AI BENCHY Category Failures
Domain specific: API error
Domain specific
API error
See which AI models are most likely to hit API error on Domain specific, so you can spot weak points faster. Sort by: Failure Count ↑.
Failure Reasons
| Rank | Model | Company | API error Count | Category Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #93 | Qwen3.6 Plus Preview medium | Qwen | 1 | 3.0 | 0/3 | 22.1s |
| #103 | DeepSeek V4 Pro high | DeepSeek | 1 | 2.9 | 0/3 | 205.7s |
| #132 | Mistral Small 4 medium | Mistral | 1 | 5.3 | 1/3 | 6.11s |
| #133 | DeepSeek V3.2 none | DeepSeek | 1 | 2.9 | 0/3 | 4.17s |
| #156 | Hy3 preview none | Tencent | 1 | 3.6 | 0/3 | 17.6s |
| #160 | LFM2-24B-A2B none | Liquid | 1 | 5.9 | 1/3 | 287ms |