agent,agent_normalized,visible_agent_name,agent_version,avg_cost,avg_steps,benchmark,finished_pct,model,model_normalized,num_tasks,score,total_cost claudecode,claude-code,Claude_Code,claude_code_2.1.7,0.5026066430000001,18.94,AppWorld,0.46,deepseek,deepseek-v3.2,100,0.03,50.26066430000001 claudecode,claude-code,Claude_Code,claude_code_2.1.7,0.10630119119999998,20.82,BrowseComp+,0.98,deepseek,deepseek-v3.2,100,0.48,10.630119119999998 claudecode,claude-code,Claude_Code,claude_code_2.1.7,0.20144125259999995,54.16,SWE-bench,0.89,deepseek,deepseek-v3.2,100,0.64,20.144125259999996 claudecode,claude-code,Claude_Code,claude_code_2.1.7,0.028655971600000007,12.06,TauBench-Airline,0.98,deepseek,deepseek-v3.2,50,0.28,1.4327985800000003 claudecode,claude-code,Claude_Code,claude_code_2.1.7,0.043596285400000004,12.51,TauBench-Retail,0.99,deepseek,deepseek-v3.2,100,0.65,4.35962854 claudecode,claude-code,Claude_Code,claude_code_2.1.7,0.07225669540000003,20.03,TauBench-Telecom,0.97,deepseek,deepseek-v3.2,100,0.61,7.225669540000003 claudecode,claude-code,Claude_Code,claude_code_2.1.7,0.8930315160000002,36.62,AppWorld,0.78,kimi,kimi-k2.5,100,0.08,89.30315160000002 claudecode,claude-code,Claude_Code,claude_code_2.1.7,0.7320507719999999,25.02,BrowseComp+,0.86,kimi,kimi-k2.5,100,0.56,73.20507719999999 claudecode,claude-code,Claude_Code,claude_code_2.1.7,0.7822629151515151,38.484848484848484,SWE-bench,0.7474747474747475,kimi,kimi-k2.5,100,0.5204081632653061,77.4440286 claudecode,claude-code,Claude_Code,claude_code_2.1.7,0.032654508000000006,2.58,TauBench-Airline,0.9,kimi,kimi-k2.5,50,0.12,1.6327254000000002 claudecode,claude-code,Claude_Code,claude_code_2.1.7,0.018570114000000006,0.56,TauBench-Retail,1.0,kimi,kimi-k2.5,100,0.03,1.8570114000000004 claudecode,claude-code,Claude_Code,claude_code_2.1.7,0.005500535999999998,0.0,TauBench-Telecom,1.0,kimi,kimi-k2.5,100,0.0,0.5500535999999998 claudecode,claude-code,Claude_Code,claude_code_2.1.7,0.0,0.0,AppWorld,0.0,gpt52,gpt-5.2,100,0.0,0.0 claudecode,claude-code,Claude_Code,claude_code_2.1.7,0.4293807000000001,8.97,BrowseComp+,1.0,gpt52,gpt-5.2,100,0.43,42.93807000000001 claudecode,claude-code,Claude_Code,claude_code_2.1.7,0.9397547250000001,23.99,SWE-bench,1.0,gpt52,gpt-5.2,100,0.58,93.97547250000001 claudecode,claude-code,Claude_Code,claude_code_2.1.7,0.21338296,10.18,TauBench-Airline,1.0,gpt52,gpt-5.2,50,0.48,10.669148 claudecode,claude-code,Claude_Code,claude_code_2.1.7,0.1200643675,9.92,TauBench-Retail,0.98,gpt52,gpt-5.2,100,0.64,12.00643675 claudecode,claude-code,Claude_Code,claude_code_2.1.7,0.0980149625,9.36,TauBench-Telecom,1.0,gpt52,gpt-5.2,100,0.55,9.80149625 claudecode,claude-code,Claude_Code,claude_code_2.1.7,13.08379215,49.69,AppWorld,0.74,claude,claude-opus-4.5,100,0.66,1308.3792150000002 