| { | |
| "llama3-llava-next-8b-hf-2412": { | |
| "VQA": 0.4186046511627907, | |
| "QA": 0.1896551724137931, | |
| "Reason": 0.23076923076923078, | |
| "VQA_Reasoning": 0.25 | |
| }, | |
| "gpt-4o-2412": { | |
| "QA": 0.9655172413793104, | |
| "Reason": 0.7692307692307693, | |
| "VQA_Reasoning": 0.85, | |
| "VQA": 0.7674418604651163 | |
| }, | |
| "gpt-4o-mini-2412": { | |
| "QA": 0.7586206896551724, | |
| "Reason": 0.5384615384615384, | |
| "VQA_Reasoning": 0.6, | |
| "VQA": 0.627906976744186 | |
| }, | |
| "fuyu-8b-2412": { | |
| "Reason": 0.0, | |
| "QA": 0.017241379310344827 | |
| }, | |
| "llava-1.5-13b-hf-2412": { | |
| "Reason": 0.0, | |
| "VQA": 0.3023255813953488, | |
| "QA": 0.0, | |
| "VQA_Reasoning": 0.65 | |
| }, | |
| "llava-1.5-7b-hf-2412": { | |
| "VQA_Reasoning": 0.45, | |
| "VQA": 0.32558139534883723, | |
| "Reason": 0.0, | |
| "QA": 0.0 | |
| }, | |
| "llava-v1.6-mistral-7b-hf-2412": { | |
| "VQA": 0.37209302325581395, | |
| "VQA_Reasoning": 0.55, | |
| "Reason": 0.15384615384615385, | |
| "QA": 0.15517241379310345 | |
| }, | |
| "llava-v1.6-vicuna-13b-hf-2412": { | |
| "VQA_Reasoning": 0.35, | |
| "VQA": 0.4186046511627907, | |
| "QA": 0.1724137931034483, | |
| "Reason": 0.15384615384615385 | |
| }, | |
| "llava-v1.6-vicuna-7b-hf-2412": { | |
| "Reason": 0.15384615384615385, | |
| "VQA": 0.23255813953488372, | |
| "VQA_Reasoning": 0.2, | |
| "QA": 0.06896551724137931 | |
| }, | |
| "MiniCPM-V-2_6-2412": { | |
| "Reason": 0.15384615384615385, | |
| "VQA": 0.5116279069767442, | |
| "VQA_Reasoning": 0.4, | |
| "QA": 0.15517241379310345 | |
| }, | |
| "llava-gemma-2b-2412": { | |
| "Reason": 0.0, | |
| "VQA": 0.3023255813953488, | |
| "VQA_Reasoning": 0.2, | |
| "QA": 0.034482758620689655 | |
| }, | |
| "molmo-7b-d-0924-2412": { | |
| "VQA": 0.5813953488372093, | |
| "VQA_Reasoning": 0.15, | |
| "QA": 0.1206896551724138, | |
| "Reason": 0.15384615384615385, | |
| "Gui_Grounding": { | |
| "100": 0.65, | |
| "20": 0.19, | |
| "50": 0.46, | |
| "200": 0.84 | |
| }, | |
| "Embodied_Grounding": { | |
| "100": 0.30916030534351147, | |
| "20": 0.03435114503816794, | |
| "50": 0.16412213740458015, | |
| "200": 0.5 | |
| } | |
| }, | |
| "molmo-72b-0924-2412": { | |
| "Reason": 0.46153846153846156, | |
| "VQA_Reasoning": 0.55, | |
| "QA": 0.3620689655172414, | |
| "VQA": 0.5581395348837209 | |
| }, | |
| "mc-sft-llava_next_8b-mcqa_v3_12_25_277k-2411": { | |
| "Reason": 0.23076923076923078, | |
| "VQA_Reasoning": 0.25, | |
| "QA": 0.6724137931034483, | |
| "VQA": 0.11627906976744186 | |
| }, | |
| "qwen2-vl-7b-instruct-2412": { | |
| "Gui_Grounding": { | |
| "100": 0.41, | |
| "20": 0.08, | |
| "200": 0.76, | |
| "50": 0.21 | |
| }, | |
| "Embodied_Grounding": { | |
| "100": 0.40458015267175573, | |
| "20": 0.13740458015267176, | |
| "200": 0.5572519083969466, | |
