Leaderboard
Search and view results for each task.
mc-vsft-llava_v1.6_vicuna_13b-mcvqa_v4_11_21_80k-2412 | 76.74 |
mc-vsft-llava_v1.6_vicuna_13b-mcvqa_v4_11_21_80k-2412 | 96.55 |
gpt-4o-2412 | 96.55 |
gpt-4o-mini-2412 | 75.86 |
mc-base-qwen2_vl_7b-v2-ckpt2400-2502 | 70.69 |
mc-base-qwen2_vl_7b-2502 | 69.83 |
mc-base-qwen2_vl_7b-v2-ckpt3200-2502 | 68.1 |
mc-sft-llava_next_8b-mcqa_v3_12_25_277k-2411 | 67.24 |
mc-point-qwen2_vl_7b-2502 | 67.24 |
mc-sft-llava_next_8b-mcqa_v3_12_25_277k-2412 | 67.24 |
mc-sft-qwen2_vl_7b-mcqa_v3_12_25_277k-2412 | 65.52 |
mc-reason-qwen2_vl_7b-ckpt2400-2502 | 65.52 |
mc-vsft-llava_v1.6_vicuna_13b-mcvqa_v4_11_21_80k-2412 | 62.07 |
mc-vsft-qwen2_vl_7b-2412 | 62.07 |
mc-vsft-llama3_llava_next_8b-mcvqa_v4_11_21_80k-2412 | 60.34 |
mc-base-llava_next_vicuna_13b-ckpt4000-2502 | 60.34 |
molmo-72b-0924-2412 | 36.21 |
mc-base-qwen2_vl_2b-v2-ckpt1600-2502 | 31.03 |
llama-3.2-11b-vision-instruct-2412 | 20.69 |
llama3-llava-next-8b-hf-2412 | 18.97 |
llava-v1.6-vicuna-13b-hf-2412 | 17.24 |
mc-vsft-qwen2_vl_2b-2412 | 17.24 |
MiniCPM-V-2_6-2412 | 15.52 |
llava-v1.6-mistral-7b-hf-2412 | 15.52 |
molmo-7b-d-0924-2412 | 12.07 |
llava-v1.6-vicuna-7b-hf-2412 | 6.9 |
qwen2-vl-7b-instruct-2412 | 6.9 |
llava-gemma-2b-2412 | 3.45 |
fuyu-8b-2412 | 1.72 |
llava-1.5-7b-hf-2412 | 0 |
llava-1.5-13b-hf-2412 | 0 |
qwen2-vl-72b-instruct-2412 | null |
mc-bbox-qwen2_vl_7b-2502 | null |
mc-base-qwen2_vl_2b-v2-ckpt4000-2502 | null |
mc-vsft-llava_v1.6_vicuna_13b-mcvqa_v4_11_21_80k-2412 | 47.5 |
gpt-4o-2412 | 85 |
mc-vsft-qwen2_vl_7b-2412 | 75 |
mc-vsft-llava_v1.6_vicuna_13b-mcvqa_v4_11_21_80k-2412 | 70 |
mc-vsft-qwen2_vl_2b-2412 | 70 |
llava-1.5-13b-hf-2412 | 65 |
gpt-4o-mini-2412 | 60 |
molmo-72b-0924-2412 | 55 |
mc-base-qwen2_vl_7b-v2-ckpt3200-2502 | 55 |
mc-vsft-llama3_llava_next_8b-mcvqa_v4_11_21_80k-2412 | 55 |
mc-base-qwen2_vl_7b-2502 | 55 |
mc-base-qwen2_vl_7b-v2-ckpt2400-2502 | 55 |
llava-v1.6-mistral-7b-hf-2412 | 55 |
mc-point-qwen2_vl_7b-2502 | 47.5 |
mc-sft-llava_next_8b-mcqa_v3_12_25_277k-2412 | 45 |
llava-1.5-7b-hf-2412 | 45 |
mc-sft-qwen2_vl_7b-mcqa_v3_12_25_277k-2412 | 45 |
mc-base-llava_next_vicuna_13b-ckpt4000-2502 | 40 |
MiniCPM-V-2_6-2412 | 40 |
mc-base-qwen2_vl_2b-v2-ckpt1600-2502 | 40 |