claudecode,claude-code,Claude_Code,claude_code_2.1.7,11.658796372549022,31.03921568627451,BrowseComp+,0.8431372549019608,claude,claude-opus-4.5,51,0.5294117647058824,594.5986150000001 claudecode,claude-code,Claude_Code,claude_code_2.1.7,5.604360979381441,31.762886597938145,SWE-bench,1.0,claude,claude-opus-4.5,97,0.7422680412371134,543.6230149999998 claudecode,claude-code,Claude_Code,claude_code_2.1.7,1.2993549000000004,11.5,TauBench-Airline,1.0,claude,claude-opus-4.5,50,0.66,64.96774500000002 claudecode,claude-code,Claude_Code,claude_code_2.1.7,1.5985232500000006,12.54,TauBench-Retail,1.0,claude,claude-opus-4.5,100,0.83,159.85232500000006 claudecode,claude-code,Claude_Code,claude_code_2.1.7,2.448864600000001,18.71,TauBench-Telecom,1.0,claude,claude-opus-4.5,100,0.76,244.8864600000001 claudecode,claude-code,Claude_Code,claude_code_2.1.7,3.10550762,38.01,AppWorld,0.86,gemini,gemini-3-pro,100,0.36,310.550762 claudecode,claude-code,Claude_Code,claude_code_2.1.7,2.8452944199999997,22.88,BrowseComp+,0.7,gemini,gemini-3-pro,100,0.51,284.52944199999996 claudecode,claude-code,Claude_Code,claude_code_2.1.7,3.679668759999999,43.72,SWE-bench,1.0,gemini,gemini-3-pro,100,0.67,367.9668759999999 claudecode,claude-code,Claude_Code,claude_code_2.1.7,0.3394426000000001,12.62,TauBench-Airline,1.0,gemini,gemini-3-pro,50,0.7,16.972130000000003 claudecode,claude-code,Claude_Code,claude_code_2.1.7,0.18525811999999994,11.18,TauBench-Retail,1.0,gemini,gemini-3-pro,100,0.71,18.525811999999995 claudecode,claude-code,Claude_Code,claude_code_2.1.7,0.21064223999999993,9.9,TauBench-Telecom,1.0,gemini,gemini-3-pro,100,0.71,21.064223999999992 openaimcp,openai-mcp,OpenAI_Solo,openai_sdk_0.7.0,0.3050881588000001,15.63,AppWorld,0.37,deepseek,deepseek-v3.2,100,0.06,30.50881588000001 openaimcp,openai-mcp,OpenAI_Solo,openai_sdk_0.7.0,0.09532471040000004,13.13,BrowseComp+,0.62,deepseek,deepseek-v3.2,100,0.3,9.532471040000004 openaimcp,openai-mcp,OpenAI_Solo,openai_sdk_0.7.0,0.11237704080000001,41.37,SWE-bench,0.38,deepseek,deepseek-v3.2,100,0.7368421052631579,11.23770408 openaimcp,openai-mcp,OpenAI_Solo,openai_sdk_0.7.0,0.016994613600000003,6.72,TauBench-Airline,0.94,deepseek,deepseek-v3.2,50,0.2,0.8497306800000002 openaimcp,openai-mcp,OpenAI_Solo,openai_sdk_0.7.0,0.011356187600000003,4.82,TauBench-Retail,0.97,deepseek,deepseek-v3.2,100,0.19,1.1356187600000003 openaimcp,openai-mcp,OpenAI_Solo,openai_sdk_0.7.0,0.023369379999999995,7.0,TauBench-Telecom,0.97,deepseek,deepseek-v3.2,100,0.18,2.3369379999999995 openaimcp,openai-mcp,OpenAI_Solo,openai_sdk_0.7.0,0.3024222959999999,19.59,AppWorld,0.48,kimi,kimi-k2.5,100,0.08,30.242229599999995 openaimcp,openai-mcp,OpenAI_Solo,openai_sdk_0.7.0,0.25144734599999996,17.61,BrowseComp+,0.53,kimi,kimi-k2.5,100,0.35,25.144734599999996 