| "50": 0.25190839694656486 | |
| }, | |
| "QA": 0.06896551724137931, | |
| "VQA": 0.4186046511627907, | |
| "VQA_Reasoning": 0.375, | |
| "Reason": 0.15384615384615385 | |
| }, | |
| "llama-3.2-11b-vision-instruct-2412": { | |
| "VQA": 0.4418604651162791, | |
| "VQA_Reasoning": 0.25, | |
| "Reason": 0.23076923076923078, | |
| "QA": 0.20689655172413793 | |
| }, | |
| "qwen2-vl-72b-instruct-2412": { | |
| "Gui_Grounding": { | |
| "100": 0.0, | |
| "20": 0.0, | |
| "200": 0.0, | |
| "50": 0.0 | |
| }, | |
| "Embodied_Grounding": { | |
| "100": 0.35877862595419846, | |
| "20": 0.09541984732824428, | |
| "200": 0.5038167938931297, | |
| "50": 0.22137404580152673 | |
| } | |
| }, | |
| "mc-sft-llava_next_8b-mcqa_v3_12_25_277k-2412": { | |
| "QA": 0.6724137931034483, | |
| "Reason": 0.38461538461538464, | |
| "VQA": 0.20930232558139536, | |
| "VQA_Reasoning": 0.45 | |
| }, | |
| "mc-vsft-llama3_llava_next_8b-mcvqa_v4_11_21_80k-2412": { | |
| "QA": 0.603448275862069, | |
| "Reason": 0.3076923076923077, | |
| "VQA": 0.5581395348837209, | |
| "VQA_Reasoning": 0.55 | |
| }, | |
| "mc-vsft-llava_v1.6_vicuna_13b-mcvqa_v4_11_21_80k-2412": { | |
| "QA": 0.6206896551724138, | |
| "Reason": 0.5384615384615384, | |
| "VQA": 0.7441860465116279, | |
| "VQA_Reasoning": 0.7 | |
| }, | |
| "mc-sft-qwen2_vl_7b-mcqa_v3_12_25_277k-2412": { | |
| "QA": 0.6551724137931034, | |
| "VQA_Reasoning": 0.45, | |
| "Reason": 0.38461538461538464, | |
| "VQA": 0.46511627906976744 | |
| }, | |
| "mc-vsft-qwen2_vl_7b-2412": { | |
| "VQA": 0.6511627906976745, | |
| "Reason": 0.23076923076923078, | |
| "QA": 0.6206896551724138, | |
| "VQA_Reasoning": 0.75 | |
| }, | |
| "mc-vsft-qwen2_vl_2b-2412": { | |
| "Reason": 0.15384615384615385, | |
| "VQA_Reasoning": 0.7, | |
| "VQA": 0.5813953488372093, | |
| "QA": 0.1724137931034483 | |
| }, | |
| "mc-point-qwen2_vl_7b-2502": { | |
| "Gui_Grounding": { | |
| "100": 0.69, | |
| "20": 0.4, | |
| "200": 0.95, | |
| "50": 0.51 | |
| }, | |
| "Embodied_Grounding": { | |
| "100": 0.6603053435114504, | |
| "20": 0.22137404580152673, | |
| "200": 0.7862595419847328, | |
| "50": 0.4732824427480916 | |
| }, | |
| "Reason": 0.38461538461538464, | |
| "QA": 0.6724137931034483, | |
| "VQA": 0.5116279069767442, | |
| "VQA_Reasoning": 0.475 | |
| }, | |
| "mc-bbox-qwen2_vl_7b-2502": { | |
| "Gui_Grounding": { | |
| "100": 0.57, | |
| "20": 0.38, | |
| "200": 0.74, | |
| "50": 0.47 | |
| }, | |
| "Embodied_Grounding": { | |
| "100": 0.0916030534351145, | |
| "20": 0.015267175572519083, | |
| "200": 0.15648854961832062, | |
| "50": 0.03435114503816794 | |
| } | |
| }, | |
| "mc-base-qwen2_vl_7b-2502": { | |
| "Gui_Grounding": { | |
| "100": 0.74, | |
| "20": 0.38, | |
| "200": 0.93, | |
| "50": 0.56 | |
| }, | |
| "Embodied_Grounding": { | |
| "100": 0.648854961832061, | |
| "20": 0.2099236641221374, | |
