Back to Archive

AutoBench Run 5 - December 2025

Latest AutoBench run with models Gpt 5.2, Claude Opus 4.5, Gemini 3 Flash and more

Latest
Date
December 19, 2025
Version
2025-12-19
Models
38
New Models
3

Run data

Model
Average (All Topics)CodingCreative WritingCurrent NewsGeneral CultureGrammarHistoryLogicsMathScienceTechnology
310.39s (#37)454.41s (#37)373.53s (#38)230.84s (#36)213.12s (#37)265.55s (#38)201.24s (#35)651.16s (#38)388.44s (#36)216.22s (#37)251.44s (#38)
247.97s (#35)357.90s (#35)211.44s (#37)187.67s (#32)174.58s (#33)156.16s (#34)192.82s (#34)406.50s (#35)400.05s (#37)189.54s (#36)217.88s (#37)
261.38s (#36)391.12s (#36)208.12s (#36)226.37s (#35)193.88s (#34)223.70s (#36)204.98s (#36)576.64s (#36)317.31s (#32)156.86s (#34)194.85s (#35)
227.43s (#34)311.14s (#34)145.02s (#35)239.83s (#37)201.64s (#36)180.41s (#35)222.08s (#37)400.03s (#34)232.09s (#29)177.33s (#35)190.64s (#34)
122.42s (#24)177.48s (#25)130.51s (#34)74.44s (#14)78.22s (#18)108.51s (#28)71.71s (#16)215.94s (#27)202.75s (#28)97.13s (#26)80.69s (#17)
316.82s (#38)548.95s (#38)102.39s (#33)246.60s (#38)235.78s (#38)240.61s (#37)257.27s (#38)631.62s (#37)589.95s (#38)236.47s (#38)208.52s (#36)
169.73s (#30)194.27s (#27)97.99s (#32)221.78s (#34)197.14s (#35)123.52s (#31)172.17s (#33)224.11s (#29)153.14s (#25)126.51s (#31)185.53s (#33)
144.01s (#28)205.12s (#28)91.87s (#31)160.29s (#31)154.82s (#31)103.08s (#26)161.93s (#32)168.86s (#24)110.98s (#22)119.37s (#29)160.87s (#32)
136.96s (#27)258.39s (#31)80.02s (#30)108.29s (#22)89.65s (#21)87.11s (#21)80.63s (#18)210.72s (#25)236.32s (#30)116.36s (#28)82.62s (#18)
110.95s (#23)108.22s (#15)77.98s (#29)139.82s (#28)119.32s (#29)96.88s (#24)118.54s (#26)146.18s (#18)93.19s (#17)85.52s (#19)128.07s (#28)
130.10s (#26)215.39s (#29)72.54s (#28)154.21s (#30)108.34s (#26)115.26s (#30)120.99s (#27)211.13s (#26)111.21s (#23)91.37s (#24)111.20s (#25)
180.11s (#32)298.51s (#32)65.54s (#27)144.69s (#29)119.88s (#30)154.57s (#33)121.90s (#28)391.60s (#33)277.86s (#31)135.10s (#32)151.08s (#30)
187.43s (#33)187.91s (#26)59.68s (#26)192.02s (#33)172.91s (#32)143.98s (#32)161.75s (#31)273.65s (#30)325.95s (#33)153.79s (#33)160.86s (#31)
99.62s (#21)111.28s (#18)56.96s (#25)97.44s (#19)93.68s (#23)104.45s (#27)90.76s (#22)149.92s (#20)109.45s (#21)89.69s (#23)94.05s (#21)
61.46s (#9)86.86s (#11)56.83s (#24)67.08s (#11)61.45s (#12)57.90s (#13)54.84s (#10)51.97s (#5)53.26s (#9)60.47s (#14)59.86s (#10)
124.57s (#25)170.32s (#24)50.12s (#23)130.16s (#26)103.72s (#25)86.24s (#20)130.67s (#30)219.40s (#28)157.63s (#26)86.19s (#20)108.45s (#24)
82.80s (#17)96.04s (#12)49.85s (#22)87.00s (#18)91.08s (#22)57.99s (#14)103.55s (#24)129.45s (#16)56.88s (#11)67.21s (#16)94.36s (#22)