openaimcp,openai-mcp,OpenAI_Solo,openai_sdk_0.7.0,0.3341831760000001,38.74,SWE-bench,0.78,kimi,kimi-k2.5,100,0.5670103092783505,33.41831760000001 openaimcp,openai-mcp,OpenAI_Solo,openai_sdk_0.7.0,0.004579271999999998,0.5,TauBench-Airline,0.88,kimi,kimi-k2.5,50,0.0,0.2289635999999999 openaimcp,openai-mcp,OpenAI_Solo,openai_sdk_0.7.0,0.0042811740000000004,0.41,TauBench-Retail,0.96,kimi,kimi-k2.5,100,0.01,0.42811740000000004 openaimcp,openai-mcp,OpenAI_Solo,openai_sdk_0.7.0,0.0046396319999999994,0.0,TauBench-Telecom,1.0,kimi,kimi-k2.5,100,0.0,0.46396319999999996 openaimcp,openai-mcp,OpenAI_Solo,openai_sdk_0.7.0,0.0,0.0,AppWorld,0.0,gpt52,gpt-5.2,100,0.0,0.0 openaimcp,openai-mcp,OpenAI_Solo,openai_sdk_0.7.0,0.3804372600000001,14.27,BrowseComp+,1.0,gpt52,gpt-5.2,100,0.48,38.043726000000014 openaimcp,openai-mcp,OpenAI_Solo,openai_sdk_0.7.0,0.259017835858586,20.444444444444443,SWE-bench,1.0,gpt52,gpt-5.2,99,0.5454545454545454,25.642765750000013 openaimcp,openai-mcp,OpenAI_Solo,openai_sdk_0.7.0,0.10711806000000001,11.4,TauBench-Airline,1.0,gpt52,gpt-5.2,50,0.5,5.3559030000000005 openaimcp,openai-mcp,OpenAI_Solo,openai_sdk_0.7.0,0.10778330499999997,9.55,TauBench-Retail,0.99,gpt52,gpt-5.2,100,0.53,10.778330499999997 openaimcp,openai-mcp,OpenAI_Solo,openai_sdk_0.7.0,0.14717545500000007,9.92,TauBench-Telecom,1.0,gpt52,gpt-5.2,100,0.53,14.717545500000005 openaimcp,openai-mcp,OpenAI_Solo,openai_sdk_0.7.0,22.764767600000006,47.65,AppWorld,0.77,claude,claude-opus-4.5,100,0.68,2276.4767600000005 openaimcp,openai-mcp,OpenAI_Solo,openai_sdk_0.7.0,7.592457349999998,27.18,BrowseComp+,1.0,claude,claude-opus-4.5,100,0.61,759.2457349999999 openaimcp,openai-mcp,OpenAI_Solo,openai_sdk_0.7.0,2.9612612048192783,34.096385542168676,SWE-bench,1.0,claude,claude-opus-4.5,83,0.8072289156626506,245.7846800000001 openaimcp,openai-mcp,OpenAI_Solo,openai_sdk_0.7.0,0.7165842000000003,12.22,TauBench-Airline,1.0,claude,claude-opus-4.5,50,0.74,35.82921000000002 openaimcp,openai-mcp,OpenAI_Solo,openai_sdk_0.7.0,0.5495812000000001,12.54,TauBench-Retail,1.0,claude,claude-opus-4.5,100,0.85,54.958120000000015 openaimcp,openai-mcp,OpenAI_Solo,openai_sdk_0.7.0,1.2459395,17.15,TauBench-Telecom,1.0,claude,claude-opus-4.5,100,0.84,124.59395 openaimcp,openai-mcp,OpenAI_Solo,openai_sdk_0.7.0,8.695528419999997,33.49,AppWorld,0.98,gemini,gemini-3-pro,100,0.57,869.5528419999997 openaimcp,openai-mcp,OpenAI_Solo,openai_sdk_0.7.0,0.6433071111111112,8.454545454545455,BrowseComp+,0.6060606060606061,gemini,gemini-3-pro,99,0.3333333333333333,63.687404 openaimcp,openai-mcp,OpenAI_Solo,openai_sdk_0.7.0,1.5791779787234044,32.361702127659576,SWE-bench,1.0,gemini,gemini-3-pro,94,0.723404255319149,148.44273 openaimcp,openai-mcp,OpenAI_Solo,openai_sdk_0.7.0,0.21380211999999996,10.9,TauBench-Airline,1.0,gemini,gemini-3-pro,50,0.62,10.690105999999998 