
54.78% |
37.5% |
32.52% |
31.33% |
62.31% |
54.24% |
45.62% |
39.94% |
30.91% |
28.66% |
40.41% |
22.61% |
40.92% |
| eagle-x5-13b |
58.33% |
56.1% |
6.13% |
23.08% |
45.93% |
30.76% |
31.24% |
29.43% |
55.83% |
69.47% |
47.49% |
35.22% |
39.57% |
| idefics_9b_instruct |
48.97% |
29.07% |
26.8% |
38.38% |
53.59% |
45.15% |
34.03% |
29.73% |
38.03% |
38.71% |
40.32% |
44.96% |
39.4% |
| eagle-x5-7b |
59.64% |
53.2% |
6.62% |
23.0% |
45.83% |
30.3% |
22.95% |
28.83% |
64.89% |
71.18% |
42.2% |
36.01% |
38.84% |
| janus-pro-1b |
69.57% |
34.01% |
5.15% |
40.63% |
44.77% |
33.18% |
40.6% |
18.62% |
50.0% |
49.22% |
39.25% |
35.9% |
38.34% |
| janusflow-1.3b |
65.17% |
41.57% |
4.66% |
32.13% |
41.28% |
31.82% |
41.34% |
35.14% |
44.58% |
49.69% |
35.57% |
38.9% |
38.25% |
| janus-1.3b |
54.31% |
30.81% |
9.31% |
41.59% |
42.54% |
20.3% |
36.55% |
54.65% |
40.94% |
45.72% |
40.41% |
31.73% |
37.41% |
| kosmos2 |
49.25% |
17.44% |
35.95% |
27.8% |
40.5% |
41.06% |
32.59% |
66.97% |
23.95% |
24.84% |
36.11% |
22.15% |
34.93% |
| llava-next-video-7b-dpo_multi_frame |
26.97% |
1.45% |
3.92% |
4.57% |
42.44% |
21.82% |
16.9% |
53.15% |
19.42% |
57.4% |
36.38% |
16.58% |
25.39% |
| llava-next-video-7b_multi_frame |
21.07% |
1.16% |
3.92% |
2.16% |
37.79% |
18.18% |
18.72% |
54.05% |
13.92% |
56.39% |
37.81% |
16.54% |
23.87% |