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
57.44s (#1)49.75s (#1)20.18s (#2)54.43s (#3)78.25s (#5)46.27s (#2)49.49s (#3)77.61s (#1)71.87s (#3)48.17s (#1)78.36s (#4)
136.57s (#6)151.27s (#6)87.09s (#10)51.96s (#2)38.37s (#2)70.02s (#4)37.09s (#1)549.69s (#26)257.35s (#14)84.60s (#2)38.28s (#2)
69.09s (#2)78.70s (#3)11.68s (#1)128.71s (#6)38.80s (#3)44.97s (#1)110.24s (#11)86.64s (#3)74.84s (#4)84.66s (#3)31.65s (#1)
154.14s (#8)108.05s (#5)233.48s (#28)256.42s (#19)82.40s (#6)55.00s (#3)104.63s (#8)423.65s (#16)68.72s (#2)92.10s (#4)116.93s (#7)
97.87s (#3)71.82s (#2)159.59s (#19)48.94s (#1)33.30s (#1)107.56s (#6)42.97s (#2)177.95s (#8)172.55s (#8)110.82s (#5)53.20s (#3)
173.94s (#9)475.33s (#21)58.33s (#6)184.80s (#11)139.99s (#11)178.27s (#12)125.50s (#14)154.38s (#7)178.77s (#9)112.88s (#6)131.14s (#8)
186.15s (#11)381.70s (#18)98.86s (#13)168.30s (#10)140.84s (#12)157.04s (#9)98.37s (#5)342.94s (#14)247.19s (#13)129.19s (#7)97.11s (#5)
131.60s (#4)173.45s (#7)103.96s (#16)157.20s (#8)159.48s (#14)133.87s (#7)108.75s (#10)116.05s (#5)119.65s (#6)135.61s (#8)107.99s (#6)
134.54s (#5)177.99s (#8)35.03s (#4)225.56s (#15)188.51s (#16)93.04s (#5)103.82s (#7)83.18s (#2)94.83s (#5)145.68s (#9)197.75s (#14)
183.02s (#10)279.10s (#9)37.39s (#5)221.63s (#14)94.44s (#7)235.04s (#17)117.91s (#12)253.53s (#11)225.41s (#12)147.66s (#10)218.10s (#20)
146.93s (#7)101.37s (#4)25.43s (#3)207.95s (#13)212.72s (#19)182.36s (#14)175.82s (#17)108.12s (#4)63.58s (#1)166.40s (#11)225.52s (#22)
211.73s (#14)338.66s (#16)195.02s (#24)111.18s (#5)64.85s (#4)178.36s (#13)92.15s (#4)473.75s (#18)272.36s (#18)169.01s (#12)222.00s (#21)
329.01s (#23)537.40s (#23)227.50s (#27)434.36s (#32)300.18s (#26)262.83s (#21)233.52s (#25)537.19s (#24)355.69s (#20)188.43s (#13)212.96s (#18)
198.13s (#12)318.52s (#15)67.47s (#8)277.47s (#21)230.39s (#21)182.53s (#15)212.87s (#23)132.59s (#6)141.92s (#7)204.26s (#14)213.26s (#19)
222.47s (#15)306.23s (#13)63.38s (#7)314.20s (#25)209.90s (#17)160.49s (#10)139.17s (#15)328.10s (#13)268.02s (#17)228.24s (#15)207.00s (#16)
207.02s (#13)285.18s (#11)73.44s (#9)100.46s (#4)138.18s (#10)177.54s (#11)99.14s (#6)516.52s (#21)266.01s (#16)246.66s (#16)167.10s (#12)
316.92s (#22)303.69s (#12)172.93s (#21)283.97s (#22)514.83s (#33)246.10s (#18)325.97s (#29)418.19s (#15)361.13s (#21)252.93s (#17)289.47s (#27)
240.32s (#17)408.06s (#20)271.44s (#31)160.54s (#9)133.01s (#8)155.29s (#8)142.28s (#16)299.67s (#12)423.42s (#22)257.52s (#18)151.94s (#10)
268.83s (#19)282.18s (#10)98.87s (#14)238.91s (#17)231.81s (#22)302.92s (#25)185.82s (#18)490.26s (#19)440.47s (#24)259.70s (#19)157.38s (#11)
257.83s (#18)560.12s (#24)166.98s (#20)239.95s (#18)185.68s (#15)267.72s (#22)200.70s (#21)246.31s (#10)214.93s (#11)269.22s (#20)226.66s (#23)