qwen2-vl-7b-instruct-2412 | 37.5 |
llava-v1.6-vicuna-13b-hf-2412 | 35 |
mc-reason-qwen2_vl_7b-ckpt2400-2502 | 32.5 |
mc-sft-llava_next_8b-mcqa_v3_12_25_277k-2411 | 25 |
llama3-llava-next-8b-hf-2412 | 25 |
llama-3.2-11b-vision-instruct-2412 | 25 |
llava-v1.6-vicuna-7b-hf-2412 | 20 |
llava-gemma-2b-2412 | 20 |
molmo-7b-d-0924-2412 | 15 |
fuyu-8b-2412 | null |
qwen2-vl-72b-instruct-2412 | null |
mc-bbox-qwen2_vl_7b-2502 | null |
mc-base-qwen2_vl_2b-v2-ckpt4000-2502 | null |
mc-vsft-llava_v1.6_vicuna_13b-mcvqa_v4_11_21_80k-2412 | 76.92 |
gpt-4o-2412 | 76.92 |
gpt-4o-mini-2412 | 53.85 |
mc-vsft-llava_v1.6_vicuna_13b-mcvqa_v4_11_21_80k-2412 | 53.85 |
mc-reason-qwen2_vl_7b-ckpt2400-2502 | 52.3 |
molmo-72b-0924-2412 | 46.15 |
mc-base-llava_next_vicuna_13b-ckpt4000-2502 | 46.15 |
mc-base-qwen2_vl_7b-v2-ckpt2400-2502 | 46.15 |
mc-sft-llava_next_8b-mcqa_v3_12_25_277k-2412 | 38.46 |
mc-point-qwen2_vl_7b-2502 | 38.46 |
mc-base-qwen2_vl_2b-v2-ckpt1600-2502 | 38.46 |
mc-sft-qwen2_vl_7b-mcqa_v3_12_25_277k-2412 | 38.46 |
mc-base-qwen2_vl_7b-2502 | 38.46 |
mc-base-qwen2_vl_7b-v2-ckpt3200-2502 | 38.46 |
mc-vsft-llama3_llava_next_8b-mcvqa_v4_11_21_80k-2412 | 30.77 |
llama3-llava-next-8b-hf-2412 | 23.08 |
llama-3.2-11b-vision-instruct-2412 | 23.08 |
mc-sft-llava_next_8b-mcqa_v3_12_25_277k-2411 | 23.08 |
mc-vsft-qwen2_vl_7b-2412 | 23.08 |
llava-v1.6-mistral-7b-hf-2412 | 15.38 |
MiniCPM-V-2_6-2412 | 15.38 |
molmo-7b-d-0924-2412 | 15.38 |
llava-v1.6-vicuna-13b-hf-2412 | 15.38 |
llava-v1.6-vicuna-7b-hf-2412 | 15.38 |
qwen2-vl-7b-instruct-2412 | 15.38 |
mc-vsft-qwen2_vl_2b-2412 | 15.38 |
llava-gemma-2b-2412 | 0 |
llava-1.5-7b-hf-2412 | 0 |
fuyu-8b-2412 | 0 |
llava-1.5-13b-hf-2412 | 0 |
qwen2-vl-72b-instruct-2412 | null |
mc-bbox-qwen2_vl_7b-2502 | null |
mc-base-qwen2_vl_2b-v2-ckpt4000-2502 | null |
mc-vsft-llava_v1.6_vicuna_13b-mcvqa_v4_11_21_80k-2412 | 24.43 |
mc-base-qwen2_vl_7b-v2-ckpt3200-2502 | 24.43 |
mc-point-qwen2_vl_7b-2502 | 22.14 |
mc-base-qwen2_vl_7b-2502 | 20.99 |
mc-base-qwen2_vl_7b-v2-ckpt2400-2502 | 20.99 |
mc-base-qwen2_vl_2b-v2-ckpt4000-2502 | 16.79 |
mc-base-llava_next_vicuna_13b-ckpt4000-2502 | 15.27 |
qwen2-vl-7b-instruct-2412 | 13.74 |
qwen2-vl-72b-instruct-2412 | 9.54 |
mc-base-qwen2_vl_2b-v2-ckpt1600-2502 | 8.02 |