171.50s (#31)301.05s (#33)49.49s (#21)117.82s (#24)101.41s (#24)88.70s (#23)100.73s (#23)306.87s (#32)351.14s (#35)122.31s (#30)142.47s (#29)
93.49s (#20)130.27s (#22)49.21s (#20)109.13s (#23)89.20s (#20)88.58s (#22)85.63s (#21)103.34s (#12)82.39s (#14)86.73s (#21)102.72s (#23)
77.76s (#16)105.92s (#14)48.55s (#19)77.59s (#15)69.34s (#14)85.09s (#19)65.80s (#14)98.05s (#11)85.36s (#15)71.01s (#17)68.61s (#14)
76.48s (#15)115.78s (#19)45.77s (#18)54.40s (#9)51.81s (#8)44.54s (#8)58.91s (#12)150.50s (#21)135.10s (#24)57.97s (#12)50.26s (#7)
66.78s (#11)124.96s (#21)41.48s (#17)47.07s (#7)36.69s (#7)47.29s (#10)41.35s (#7)127.95s (#15)107.37s (#20)40.87s (#7)55.15s (#8)
76.11s (#14)111.22s (#17)41.26s (#16)68.72s (#13)67.46s (#13)63.85s (#16)59.18s (#13)138.24s (#17)94.61s (#18)57.76s (#11)63.33s (#12)
86.80s (#18)109.99s (#16)37.54s (#15)99.57s (#20)87.05s (#19)65.15s (#17)74.77s (#17)125.07s (#14)98.05s (#19)75.34s (#18)88.03s (#20)
104.78s (#22)133.33s (#23)35.13s (#14)78.98s (#16)71.22s (#16)115.15s (#29)81.85s (#20)163.34s (#23)184.08s (#27)89.48s (#22)78.70s (#16)
163.15s (#29)250.89s (#30)33.18s (#13)130.32s (#27)118.61s (#28)102.73s (#25)125.26s (#29)275.60s (#31)337.88s (#34)103.09s (#27)122.18s (#27)
30.08s (#3)32.65s (#4)32.72s (#12)24.90s (#2)19.69s (#2)22.45s (#4)21.21s (#2)61.72s (#7)40.39s (#5)22.79s (#2)26.99s (#3)
45.56s (#6)53.77s (#7)32.38s (#11)26.78s (#3)22.85s (#3)25.74s (#5)21.98s (#3)151.49s (#22)80.19s (#13)24.03s (#4)25.94s (#2)
75.48s (#13)85.57s (#10)30.21s (#10)107.38s (#21)77.74s (#17)54.72s (#11)80.89s (#19)119.53s (#13)48.96s (#7)66.82s (#15)85.84s (#19)
65.62s (#10)122.23s (#20)28.98s (#9)68.60s (#12)58.98s (#10)57.46s (#12)53.43s (#8)77.53s (#10)70.88s (#12)47.92s (#8)65.63s (#13)
89.96s (#19)79.29s (#9)28.51s (#8)126.28s (#25)111.76s (#27)80.96s (#18)115.38s (#25)70.50s (#9)54.86s (#10)93.78s (#25)116.97s (#26)
69.24s (#12)99.81s (#13)27.59s (#7)50.98s (#8)55.06s (#9)58.78s (#15)53.50s (#9)147.27s (#19)93.10s (#16)58.38s (#13)58.09s (#9)
31.40s (#4)28.89s (#3)22.10s (#6)41.26s (#6)28.73s (#4)21.60s (#2)29.61s (#5)54.54s (#6)24.61s (#3)32.07s (#6)33.78s (#5)
51.84s (#7)59.24s (#8)19.71s (#5)61.11s (#10)61.19s (#11)38.99s (#7)55.96s (#11)49.03s (#4)50.09s (#8)49.47s (#9)62.25s (#11)
52.25s (#8)37.22s (#5)15.67s (#4)81.62s (#17)70.42s (#15)46.77s (#9)67.96s (#15)43.20s (#3)23.28s (#2)55.35s (#10)69.74s (#15)
38.77s (#5)48.24s (#6)14.60s (#3)37.91s (#5)32.82s (#6)38.56s (#6)29.79s (#6)64.65s (#8)47.49s (#6)31.65s (#5)40.13s (#6)
23.60s (#2)22.59s (#1)10.52s (#2)30.52s (#4)29.92s (#5)22.21s (#3)27.63s (#4)22.90s (#1)14.23s (#1)23.01s (#3)30.30s (#4)
20.42s (#1)27.69s (#2)7.47s (#1)22.16s (#1)13.57s (#1)17.90s (#1)19.61s (#1)31.56s (#2)27.47s (#4)17.06s (#1)16.96s (#1)
AutoBench Run 5 - December 2025 - AutoBench