425.28s (#27)945.31s (#30)88.57s (#11)379.63s (#29)236.09s (#23)270.87s (#23)253.79s (#27)632.83s (#28)900.50s (#30)274.40s (#21)270.86s (#26)
410.46s (#26)631.21s (#25)193.29s (#23)356.02s (#28)313.10s (#28)393.95s (#29)395.74s (#31)541.90s (#25)691.56s (#28)278.37s (#22)309.50s (#29)
226.68s (#16)497.62s (#22)107.44s (#17)187.07s (#12)154.37s (#13)247.60s (#19)120.27s (#13)189.55s (#9)343.78s (#19)279.02s (#23)140.04s (#9)
373.31s (#25)834.12s (#27)210.10s (#25)329.94s (#26)377.65s (#29)254.76s (#20)382.09s (#30)493.52s (#20)264.77s (#15)281.70s (#24)304.43s (#28)
434.15s (#28)983.23s (#31)173.15s (#22)458.68s (#33)401.14s (#30)278.51s (#24)244.60s (#26)743.59s (#31)574.40s (#27)283.53s (#25)200.63s (#15)
337.21s (#24)388.67s (#19)256.53s (#30)274.04s (#20)224.98s (#20)386.17s (#28)290.78s (#28)524.49s (#22)507.05s (#26)284.57s (#26)234.87s (#24)
270.44s (#20)345.25s (#17)273.29s (#32)135.28s (#7)136.91s (#9)222.38s (#16)107.56s (#9)467.38s (#17)507.04s (#25)302.23s (#27)207.07s (#17)
476.75s (#31)847.62s (#29)216.36s (#26)502.25s (#35)555.51s (#35)406.21s (#31)564.10s (#36)526.61s (#23)428.48s (#23)340.18s (#28)380.19s (#33)
472.81s (#29)991.82s (#33)589.49s (#36)238.88s (#16)288.48s (#25)400.58s (#30)201.58s (#22)562.56s (#27)746.35s (#29)374.69s (#29)333.69s (#31)
562.46s (#32)1010.63s (#34)281.41s (#33)304.53s (#23)211.69s (#18)448.43s (#32)189.40s (#19)1420.30s (#35)1052.80s (#32)377.39s (#30)327.97s (#30)
291.84s (#21)309.68s (#14)98.59s (#12)308.84s (#24)258.63s (#24)313.48s (#26)194.04s (#20)684.89s (#29)180.43s (#10)380.11s (#31)189.75s (#13)
783.82s (#36)1424.65s (#38)435.14s (#35)477.57s (#34)586.24s (#37)582.91s (#37)431.57s (#33)1706.35s (#37)1289.05s (#35)425.52s (#32)479.20s (#37)
627.33s (#33)991.04s (#32)369.43s (#34)416.66s (#31)430.18s (#31)560.75s (#36)468.29s (#35)1079.65s (#33)1077.59s (#33)512.74s (#33)366.99s (#32)
729.12s (#35)1063.41s (#35)599.81s (#37)401.07s (#30)574.37s (#36)506.63s (#34)437.62s (#34)1223.91s (#34)1507.26s (#37)520.56s (#34)456.51s (#36)
630.49s (#34)726.63s (#26)152.22s (#18)537.89s (#38)591.02s (#38)502.27s (#33)618.98s (#38)898.32s (#32)1317.98s (#36)546.11s (#35)413.46s (#34)
476.65s (#30)844.76s (#28)99.46s (#15)344.66s (#27)310.40s (#27)362.74s (#27)220.56s (#24)737.76s (#30)1043.45s (#31)548.97s (#36)253.75s (#25)
810.89s (#37)1366.04s (#37)248.13s (#29)506.33s (#36)540.14s (#34)515.38s (#35)580.07s (#37)1677.41s (#36)1660.09s (#38)582.45s (#37)432.82s (#35)
832.67s (#38)1311.96s (#36)650.23s (#38)528.49s (#37)503.19s (#32)607.86s (#38)403.12s (#32)1755.13s (#38)1282.71s (#34)701.66s (#38)582.35s (#38)
AutoBench Run 5 - December 2025 - AutoBench