openaimcp,openai-mcp,OpenAI_Solo,openai_sdk_0.7.0,0.26648499999999986,10.62,TauBench-Retail,1.0,gemini,gemini-3-pro,100,0.73,26.648499999999988 openaimcp,openai-mcp,OpenAI_Solo,openai_sdk_0.7.0,0.5351315199999997,10.82,TauBench-Telecom,0.89,gemini,gemini-3-pro,100,0.79,53.51315199999998 smolagent,smolagents,Smolagent,smolagents_1.24.0,0.2420605992000001,54.69,AppWorld,0.81,deepseek,deepseek-v3.2,100,0.13,24.20605992000001 smolagent,smolagents,Smolagent,smolagents_1.24.0,0.07768438359999996,12.01,BrowseComp+,1.0,deepseek,deepseek-v3.2,100,0.21,7.768438359999997 smolagent,smolagents,Smolagent,smolagents_1.24.0,0.5519223772,69.43,SWE-bench,0.98,deepseek,deepseek-v3.2,100,0.56,55.19223772000001 smolagent,smolagents,Smolagent,smolagents_1.24.0,0.055420856,18.94,TauBench-Airline,1.0,deepseek,deepseek-v3.2,50,0.6,2.7710428 smolagent,smolagents,Smolagent,smolagents_1.24.0,0.05129110320000001,14.06,TauBench-Retail,0.98,deepseek,deepseek-v3.2,100,0.77,5.1291103200000006 smolagent,smolagents,Smolagent,smolagents_1.24.0,0.06806756960000002,18.3,TauBench-Telecom,1.0,deepseek,deepseek-v3.2,100,0.84,6.806756960000001 smolagent,smolagents,Smolagent,smolagents_1.24.0,0.6740286120000001,50.63,AppWorld,0.91,kimi,kimi-k2.5,100,0.11,67.4028612 smolagent,smolagents,Smolagent,smolagents_1.24.0,0.4948784999999996,29.79,BrowseComp+,0.95,kimi,kimi-k2.5,100,0.33,49.48784999999996 smolagent,smolagents,Smolagent,smolagents_1.24.0,1.3741787032258057,65.91397849462365,SWE-bench,0.8709677419354839,kimi,kimi-k2.5,100,0.5760869565217391,127.79861939999994 smolagent,smolagents,Smolagent,smolagents_1.24.0,0.09928738799999998,13.0,TauBench-Airline,1.0,kimi,kimi-k2.5,50,0.56,4.964369399999999 smolagent,smolagents,Smolagent,smolagents_1.24.0,0.06753205714285712,12.887755102040817,TauBench-Retail,1.0,kimi,kimi-k2.5,100,0.7244897959183674,6.618141599999998 smolagent,smolagents,Smolagent,smolagents_1.24.0,0.15341341818181825,19.141414141414142,TauBench-Telecom,1.0,kimi,kimi-k2.5,100,0.7070707070707071,15.187928400000008 smolagent,smolagents,Smolagent,smolagents_1.24.0,0.5503114225,51.59,AppWorld,0.61,gpt52,gpt-5.2,100,0.07,55.03114225 smolagent,smolagents,Smolagent,smolagents_1.24.0,0.17156755,6.57,BrowseComp+,0.99,gpt52,gpt-5.2,100,0.26,17.156755 smolagent,smolagents,Smolagent,smolagents_1.24.0,0.45031795454545454,19.97979797979798,SWE-bench,1.0,gpt52,gpt-5.2,99,0.5252525252525253,44.5814775 smolagent,smolagents,Smolagent,smolagents_1.24.0,0.2932717550000001,10.68,TauBench-Airline,1.0,gpt52,gpt-5.2,50,0.6,14.663587750000003 smolagent,smolagents,Smolagent,smolagents_1.24.0,0.25194685249999993,11.08,TauBench-Retail,1.0,gpt52,gpt-5.2,100,0.68,25.194685249999992 