| "200": 0.7786259541984732, | |
| "50": 0.4618320610687023 | |
| }, | |
| "Reason": 0.38461538461538464, | |
| "QA": 0.6982758620689655, | |
| "VQA": 0.5348837209302325, | |
| "VQA_Reasoning": 0.55 | |
| }, | |
| "mc-base-qwen2_vl_7b-v2-ckpt2400-2502": { | |
| "Gui_Grounding": { | |
| "100": 0.92, | |
| "20": 0.79, | |
| "200": 0.99, | |
| "50": 0.88 | |
| }, | |
| "Embodied_Grounding": { | |
| "100": 0.6068702290076335, | |
| "20": 0.2099236641221374, | |
| "200": 0.7824427480916031, | |
| "50": 0.41603053435114506 | |
| }, | |
| "QA": 0.7068965517241379, | |
| "VQA": 0.7674418604651163, | |
| "VQA_Reasoning": 0.55, | |
| "Reason": 0.46153846153846156 | |
| }, | |
| "mc-base-qwen2_vl_7b-v2-ckpt3200-2502": { | |
| "Gui_Grounding": { | |
| "100": 0.93, | |
| "20": 0.84, | |
| "200": 0.99, | |
| "50": 0.9 | |
| }, | |
| "Embodied_Grounding": { | |
| "100": 0.6259541984732825, | |
| "20": 0.24427480916030533, | |
| "200": 0.7748091603053435, | |
| "50": 0.46946564885496184 | |
| }, | |
| "QA": 0.6810344827586207, | |
| "VQA": 0.6976744186046512, | |
| "VQA_Reasoning": 0.55, | |
| "Reason": 0.38461538461538464 | |
| }, | |
| "mc-base-qwen2_vl_2b-v2-ckpt1600-2502": { | |
| "Gui_Grounding": { | |
| "100": 0.54, | |
| "20": 0.32, | |
| "200": 0.93, | |
| "50": 0.38 | |
| }, | |
| "Embodied_Grounding": { | |
| "100": 0.5038167938931297, | |
| "20": 0.08015267175572519, | |
| "200": 0.7175572519083969, | |
| "50": 0.2748091603053435 | |
| }, | |
| "QA": 0.3103448275862069, | |
| "VQA": 0.5116279069767442, | |
| "VQA_Reasoning": 0.4, | |
| "Reason": 0.38461538461538464 | |
| }, | |
| "mc-base-qwen2_vl_2b-v2-ckpt4000-2502": { | |
| "Gui_Grounding": { | |
| "100": 0.59, | |
| "20": 0.39, | |
| "200": 0.94, | |
| "50": 0.45 | |
| }, | |
| "Embodied_Grounding": { | |
| "100": 0.5305343511450382, | |
| "20": 0.16793893129770993, | |
| "200": 0.7557251908396947, | |
| "50": 0.3473282442748092 | |
| } | |
| }, | |
| "mc-base-llava_next_vicuna_13b-ckpt4000-2502": { | |
| "Gui_Grounding": { | |
| "100": 0.74, | |
| "20": 0.6, | |
| "200": 0.99, | |
| "50": 0.68 | |
| }, | |
| "Embodied_Grounding": { | |
| "100": 0.6259541984732825, | |
| "20": 0.15267175572519084, | |
| "200": 0.7748091603053435, | |
| "50": 0.4122137404580153 | |
| }, | |
| "QA": 0.603448275862069, | |
| "VQA": 0.4883720930232558, | |
| "VQA_Reasoning": 0.4, | |
| "Reason": 0.46153846153846156 | |
| }, | |
| "mc-reason-qwen2_vl_7b-ckpt2400-2502": { | |
| "Gui_Grounding": { | |
| "100": 0.0, | |
| "20": 0.0, | |
| "200": 0.0, | |
| "50": 0.0 | |
| }, | |
| "Embodied_Grounding": { | |
| "100": 0.0, | |
| "20": 0.0, | |
| "200": 0.003816793893129771, | |
| "50": 0.0 | |
| }, | |
| "QA": 0.6551724137931034, | |
| "VQA": 0.6046511627906976, | |
| "VQA_Reasoning": 0.325, | |
| "Reason": 0.5229885057471264 | |
| } | |
| } |