AI BENCHY
Your ad here

AI BENCHY Failures

API error Failures

See which AI models run into API error most often, so you can spot reliability risks before choosing one. Sort by: Response Time (avg) ↑.

Models Shown

3

Total Failures

27

Most Affected Model

Step 3.5 Flash 1

Categories

In category Coding6 In category Data parsing and extraction6 In category Tool Calling6 In category Combined5 In category Domain specific2 In category Instructions following1 In category Puzzle Solving1
Rank Model Company API error Count Score Tests Correct Response Time (avg)
#14 Gemma 4 31B medium Google 2 8.3 13/18 24.9s
#43 Qwen3.5-35B-A3B medium Qwen 1 7.4 10/18 44.5s
#32 Qwen3.5-Flash medium Qwen 1 7.8 11/18 66.7s

Top Models by API error Count

API error Count vs Score

Top Models by Response Time (avg)