smolagent,smolagents,Smolagent,smolagents_1.24.0,0.30355347749999995,10.11,TauBench-Telecom,1.0,gpt52,gpt-5.2,100,0.71,30.355347749999993 smolagent,smolagents,Smolagent,smolagents_1.24.0,5.585109100000002,41.07,AppWorld,0.82,claude,claude-opus-4.5,100,0.7,558.5109100000002 smolagent,smolagents,Smolagent,smolagents_1.24.0,6.303725049999997,24.16,BrowseComp+,1.0,claude,claude-opus-4.5,100,0.61,630.3725049999997 smolagent,smolagents,Smolagent,smolagents_1.24.0,4.8521832499999995,39.13,SWE-bench,1.0,claude,claude-opus-4.5,100,0.65,485.218325 smolagent,smolagents,Smolagent,smolagents_1.24.0,0.7801527999999999,11.88,TauBench-Airline,1.0,claude,claude-opus-4.5,50,0.72,39.007639999999995 smolagent,smolagents,Smolagent,smolagents_1.24.0,0.6711861,11.71,TauBench-Retail,1.0,claude,claude-opus-4.5,100,0.78,67.11861 smolagent,smolagents,Smolagent,smolagents_1.24.0,1.0643879000000003,13.77,TauBench-Telecom,1.0,claude,claude-opus-4.5,100,0.58,106.43879000000003 smolagent,smolagents,Smolagent,smolagents_1.24.0,2.542546020000001,49.13,AppWorld,0.71,gemini,gemini-3-pro,100,0.13,254.2546020000001 smolagent,smolagents,Smolagent,smolagents_1.24.0,2.388851260000001,29.63,BrowseComp+,0.69,gemini,gemini-3-pro,100,0.57,238.88512600000007 smolagent,smolagents,Smolagent,smolagents_1.24.0,2.209661838383839,38.101010101010104,SWE-bench,1.0,gemini,gemini-3-pro,99,0.7575757575757576,218.75652200000005 smolagent,smolagents,Smolagent,smolagents_1.24.0,0.19590487999999995,12.28,TauBench-Airline,1.0,gemini,gemini-3-pro,50,0.68,9.795243999999997 smolagent,smolagents,Smolagent,smolagents_1.24.0,0.2056864,11.3,TauBench-Retail,1.0,gemini,gemini-3-pro,100,0.75,20.56864 smolagent,smolagents,Smolagent,smolagents_1.24.0,0.3461698999999998,12.71,TauBench-Telecom,1.0,gemini,gemini-3-pro,100,0.88,34.61698999999998 litellm,litellm-react,React,exgentic_0.1.0,0.8332616264000001,31.69,AppWorld,0.88,deepseek,deepseek-v3.2,100,0.09,83.32616264 litellm,litellm-react,React,exgentic_0.1.0,0.1679167768,34.19,BrowseComp+,0.98,deepseek,deepseek-v3.2,100,0.36,16.79167768 litellm,litellm-react,React,exgentic_0.1.0,0.47889091680000007,77.44,SWE-bench,0.94,deepseek,deepseek-v3.2,100,0.6875,47.88909168000001 litellm,litellm-react,React,exgentic_0.1.0,0.033952516,15.28,TauBench-Airline,1.0,deepseek,deepseek-v3.2,50,0.56,1.6976258 litellm,litellm-react,React,exgentic_0.1.0,0.029598555599999986,14.44,TauBench-Retail,1.0,deepseek,deepseek-v3.2,100,0.82,2.9598555599999985 litellm,litellm-react,React,exgentic_0.1.0,0.04940463720000001,18.11,TauBench-Telecom,1.0,deepseek,deepseek-v3.2,100,0.71,4.940463720000001 litellm,litellm-react,React,exgentic_0.1.0,0.8925547499999997,25.05,AppWorld,0.9,kimi,kimi-k2.5,100,0.09,89.25547499999998 litellm,litellm-react,React,exgentic_0.1.0,0.3791127780000001,26.27,BrowseComp+,0.74,kimi,kimi-k2.5,100,0.34,37.91127780000001 