API error Failures
See which AI models run into API error most often, so you can spot reliability risks before choosing one. Sort by: Score ↓.
149/149
Filter models
No models match the current search and filters.
| Rank | Model | Company | API error Count | Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #293 | Nemotron 3 Ultra none | NVIDIA | 2 | 0.6 | $0.164 | 8/23 | 6.76s |
| #298 | DeepSeek V4.1 Flash none | DeepSeek | 1 | 0.6 | $0.391 | 7/23 | 16.6s |
| #299 | Ling 3.0 Flash high | Inclusionai | 2 | 0.6 | $0.021 | 12/23 | 13.1s |
| #300 | Ring 2.6 1t medium | Inclusionai | 3 | 0.6 | $0.102 | 11/23 | 65.5s |
| #307 | Gemma 4 31B none | 2 | 0.6 | $0.031 | 9/23 | 7.28s | |
| #311 | Step 5 Preview low | Stepfun | 2 | 0.6 | $4.110 | 10/23 | 138.3s |
| #315 | Nemotron 3 Super medium | NVIDIA | 4 | 0.6 | $0.081 | 8/23 | 56.4s |
| #319 | GPT-6 Luna none | OpenAI | 1 | 0.5 | $0.026 | 7/23 | 20.5s |
| #325 | North Mini Code medium | Cohere | 1 | 0.5 | $0.000 | 8/23 | 140.4s |
| #326 | Hy4 preview low | Tencent | 5 | 0.5 | $1.844 | 3/23 | 207.2s |
| #328 | Step 3.5 Flash medium | Stepfun | 1 | 0.5 | $0.105 | 10/22 | 190.5s |
| #329 | Ember-1 none | Fireworks | 5 | 0.5 | $0.786 | 8/23 | 22.6s |
| #330 | Hy3 preview medium | Tencent | 3 | 0.5 | $0.049 | 14/21 | 16.3s |
| #336 | Qwen3.6 35B A3B none | Qwen | 2 | 0.5 | $0.105 | 4/23 | 8.43s |
| #337 | Inkling Small low | Thinkingmachines | 1 | 0.5 | $0.055 | 9/23 | 1.99s |