{
    "GPT_4o": {
        "core_noncot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.5203440930873326,
            "micro_mean_score": 0.514302640282204
        },
        "core_cot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.5265030595065238,
            "micro_mean_score": 0.5236338521693411
        },
        "open": {
            "num_eval_tasks": 65,
            "num_eval_samples": 1163,
            "macro_mean_score": 0.6478225794744895,
            "micro_mean_score": 0.665391229578676
        },
        "overall_score": 0.5421184432647768
    },
    "Gemini_1.5_pro_002": {
        "core_noncot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.4699992918320008,
            "micro_mean_score": 0.4651116133689296
        },
        "core_cot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.4822473962867704,
            "micro_mean_score": 0.4764805563057179
        },
        "open": {
            "num_eval_tasks": 65,
            "num_eval_samples": 1163,
            "macro_mean_score": 0.5858190649927173,
            "micro_mean_score": 0.6104901117798793
        },
        "overall_score": 0.4955784031499121
    },
    "Gemini_1.5_flash_002": {
        "core_noncot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.41898948981774853,
            "micro_mean_score": 0.4127376993779598
        },
        "core_cot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.4189319021967416,
            "micro_mean_score": 0.41567515414375245
        },
        "open": {
            "num_eval_tasks": 65,
            "num_eval_samples": 1163,
            "macro_mean_score": 0.5691365176285039,
            "micro_mean_score": 0.5987532244196045
        },
        "overall_score": 0.43831534488249924
    },
    "Claude_3.5": {
        "core_noncot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.48800427486796155,
            "micro_mean_score": 0.4814327812005499
        },
        "core_cot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.5040975742801586,
            "micro_mean_score": 0.5002259116666758
        },
        "open": {
            "num_eval_tasks": 65,
            "num_eval_samples": 1163,
            "macro_mean_score": 0.6373907158949892,
            "micro_mean_score": 0.6569647463456579
        },
        "overall_score": 0.5212541172602853
    },
    "Claude_3.5_new": {
        "core_noncot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.4919657684484185,
            "micro_mean_score": 0.4874520567007144
        },
        "core_cot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.5259191914020757,
            "micro_mean_score": 0.5230785894131227
        },
        "open": {
            "num_eval_tasks": 65,
            "num_eval_samples": 1163,
            "macro_mean_score": 0.6563419761104125,
            "micro_mean_score": 0.6724419604471196
        },
        "overall_score": 0.5427062825031487
    },
    "GPT_4o_mini": {
        "core_noncot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.39854757130003565,
            "micro_mean_score": 0.3936551517403452
        },
        "core_cot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.40767494558789397,
            "micro_mean_score": 0.40431644154143376
        },
        "open": {
            "num_eval_tasks": 65,
            "num_eval_samples": 1163,
            "macro_mean_score": 0.586537827213665,
            "micro_mean_score": 0.6133276010318144
        },
        "overall_score": 0.43069690064863675
    },
    "Qwen2_VL_72B": {
        "core_noncot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.46406654108789214,
            "micro_mean_score": 0.4584702152011697
        },
        "core_cot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.4542376574527161,
            "micro_mean_score": 0.4501201906164793
        },
        "open": {
            "num_eval_tasks": 65,
            "num_eval_samples": 1163,
            "macro_mean_score": 0.5639771804231668,
            "micro_mean_score": 0.5835339638865004
        },
        "overall_score": 0.4769263263488681
    },
    "Qwen2_VL_7B": {
        "core_noncot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.3480020832611913,
            "micro_mean_score": 0.3441858958345098
        },
        "core_cot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.3293449599230247,
            "micro_mean_score": 0.325331493515679
        },
        "open": {
            "num_eval_tasks": 65,
            "num_eval_samples": 1170,
            "macro_mean_score": 0.43955105763038577,
            "micro_mean_score": 0.45508547008546996
        },
        "overall_score": 0.3597856146156421
    },
    "llava_onevision_72B": {
        "core_noncot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.3199332158220174,
            "micro_mean_score": 0.31770770553892647
        },
        "core_cot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.2974368415462532,
            "micro_mean_score": 0.2956217833156672
        },
        "open": {
            "num_eval_tasks": 65,
            "num_eval_samples": 1163,
            "macro_mean_score": 0.4599484231632498,
            "micro_mean_score": 0.4850386930352536
        },
        "overall_score": 0.33795497518277007
    },
    "llava_onevision_7B": {
        "core_noncot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.22409531510496777,
            "micro_mean_score": 0.22238854298563537
        },
        "core_cot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.21362697219149712,
            "micro_mean_score": 0.21073910058505504
        },
        "open": {
            "num_eval_tasks": 65,
            "num_eval_samples": 1163,
            "macro_mean_score": 0.33979975321921935,
            "micro_mean_score": 0.36474634565778147
        },
        "overall_score": 0.23898796555531696
    },
    "InternVL2_76B": {
        "core_noncot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.3502244283768534,
            "micro_mean_score": 0.3456783051732046
        },
        "core_cot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.3562710424410931,
            "micro_mean_score": 0.35129859801162616
        },
        "open": {
            "num_eval_tasks": 65,
            "num_eval_samples": 1163,
            "macro_mean_score": 0.5192997443033639,
            "micro_mean_score": 0.5421324161650903
        },
        "overall_score": 0.3772549347599992
    },
    "InternVL2_8B": {