molmo-7b-d-0924-2412 | 3.44 |
mc-bbox-qwen2_vl_7b-2502 | 1.53 |
mc-reason-qwen2_vl_7b-ckpt2400-2502 | 0 |
llama3-llava-next-8b-hf-2412 | null |
gpt-4o-2412 | null |
gpt-4o-mini-2412 | null |
fuyu-8b-2412 | null |
llava-1.5-13b-hf-2412 | null |
llava-1.5-7b-hf-2412 | null |
llava-v1.6-mistral-7b-hf-2412 | null |
llava-v1.6-vicuna-13b-hf-2412 | null |
llava-v1.6-vicuna-7b-hf-2412 | null |
MiniCPM-V-2_6-2412 | null |
llava-gemma-2b-2412 | null |
molmo-72b-0924-2412 | null |
mc-sft-llava_next_8b-mcqa_v3_12_25_277k-2411 | null |
llama-3.2-11b-vision-instruct-2412 | null |
mc-sft-llava_next_8b-mcqa_v3_12_25_277k-2412 | null |
mc-vsft-llama3_llava_next_8b-mcvqa_v4_11_21_80k-2412 | null |
mc-vsft-llava_v1.6_vicuna_13b-mcvqa_v4_11_21_80k-2412 | null |
mc-sft-qwen2_vl_7b-mcqa_v3_12_25_277k-2412 | null |
mc-vsft-qwen2_vl_7b-2412 | null |
mc-vsft-qwen2_vl_2b-2412 | null |
mc-vsft-llava_v1.6_vicuna_13b-mcvqa_v4_11_21_80k-2412 | null |
mc-base-qwen2_vl_7b-v2-ckpt3200-2502 | 84 |
mc-base-qwen2_vl_7b-v2-ckpt2400-2502 | 79 |
mc-base-llava_next_vicuna_13b-ckpt4000-2502 | 60 |
mc-point-qwen2_vl_7b-2502 | 40 |
mc-base-qwen2_vl_2b-v2-ckpt4000-2502 | 39 |
mc-bbox-qwen2_vl_7b-2502 | 38 |
mc-base-qwen2_vl_7b-2502 | 38 |
mc-base-qwen2_vl_2b-v2-ckpt1600-2502 | 32 |
molmo-7b-d-0924-2412 | 19 |
qwen2-vl-7b-instruct-2412 | 8 |
qwen2-vl-72b-instruct-2412 | 0 |
mc-reason-qwen2_vl_7b-ckpt2400-2502 | 0 |
llama3-llava-next-8b-hf-2412 | null |
gpt-4o-2412 | null |
gpt-4o-mini-2412 | null |
fuyu-8b-2412 | null |
llava-1.5-13b-hf-2412 | null |
llava-1.5-7b-hf-2412 | null |
llava-v1.6-mistral-7b-hf-2412 | null |
llava-v1.6-vicuna-13b-hf-2412 | null |
llava-v1.6-vicuna-7b-hf-2412 | null |
MiniCPM-V-2_6-2412 | null |
llava-gemma-2b-2412 | null |
molmo-72b-0924-2412 | null |
mc-sft-llava_next_8b-mcqa_v3_12_25_277k-2411 | null |
llama-3.2-11b-vision-instruct-2412 | null |
mc-sft-llava_next_8b-mcqa_v3_12_25_277k-2412 | null |
mc-vsft-llama3_llava_next_8b-mcvqa_v4_11_21_80k-2412 | null |
mc-vsft-llava_v1.6_vicuna_13b-mcvqa_v4_11_21_80k-2412 | null |
mc-sft-qwen2_vl_7b-mcqa_v3_12_25_277k-2412 | null |
mc-vsft-qwen2_vl_7b-2412 | null |
mc-vsft-qwen2_vl_2b-2412 | null |
Threshold corresponding to the values of GUI and Embodied Grounding: 20