Spaces:
Running
Running
| {"agent_name": "Qwen3-Embedding-4B", "model_family": "Qwen3-32B", "Date": "2026-03-03", "verified": true, "Score": {"GAME": [{"A": 0.4914}, {"B": 0.5278}, {"C": 0.5769}, {"D": 0.4667}], "EMBODIED_AI": [{"A": 0.4262}, {"B": 0.2444}, {"C": 0.1467}, {"D": 0.0}], "WEB": [{"A": 0.312}, {"B": 0.4194}, {"C": 0.2043}, {"D": 0.2131}], "TEXT2SQL": [{"A": 0.5785}, {"B": 0.5556}, {"C": 0.306}, {"D": 0.2255}], "OPENWORLD_QA": [{"A": 0.4388}, {"B": 0.4632}, {"C": 0.4112}, {"D": 0.2833}], "SOFTWARE": [{"A": 0.5849}, {"B": 0.7067}, {"C": 0.4795}, {"D": 0.625}]}} | |
| {"agent_name": "AMA-agent", "model_family": "Qwen3-32B", "Date": "2026-03-04", "verified": true, "Score": {"GAME": [{"A": 0.6471}, {"B": 0.7}, {"C": 0.6}, {"D": 0.6167}], "EMBODIED_AI": [{"A": 0.8033}, {"B": 0.5778}, {"C": 0.44}, {"D": 0.2169}], "WEB": [{"A": 0.53}, {"B": 0.68}, {"C": 0.4133}, {"D": 0.4}], "TEXT2SQL": [{"A": 0.7584}, {"B": 0.4615}, {"C": 0.6782}, {"D": 0.4118}], "OPENWORLD_QA": [{"A": 0.4482}, {"B": 0.5558}, {"C": 0.4612}, {"D": 0.39}], "SOFTWARE": [{"A": 0.6049}, {"B": 0.7268}, {"C": 0.4905}, {"D": 0.7778}]}} | |
| {"agent_name": "GRAPHRAG", "model_family": "Qwen3-32B", "Date": "2026-03-03", "verified": true, "Score": {"GAME": [{"A": 0.5347}, {"B": 0.5484}, {"C": 0.5588}, {"D": 0.5962}], "EMBODIED_AI": [{"A": 0.0426}, {"B": 0.3913}, {"C": 0.1565}, {"D": 0.0}], "WEB": [{"A": 0.314}, {"B": 0.4778}, {"C": 0.4333}, {"D": 0.4576}], "TEXT2SQL": [{"A": 0.2646}, {"B": 0.2353}, {"C": 0.2687}, {"D": 0.098}], "OPENWORLD_QA": [{"A": 0.3474}, {"B": 0.4348}, {"C": 0.233}, {"D": 0.2586}], "SOFTWARE": [{"A": 0.3585}, {"B": 0.36}, {"C": 0.2603}, {"D": 0.4167}]}} | |
| {"agent_name": "Hipporag2", "model_family": "Qwen3-32B", "Date": "2026-03-03", "verified": true, "Score": {"GAME": [{"A": 0.5137}, {"B": 0.6029}, {"C": 0.6806}, {"D": 0.625}], "EMBODIED_AI": [{"A": 0.3607}, {"B": 0.2111}, {"C": 0.1333}, {"D": 0.0}], "WEB": [{"A": 0.344}, {"B": 0.4731}, {"C": 0.4086}, {"D": 0.2787}], "TEXT2SQL": [{"A": 0.6233}, {"B": 0.5882}, {"C": 0.4627}, {"D": 0.1765}], "OPENWORLD_QA": [{"A": 0.4595}, {"B": 0.5135}, {"C": 0.5122}, {"D": 0.3478}], "SOFTWARE": [{"A": 0.3471}, {"B": 0.5902}, {"C": 0.4237}, {"D": 0.7586}]}} | |
| {"agent_name": "Memagent", "model_family": "Qwen3-32B", "Date": "2026-03-03", "verified": true, "Score": {"GAME": [{"A": 0.3103}, {"B": 0.3056}, {"C": 0.3718}, {"D": 0.2833}], "EMBODIED_AI": [{"A": 0.0656}, {"B": 0.2889}, {"C": 0.0533}, {"D": 0.0169}], "WEB": [{"A": 0.256}, {"B": 0.3118}, {"C": 0.2258}, {"D": 0.2623}], "TEXT2SQL": [{"A": 0.2518}, {"B": 0.2975}, {"C": 0.272}, {"D": 0.1602}], "OPENWORLD_QA": [{"A": 0.1939}, {"B": 0.1895}, {"C": 0.1495}, {"D": 0.1}], "SOFTWARE": [{"A": 0.4292}, {"B": 0.6267}, {"C": 0.6027}, {"D": 0.5}]}} | |
