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

Gemini 3.1 Pro Preview 1

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)
#17 Gemini 3.1 Flash Lite Preview medium Google 4 8.2 13/18 3.74s
#18 GLM 5 Turbo medium Z.ai 3 8.1 12/18 17.7s
#19 Qwen3.5-122B-A10B medium Qwen 3 8.1 13/18 31.4s
#20 Qwen3.6 Plus medium Qwen 3 8.1 13/18 15.3s
#21 Gemini 3 Flash Preview none Google 5 8.1 13/18 1.65s
#22 Gemini 3.1 Flash Lite Preview low Google 4 8.1 13/18 3.22s
#23 MiMo-V2-Pro medium Xiaomi 3 8.1 12/18 12.3s
#24 Gemma 4 26B A4B medium Google 2 8.0 13/18 25.0s
#25 Grok 4.20 Beta medium X AI 3 8.0 12/18 9.81s
#26 Claude Sonnet 4.6 medium Anthropic 2 8.0 13/18 12.7s
#27 DeepSeek V3.2 medium DeepSeek 3 8.0 12/18 46.4s
#28 GPT-5.2 Chat none OpenAI 5 7.9 12/18 6.84s
#29 Gemini 3.1 Flash Lite Preview none Google 4 7.9 12/18 1.30s
#30 Step 3.5 Flash medium Stepfun 3 7.9 11/17 26.8s
#31 GLM 5V Turbo medium Z.ai 3 7.8 11/18 15.0s

Top Models by Wrong answer Count

Wrong answer Count vs Score

Top Models by Response Time (avg)