        "core_noncot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.25956581776451815,
            "micro_mean_score": 0.2546984460483302
        },
        "core_cot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.24090301358258295,
            "micro_mean_score": 0.23819084111520938
        },
        "open": {
            "num_eval_tasks": 65,
            "num_eval_samples": 1165,
            "macro_mean_score": 0.3978571701460552,
            "micro_mean_score": 0.4108583690987125
        },
        "overall_score": 0.2773656948037259
    },
    "MiniCPM_v2.6": {
        "core_noncot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.2287645706203155,
            "micro_mean_score": 0.2249087742955901
        },
        "core_cot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.22955895202146906,
            "micro_mean_score": 0.22560399396899078
        },
        "open": {
            "num_eval_tasks": 65,
            "num_eval_samples": 1163,
            "macro_mean_score": 0.41728623355613875,
            "micro_mean_score": 0.43452278589853827
        },
        "overall_score": 0.2537218694467236
    },
    "Phi-3.5-vision": {
        "core_noncot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.23271251159409778,
            "micro_mean_score": 0.2296262323791101
        },
        "core_cot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.22995297916629392,
            "micro_mean_score": 0.22708502951025372
        },
        "open": {
            "num_eval_tasks": 65,
            "num_eval_samples": 1163,
            "macro_mean_score": 0.3947914647737769,
            "micro_mean_score": 0.42459157351676696
        },
        "overall_score": 0.25357415903306635
    },
    "Pixtral_12B": {
        "core_noncot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.31905695620134694,
            "micro_mean_score": 0.31556607913724777
        },
        "core_cot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.31362045151669854,
            "micro_mean_score": 0.3100986209078182
        },
        "open": {
            "num_eval_tasks": 65,
            "num_eval_samples": 1163,
            "macro_mean_score": 0.4566234428542061,
            "micro_mean_score": 0.4870593293207223
        },
        "overall_score": 0.33676353369131895
    },
    "Llama_3_2_11B": {
        "core_noncot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.10044261716549671,
            "micro_mean_score": 0.09980638766828835
        },
        "core_cot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.15999641916771298,
            "micro_mean_score": 0.15809331016967038
        },
        "open": {
            "num_eval_tasks": 65,
            "num_eval_samples": 1163,
            "macro_mean_score": 0.3173342406187366,
            "micro_mean_score": 0.3487962166809973
        },
        "overall_score": 0.1802478219287358
    },
    "Idefics3": {
        "core_noncot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.11118980301103833,
            "micro_mean_score": 0.11201785633274061
        },
        "core_cot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.08956972487602757,
            "micro_mean_score": 0.08982225274252693
        },
        "open": {
            "num_eval_tasks": 65,
            "num_eval_samples": 1163,
            "macro_mean_score": 0.3210866162255635,
            "micro_mean_score": 0.35649183147033553
        },
        "overall_score": 0.138206224513898
    },
    "Aria": {
        "core_noncot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.30485930718699694,
            "micro_mean_score": 0.3016713629035311
        },
        "core_cot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.289073788209904,
            "micro_mean_score": 0.2859007507765791
        },
        "open": {
            "num_eval_tasks": 65,
            "num_eval_samples": 1163,
            "macro_mean_score": 0.5103725263180767,
            "micro_mean_score": 0.5349957007738607
        },
        "overall_score": 0.3313115037088191
    },
    "NVLM": {
        "core_noncot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.2420528895703979,
            "micro_mean_score": 0.23838419989257642
        },
        "core_cot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.21589726765847422,
            "micro_mean_score": 0.21406043849932396
        },
        "open": {
            "num_eval_tasks": 65,
            "num_eval_samples": 1163,
            "macro_mean_score": 0.3478114310231307,
            "micro_mean_score": 0.3947549441100602
        },
        "overall_score": 0.25566537510391796
    },
    "InternVL2_2B": {
        "core_noncot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.09089701489596874,
            "micro_mean_score": 0.09036328295381871
        },
        "core_cot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.13141974398938763,
            "micro_mean_score": 0.13063500716262516
        },
        "open": {
            "num_eval_tasks": 65,
            "num_eval_samples": 1163,
            "macro_mean_score": 0.23864417043743646,
            "micro_mean_score": 0.24901117798796224
        },
        "overall_score": 0.14522090778963154
    },
    "Qwen2_VL_2B": {
        "core_noncot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.16448220309703876,
            "micro_mean_score": 0.1610710186451323
        },
        "core_cot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.20877163406364055,
            "micro_mean_score": 0.20561526268932287
        },
        "open": {
            "num_eval_tasks": 65,
            "num_eval_samples": 1163,
            "macro_mean_score": 0.3154302566225611,
            "micro_mean_score": 0.33856405846947557
        },
        "overall_score": 0.22249997162072932
    },
    "Aquila_VL_2B": {
        "core_noncot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.16317824309838627,
            "micro_mean_score": 0.16198837245148487
        },
        "core_cot": {
            "num_eval_tasks": 440,
            "num_eval_samples": 6539,
            "num_not_eval_samples": 0,
            "macro_mean_score": 0.159970161379836,
            "micro_mean_score": 0.15844711671722148
        },
        "open": {
            "num_eval_tasks": 65,
            "num_eval_samples": 1163,
            "macro_mean_score": 0.24567572098570653,
            "micro_mean_score": 0.2704213241616509
        },
        "overall_score": 0.17379673035120966
    }
}