Combined: API error
Combined
API error
See which AI models are most likely to hit API error on Combined, so you can spot weak points faster. Sort by: Failure Count ↑.
Failure Reasons
24/24
Filter models
No models match the current search and filters.
| Rank | Model | Company | API error Count | Category Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #33 | Kimi K3 max | Moonshot AI | 1 | 6.5 | $3.112 | 1/2 | 223.0s |
| #60 | LongCat 2.0 medium | Meituan | 1 | 7.3 | $0.478 | 1/2 | 151.0s |
| #62 | KAT-Coder-Pro V2.5 low | Kwaipilot | 1 | 6.4 | $0.387 | 1/2 | 111.9s |
| #81 | KAT-Coder-Pro V2.5 medium | Kwaipilot | 1 | 6.4 | $0.467 | 1/2 | 135.7s |
| #90 | Qwen3.6 35B A3B medium | Qwen | 1 | 3.0 | $0.746 | 0/2 | 817.6s |
| #110 | Gemma 4 31B medium | 1 | 2.9 | $0.163 | 0/2 | 433.1s | |
| #115 | Gemma 4 31B none | 1 | 3.8 | $0.035 | 0/2 | 30.0s | |
| #129 | Nemotron 3 Ultra none | NVIDIA | 1 | 3.0 | $0.095 | 0/2 | 21.1s |
| #130 | Step 3.5 Flash medium | Stepfun | 1 | 6.5 | $0.108 | 1/2 | 813.7s |
| #140 | Nemotron 3 Super medium | NVIDIA | 1 | 6.4 | $0.050 | 1/2 | 259.9s |
| #144 | KAT-Coder-Air V2.5 high | Kwaipilot | 1 | 6.5 | $0.077 | 1/2 | 74.5s |
| #149 | KAT-Coder-Air V2.5 medium | Kwaipilot | 1 | 6.5 | $0.048 | 1/2 | 19.6s |
| #158 | KAT-Coder-Air V2.5 low | Kwaipilot | 1 | 6.4 | $0.041 | 1/2 | 55.9s |
| #161 | Qwen3.6 35B A3B none | Qwen | 1 | 3.8 | $0.061 | 0/2 | 39.5s |
| #181 | Grok 4.20 Multi Agent Beta medium | X AI | 1 | 1.5 | $5.599 | 0/1 | 0ms |