Back to Archive

AutoBench Agentic Run 1 - April 2026

The first AutoBench run to measure agentic performance of top LLMs

Past
Date
April 16, 2026
Version
2026-04-16
Models
31
New Models
22

Run data

Model
Average (All Topics)Adaptive ReplanningApi WorkflowDomain WorkflowError HandlingFailure RecoveryMulti Step OrchestrationParallel ExecutionParameter ComplexitySingle Tool CallTool Selection
9.27s (#1)11.02s (#2)11.39s (#3)12.33s (#2)9.96s (#2)9.45s (#1)9.74s (#1)12.16s (#2)5.79s (#2)4.09s (#1)5.78s (#1)
10.56s (#2)10.48s (#1)9.58s (#1)11.41s (#1)9.21s (#1)22.29s (#7)9.79s (#2)12.12s (#1)4.88s (#1)4.38s (#2)6.49s (#3)
12.95s (#3)16.77s (#4)13.80s (#5)14.10s (#5)13.62s (#4)14.87s (#4)12.94s (#3)15.46s (#3)9.85s (#6)8.01s (#5)8.22s (#5)
13.14s (#4)15.39s (#3)14.56s (#6)13.67s (#4)13.48s (#3)13.44s (#2)14.05s (#4)19.84s (#5)8.31s (#5)8.10s (#6)8.42s (#6)
13.64s (#5)16.99s (#5)10.22s (#2)13.02s (#3)16.24s (#5)16.54s (#5)16.16s (#5)20.91s (#7)6.47s (#3)7.18s (#4)5.99s (#2)
14.33s (#6)18.61s (#7)17.74s (#8)17.04s (#6)17.16s (#6)14.09s (#3)16.21s (#6)18.54s (#4)7.00s (#4)6.60s (#3)8.44s (#7)
18.03s (#7)18.21s (#6)12.63s (#4)20.54s (#8)25.83s (#7)20.13s (#6)22.44s (#7)20.26s (#6)14.20s (#8)14.53s (#9)6.51s (#4)
23.17s (#8)25.97s (#9)15.68s (#7)18.29s (#7)29.88s (#9)31.61s (#11)36.07s (#10)29.29s (#8)13.92s (#7)12.31s (#7)17.37s (#11)
25.60s (#9)28.50s (#10)28.99s (#11)27.09s (#10)30.50s (#10)26.21s (#9)27.52s (#8)30.32s (#9)19.02s (#10)17.84s (#13)15.41s (#8)
25.96s (#10)25.22s (#8)28.35s (#10)25.54s (#9)28.39s (#8)26.06s (#8)29.56s (#9)35.05s (#12)23.27s (#12)16.59s (#10)20.01s (#12)
28.15s (#11)34.00s (#11)25.95s (#9)30.32s (#11)34.93s (#12)31.03s (#10)37.55s (#13)31.60s (#10)17.64s (#9)17.51s (#12)15.51s (#9)
36.20s (#12)36.46s (#13)39.22s (#12)40.12s (#14)31.15s (#11)35.65s (#13)64.63s (#23)41.20s (#15)30.46s (#16)21.32s (#16)29.43s (#19)
36.77s (#13)35.13s (#12)48.29s (#19)37.43s (#13)51.09s (#16)35.09s (#12)40.00s (#14)36.07s (#13)40.46s (#25)19.21s (#15)24.21s (#15)
37.86s (#14)42.11s (#15)53.33s (#21)45.46s (#16)43.04s (#13)39.82s (#16)37.25s (#12)45.18s (#16)28.91s (#15)16.99s (#11)22.35s (#13)
41.27s (#15)44.09s (#17)43.68s (#16)36.73s (#12)44.50s (#14)42.22s (#17)45.37s (#16)34.32s (#11)42.21s (#26)36.31s (#24)45.09s (#25)
42.87s (#16)43.70s (#16)43.95s (#17)49.20s (#19)60.11s (#19)48.82s (#19)37.08s (#11)49.67s (#17)32.33s (#17)22.81s (#17)30.26s (#20)
43.55s (#17)50.45s (#19)40.41s (#14)43.28s (#15)66.69s (#23)39.12s (#15)48.02s (#18)52.61s (#20)36.52s (#22)23.05s (#18)22.97s (#14)
43.96s (#18)46.13s (#18)46.11s (#18)48.04s (#18)60.34s (#20)36.17s (#14)55.44s (#20)39.55s (#14)35.16s (#20)24.52s (#19)52.17s (#27)
46.45s (#19)51.11s (#20)52.82s (#20)76.56s (#24)50.14s (#15)52.09s (#20)42.69s (#15)52.34s (#19)38.55s (#23)18.80s (#14)28.42s (#18)
47.52s (#20)55.55s (#21)40.21s (#13)61.50s (#22)60.69s (#21)43.95s (#18)47.46s (#17)60.61s (#22)24.88s (#14)32.38s (#23)40.66s (#23)
51.69s (#21)41.67s (#14)53.58s (#22)81.31s (#26)54.97s (#17)52.10s (#21)59.09s (#22)83.55s (#27)22.69s (#11)24.67s (#20)49.91s (#26)
54.32s (#22)70.44s (#22)60.62s (#23)46.12s (#17)56.21s (#18)79.40s (#26)77.50s (#25)55.48s (#21)35.35s (#21)26.04s (#21)27.03s (#17)
54.68s (#23)87.02s (#25)40.73s (#15)54.47s (#20)62.14s (#22)52.20s (#22)52.93s (#19)76.31s (#24)40.25s (#24)39.78s (#26)31.13s (#21)
56.85s (#24)84.84s (#24)69.59s (#26)61.18s (#21)79.18s (#24)69.15s (#23)58.65s (#21)81.88s (#25)23.93s (#13)12.66s (#8)16.30s (#10)
66.09s (#25)70.58s (#23)71.50s (#27)86.14s (#28)80.67s (#25)75.41s (#24)67.05s (#24)95.99s (#29)32.96s (#18)26.56s (#22)35.16s (#22)
71.87s (#26)109.42s (#27)65.41s (#24)83.89s (#27)86.94s (#26)89.87s (#28)82.89s (#26)72.44s (#23)33.26s (#19)37.00s (#25)44.33s (#24)
85.20s (#27)93.19s (#26)84.37s (#28)103.64s (#29)118.28s (#29)98.50s (#29)93.13s (#27)86.39s (#28)45.75s (#27)43.60s (#27)60.70s (#29)
86.91s (#28)153.36s (#30)90.63s (#29)81.13s (#25)90.32s (#27)101.93s (#30)103.88s (#28)49.85s (#18)91.57s (#30)78.56s (#29)26.54s (#16)
93.34s (#29)128.94s (#28)68.28s (#25)67.87s (#23)145.88s (#31)77.75s (#25)140.74s (#31)82.56s (#26)78.78s (#29)80.94s (#30)78.70s (#30)
102.96s (#30)136.44s (#29)120.18s (#30)121.23s (#31)103.15s (#28)107.53s (#31)131.66s (#30)127.45s (#31)68.52s (#28)53.64s (#28)60.04s (#28)
129.26s (#31)190.70s (#31)125.98s (#31)111.21s (#30)140.38s (#30)81.52s (#27)131.34s (#29)101.41s (#30)160.13s (#31)108.83s (#31)175.72s (#31)
AutoBench Agentic Run 1 - April 2026 - AutoBench