AI BENCHY
Your ad here

AI BENCHY Failures

Wrong answer Failures

See which AI models run into Wrong answer most often, so you can spot reliability risks before choosing one. Sort by: Score ↑.

Models Shown

15

Total Failures

572

Most Affected Model

LFM2-24B-A2B 9

Categories

In category Domain specific182 In category Anti-AI Tricks165 In category Puzzle Solving85 In category Instructions following44 In category Combined37 In category Coding28 In category Data parsing and extraction19 In category General Intelligence10 In category Tool Calling2
Rank Model Company Wrong answer Count Score Tests Correct Response Time (avg)
#23 MiMo-V2-Pro medium Xiaomi 3 8.1 12/18 12.3s
#22 Gemini 3.1 Flash Lite Preview low Google 4 8.1 13/18 3.22s
#21 Gemini 3 Flash Preview none Google 5 8.1 13/18 1.65s
#20 Qwen3.6 Plus medium Qwen 3 8.1 13/18 15.3s
#19 Qwen3.5-122B-A10B medium Qwen 3 8.1 13/18 31.4s
#18 GLM 5 Turbo medium Z.ai 3 8.1 12/18 17.7s
#17 Gemini 3.1 Flash Lite Preview medium Google 4 8.2 13/18 3.74s
#16 GPT-5.4 medium OpenAI 3 8.2 13/18 18.6s
#15 Gemini 2.5 Flash medium Google 4 8.2 13/18 12.1s
#14 Gemma 4 31B medium Google 1 8.3 13/18 24.9s
#13 GLM 5 medium Z.ai 2 8.4 13/18 23.3s
#12 Gemini 3 PRO Preview medium Google 3 8.4 14/18 9.06s
#11 Gemini 3.1 Flash Lite Preview high Google 3 8.4 12/16 68.8s
#10 Qwen3.5-27B medium Qwen 1 8.4 13/18 53.0s
#9 Qwen3.6 Plus Preview medium Qwen 3 8.5 13/17 13.9s

Top Models by Wrong answer Count

Wrong answer Count vs Score

Top Models by Response Time (avg)