| {"agent_name": "Mem1", "model_family": "Qwen3-32B", "Date": "2026-03-03", "verified": true, "Score": {"GAME": [{"A": 0.2217}, {"B": 0.24}, {"C": 0.1918}, {"D": 0.25}], "EMBODIED_AI": [{"A": 0.0164}, {"B": 0.1111}, {"C": 0.0067}, {"D": 0.0}], "WEB": [{"A": 0.12}, {"B": 0.1075}, {"C": 0.1828}, {"D": 0.1148}], "TEXT2SQL": [{"A": 0.0762}, {"B": 0.0784}, {"C": 0.0746}, {"D": 0.0294}], "OPENWORLD_QA": [{"A": 0.1224}, {"B": 0.2}, {"C": 0.0935}, {"D": 0.0667}], "SOFTWARE": [{"A": 0.1698}, {"B": 0.16}, {"C": 0.1918}, {"D": 0.2222}]}} | |
| {"agent_name": "Amem", "model_family": "Qwen3-32B", "Date": "2026-03-03", "verified": true, "Score": {"GAME": [{"A": 0.3793}, {"B": 0.4028}, {"C": 0.5}, {"D": 0.4167}], "EMBODIED_AI": [{"A": 0.082}, {"B": 0.4}, {"C": 0.22}, {"D": 0.0339}], "WEB": [{"A": 0.36}, {"B": 0.4624}, {"C": 0.3011}, {"D": 0.4426}], "TEXT2SQL": [{"A": 0.4036}, {"B": 0.3333}, {"C": 0.3134}, {"D": 0.2059}], "OPENWORLD_QA": [{"A": 0.2755}, {"B": 0.3579}, {"C": 0.2243}, {"D": 0.3167}], "SOFTWARE": [{"A": 0.283}, {"B": 0.2667}, {"C": 0.2877}, {"D": 0.3472}]}} | |
| {"agent_name": "Mem0", "model_family": "Qwen3-32B", "Date": "2026-03-03", "verified": true, "Score": {"GAME": [{"A": 0.4259}, {"B": 0.3788}, {"C": 0.473}, {"D": 0.2857}], "EMBODIED_AI": [{"A": 0.0164}, {"B": 0.3444}, {"C": 0.0667}, {"D": 0.0169}], "WEB": [{"A": 0.256}, {"B": 0.3656}, {"C": 0.2473}, {"D": 0.2131}], "TEXT2SQL": [{"A": 0.16}, {"B": 0.1512}, {"C": 0.1139}, {"D": 0.0517}], "OPENWORLD_QA": [{"A": 0.1735}, {"B": 0.1895}, {"C": 0.1682}, {"D": 0.1167}], "SOFTWARE": [{"A": 0.1953}, {"B": 0.234}, {"C": 0.2444}, {"D": 0.2727}]}} | |
| {"agent_name": "Memorag", "model_family": "Qwen3-32B", "Date": "2026-03-03", "verified": true, "Score": {"GAME": [{"A": 0.5405}, {"B": 0.6}, {"C": 0.64}, {"D": 0.45}], "EMBODIED_AI": [{"A": 0.1639}, {"B": 0.1111}, {"C": 0.0667}, {"D": 0.0}], "WEB": [{"A": 0.368}, {"B": 0.4839}, {"C": 0.2473}, {"D": 0.3607}], "TEXT2SQL": [{"A": 0.7273}, {"B": 0.7333}, {"C": 0.6154}, {"D": 0.4}], "OPENWORLD_QA": [{"A": 0.4}, {"B": 0.5789}, {"C": 0.3333}, {"D": 0.3333}], "SOFTWARE": [{"A": 0.4495}, {"B": 0.6494}, {"C": 0.5067}, {"D": 0.5946}]}} | |