litellm,litellm-react,React,exgentic_0.1.0,0.590102075510204,48.765306122448976,SWE-bench,0.8775510204081632,kimi,kimi-k2.5,100,0.5714285714285714,57.830003399999995 litellm,litellm-react,React,exgentic_0.1.0,0.03922161599999999,9.6,TauBench-Airline,1.0,kimi,kimi-k2.5,50,0.62,1.9610807999999995 litellm,litellm-react,React,exgentic_0.1.0,0.04560821212121211,12.313131313131313,TauBench-Retail,1.0,kimi,kimi-k2.5,100,0.6464646464646465,4.515212999999999 litellm,litellm-react,React,exgentic_0.1.0,0.092763078,16.14,TauBench-Telecom,1.0,kimi,kimi-k2.5,100,0.83,9.2763078 litellm,litellm-react,React,exgentic_0.1.0,0.0,0.0,AppWorld,0.0,gpt52,gpt-5.2,100,0.0,0.0 litellm,litellm-react,React,exgentic_0.1.0,0.2961726250000001,8.14,BrowseComp+,0.99,gpt52,gpt-5.2,100,0.46,29.617262500000006 litellm,litellm-react,React,exgentic_0.1.0,0.247620555,20.47,SWE-bench,1.0,gpt52,gpt-5.2,100,0.57,24.7620555 litellm,litellm-react,React,exgentic_0.1.0,0.12510473500000002,11.22,TauBench-Airline,1.0,gpt52,gpt-5.2,50,0.54,6.255236750000001 litellm,litellm-react,React,exgentic_0.1.0,0.11093171249999992,10.33,TauBench-Retail,1.0,gpt52,gpt-5.2,100,0.73,11.093171249999992 litellm,litellm-react,React,exgentic_0.1.0,0.14089510749999992,10.18,TauBench-Telecom,0.99,gpt52,gpt-5.2,100,0.53,14.089510749999993 litellm,litellm-react,React,exgentic_0.1.0,11.324659950000004,21.99,AppWorld,0.83,claude,claude-opus-4.5,100,0.61,1132.4659950000005 litellm,litellm-react,React,exgentic_0.1.0,7.093632849999999,21.66,BrowseComp+,0.93,claude,claude-opus-4.5,100,0.49,709.3632849999999 litellm,litellm-react,React,exgentic_0.1.0,3.971294949494951,43.44444444444444,SWE-bench,1.0,claude,claude-opus-4.5,99,0.6060606060606061,393.15820000000014 litellm,litellm-react,React,exgentic_0.1.0,0.46923760000000003,10.0,TauBench-Airline,1.0,claude,claude-opus-4.5,50,0.66,23.46188 litellm,litellm-react,React,exgentic_0.1.0,0.46742524999999985,11.33,TauBench-Retail,1.0,claude,claude-opus-4.5,100,0.78,46.742524999999986 litellm,litellm-react,React,exgentic_0.1.0,0.9157812500000004,17.22,TauBench-Telecom,1.0,claude,claude-opus-4.5,100,0.76,91.57812500000004 litellm,litellm-react,React,exgentic_0.1.0,1.8818770200000003,21.76,AppWorld,0.99,gemini,gemini-3-pro,100,0.5,188.18770200000003 litellm,litellm-react,React,exgentic_0.1.0,0.4394335600000001,7.85,BrowseComp+,0.99,gemini,gemini-3-pro,100,0.48,43.94335600000001 litellm,litellm-react,React,exgentic_0.1.0,0.6956134199999998,32.55,SWE-bench,1.0,gemini,gemini-3-pro,100,0.71,69.56134199999998 litellm,litellm-react,React,exgentic_0.1.0,0.15854967999999997,10.14,TauBench-Airline,1.0,gemini,gemini-3-pro,50,0.7,7.927483999999998 litellm,litellm-react,React,exgentic_0.1.0,0.15649691999999996,11.25,TauBench-Retail,1.0,gemini,gemini-3-pro,100,0.82,15.649691999999995 