Back to Archive

AutoBench Run 5 - December 2025

Latest AutoBench run with models Gpt 5.2, Claude Opus 4.5, DeepSeek 3.2 Speciale and more

Latest
Date
December 16, 2025
Version
2025-12-16
Models
35
New Models
13

Run data

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