| {"agent_name": "Memgpt", "model_family": "Qwen3-32B", "Date": "2026-03-03", "verified": true, "Score": {"GAME": [{"A": 0.3534}, {"B": 0.3472}, {"C": 0.4744}, {"D": 0.5667}], "EMBODIED_AI": [{"A": 0.1475}, {"B": 0.2444}, {"C": 0.04}, {"D": 0.0169}], "WEB": [{"A": 0.384}, {"B": 0.4624}, {"C": 0.2688}, {"D": 0.1967}], "TEXT2SQL": [{"A": 0.287}, {"B": 0.3595}, {"C": 0.1418}, {"D": 0.0392}], "OPENWORLD_QA": [{"A": 0.2615}, {"B": 0.5156}, {"C": 0.3099}, {"D": 0.175}], "SOFTWARE": [{"A": 0.5385}, {"B": 0.7333}, {"C": 0.5111}, {"D": 0.6136}]}} | |
| {"agent_name": "Mem-alpha", "model_family": "Qwen3-32B", "Date": "2026-03-03", "verified": true, "Score": {"GAME": [{"A": 0.4286}, {"B": 0.4783}, {"C": 0.4868}, {"D": 0.3621}], "EMBODIED_AI": [{"A": 0.0984}, {"B": 0.4222}, {"C": 0.1}, {"D": 0.0}], "WEB": [{"A": 0.3077}, {"B": 0.5172}, {"C": 0.2759}, {"D": 0.3509}], "TEXT2SQL": [{"A": 0.3318}, {"B": 0.3922}, {"C": 0.3806}, {"D": 0.098}], "OPENWORLD_QA": [{"A": 0.2674}, {"B": 0.2927}, {"C": 0.2065}, {"D": 0.1538}], "SOFTWARE": [{"A": 0.2594}, {"B": 0.4133}, {"C": 0.3288}, {"D": 0.3889}]}} | |
| {"agent_name": "Memorybank", "model_family": "Qwen3-32B", "Date": "2026-03-03", "verified": true, "Score": {"GAME": [{"A": 0.4359}, {"B": 0.4028}, {"C": 0.5}, {"D": 0.4167}], "EMBODIED_AI": [{"A": 0.1017}, {"B": 0.3908}, {"C": 0.131}, {"D": 0.0175}], "WEB": [{"A": 0.3393}, {"B": 0.5357}, {"C": 0.3571}, {"D": 0.375}], "TEXT2SQL": [{"A": 0.3139}, {"B": 0.3007}, {"C": 0.2612}, {"D": 0.0784}], "OPENWORLD_QA": [{"A": 0.2959}, {"B": 0.4421}, {"C": 0.2897}, {"D": 0.3667}], "SOFTWARE": [{"A": 0.4386}, {"B": 0.4545}, {"C": 0.2857}, {"D": 0.85}]}} | |
| {"agent_name": "Simple mem", "model_family": "Qwen3-32B", "Date": "2026-03-03", "verified": true, "Score": {"GAME": [{"A": 0.2083}, {"B": 0.2353}, {"C": 0.4615}, {"D": 0.25}], "EMBODIED_AI": [{"A": 0.0}, {"B": 0.1149}, {"C": 0.069}, {"D": 0.0}], "WEB": [{"A": 0.156}, {"B": 0.2099}, {"C": 0.0988}, {"D": 0.0943}], "TEXT2SQL": [{"A": 0.354}, {"B": 0.1644}, {"C": 0.1802}, {"D": 0.0717}], "OPENWORLD_QA": [{"A": 0.1224}, {"B": 0.1684}, {"C": 0.1121}, {"D": 0.0833}], "SOFTWARE": [{"A": 0.2538}, {"B": 0.2444}, {"C": 0.1333}, {"D": 0.3409}]}} | |
| {"agent_name": "Long context", "model_family": "Qwen3-32B", "Date": "2026-03-03", "verified": true, "Score": {"GAME": [{"A": 0.5431}, {"B": 0.4861}, {"C": 0.5128}, {"D": 0.6}], "EMBODIED_AI": [{"A": 0.7966}, {"B": 0.6437}, {"C": 0.4345}, {"D": 0.0526}], "WEB": [{"A": 0.504}, {"B": 0.6667}, {"C": 0.5054}, {"D": 0.541}], "TEXT2SQL": [{"A": 0.7309}, {"B": 0.3203}, {"C": 0.5672}, {"D": 0.2059}], "OPENWORLD_QA": [{"A": 0.4894}, {"B": 0.5978}, {"C": 0.4904}, {"D": 0.4138}], "SOFTWARE": [{"A": 0.5581}, {"B": 0.5254}, {"C": 0.3898}, {"D": 0.4655}]}} | |