litellm,litellm-react,React,exgentic_0.1.0,0.29797836000000005,14.84,TauBench-Telecom,1.0,gemini,gemini-3-pro,100,0.73,29.797836000000004 litellm-shortlist,litellm-shortlist,React_+_Shortlisting,exgentic_0.1.0_·_litellm_1.79.1,0.23222570840000004,28.51,AppWorld,0.52,deepseek,deepseek-v3.2,100,0.04,23.222570840000003 litellm-shortlist,litellm-shortlist,React_+_Shortlisting,exgentic_0.1.0_·_litellm_1.79.1,0.1679167768,34.19,BrowseComp+,0.98,deepseek,deepseek-v3.2,100,0.36,16.79167768 litellm-shortlist,litellm-shortlist,React_+_Shortlisting,exgentic_0.1.0_·_litellm_1.79.1,0.47889091680000007,77.44,SWE-bench,0.94,deepseek,deepseek-v3.2,100,0.6875,47.88909168000001 litellm-shortlist,litellm-shortlist,React_+_Shortlisting,exgentic_0.1.0_·_litellm_1.79.1,0.033952516,15.28,TauBench-Airline,1.0,deepseek,deepseek-v3.2,50,0.56,1.6976258 litellm-shortlist,litellm-shortlist,React_+_Shortlisting,exgentic_0.1.0_·_litellm_1.79.1,0.029598555599999986,14.44,TauBench-Retail,1.0,deepseek,deepseek-v3.2,100,0.82,2.9598555599999985 litellm-shortlist,litellm-shortlist,React_+_Shortlisting,exgentic_0.1.0_·_litellm_1.79.1,0.04940463720000001,18.11,TauBench-Telecom,1.0,deepseek,deepseek-v3.2,100,0.71,4.940463720000001 litellm-shortlist,litellm-shortlist,React_+_Shortlisting,exgentic_0.1.0_·_litellm_1.79.1,0.6031619339999997,23.53,AppWorld,0.89,kimi,kimi-k2.5,100,0.1,60.316193399999975 litellm-shortlist,litellm-shortlist,React_+_Shortlisting,exgentic_0.1.0_·_litellm_1.79.1,0.3791127780000001,26.27,BrowseComp+,0.74,kimi,kimi-k2.5,100,0.34,37.91127780000001 litellm-shortlist,litellm-shortlist,React_+_Shortlisting,exgentic_0.1.0_·_litellm_1.79.1,0.590102075510204,48.765306122448976,SWE-bench,0.8775510204081632,kimi,kimi-k2.5,100,0.5714285714285714,57.830003399999995 litellm-shortlist,litellm-shortlist,React_+_Shortlisting,exgentic_0.1.0_·_litellm_1.79.1,0.03922161599999999,9.6,TauBench-Airline,1.0,kimi,kimi-k2.5,50,0.62,1.9610807999999995 litellm-shortlist,litellm-shortlist,React_+_Shortlisting,exgentic_0.1.0_·_litellm_1.79.1,0.04560821212121211,12.313131313131313,TauBench-Retail,1.0,kimi,kimi-k2.5,100,0.6464646464646465,4.515212999999999 litellm-shortlist,litellm-shortlist,React_+_Shortlisting,exgentic_0.1.0_·_litellm_1.79.1,0.092763078,16.14,TauBench-Telecom,1.0,kimi,kimi-k2.5,100,0.83,9.2763078 litellm-shortlist,litellm-shortlist,React_+_Shortlisting,exgentic_0.1.0_·_litellm_1.79.1,0.36371315749999994,10.05,AppWorld,1.0,gpt52,gpt-5.2,100,0.22,36.371315749999994 litellm-shortlist,litellm-shortlist,React_+_Shortlisting,exgentic_0.1.0_·_litellm_1.79.1,0.2961726250000001,8.14,BrowseComp+,0.99,gpt52,gpt-5.2,100,0.46,29.617262500000006 litellm-shortlist,litellm-shortlist,React_+_Shortlisting,exgentic_0.1.0_·_litellm_1.79.1,0.247620555,20.47,SWE-bench,1.0,gpt52,gpt-5.2,100,0.57,24.7620555 litellm-shortlist,litellm-shortlist,React_+_Shortlisting,exgentic_0.1.0_·_litellm_1.79.1,0.12510473500000002,11.22,TauBench-Airline,1.0,gpt52,gpt-5.2,50,0.54,6.255236750000001 litellm-shortlist,litellm-shortlist,React_+_Shortlisting,exgentic_0.1.0_·_litellm_1.79.1,0.11093171249999992,10.33,TauBench-Retail,1.0,gpt52,gpt-5.2,100,0.73,11.093171249999992 litellm-shortlist,litellm-shortlist,React_+_Shortlisting,exgentic_0.1.0_·_litellm_1.79.1,0.14089510749999992,10.18,TauBench-Telecom,0.99,gpt52,gpt-5.2,100,0.53,14.089510749999993 litellm-shortlist,litellm-shortlist,React_+_Shortlisting,exgentic_0.1.0_·_litellm_1.79.1,3.4332017499999994,20.06,AppWorld,0.82,claude,claude-opus-4.5,100,0.64,343.32017499999995 litellm-shortlist,litellm-shortlist,React_+_Shortlisting,exgentic_0.1.0_·_litellm_1.79.1,7.093632849999999,21.66,BrowseComp+,0.93,claude,claude-opus-4.5,100,0.49,709.3632849999999 litellm-shortlist,litellm-shortlist,React_+_Shortlisting,exgentic_0.1.0_·_litellm_1.79.1,3.971294949494951,43.44444444444444,SWE-bench,1.0,claude,claude-opus-4.5,99,0.6060606060606061,393.15820000000014 litellm-shortlist,litellm-shortlist,React_+_Shortlisting,exgentic_0.1.0_·_litellm_1.79.1,0.46923760000000003,10.0,TauBench-Airline,1.0,claude,claude-opus-4.5,50,0.66,23.46188 litellm-shortlist,litellm-shortlist,React_+_Shortlisting,exgentic_0.1.0_·_litellm_1.79.1,0.46742524999999985,11.33,TauBench-Retail,1.0,claude,claude-opus-4.5,100,0.78,46.742524999999986 litellm-shortlist,litellm-shortlist,React_+_Shortlisting,exgentic_0.1.0_·_litellm_1.79.1,0.9157812500000004,17.22,TauBench-Telecom,1.0,claude,claude-opus-4.5,100,0.76,91.57812500000004 litellm-shortlist,litellm-shortlist,React_+_Shortlisting,exgentic_0.1.0_·_litellm_1.79.1,1.30485292,22.59,AppWorld,1.0,gemini,gemini-3-pro,100,0.55,130.48529200000002 litellm-shortlist,litellm-shortlist,React_+_Shortlisting,exgentic_0.1.0_·_litellm_1.79.1,0.4394335600000001,7.85,BrowseComp+,0.99,gemini,gemini-3-pro,100,0.48,43.94335600000001 litellm-shortlist,litellm-shortlist,React_+_Shortlisting,exgentic_0.1.0_·_litellm_1.79.1,0.6956134199999998,32.55,SWE-bench,1.0,gemini,gemini-3-pro,100,0.71,69.56134199999998 litellm-shortlist,litellm-shortlist,React_+_Shortlisting,exgentic_0.1.0_·_litellm_1.79.1,0.15854967999999997,10.14,TauBench-Airline,1.0,gemini,gemini-3-pro,50,0.7,7.927483999999998 litellm-shortlist,litellm-shortlist,React_+_Shortlisting,exgentic_0.1.0_·_litellm_1.79.1,0.15649691999999996,11.25,TauBench-Retail,1.0,gemini,gemini-3-pro,100,0.82,15.649691999999995 litellm-shortlist,litellm-shortlist,React_+_Shortlisting,exgentic_0.1.0_·_litellm_1.79.1,0.29797836000000005,14.84,TauBench-Telecom,1.0,gemini,gemini-3-pro,100,0.73,29.797836000000004