Tool Calling: API error
Tool Calling
API error
See which AI models are most likely to hit API error on Tool Calling, so you can spot weak points faster. Sort by: Total Cost ↑.
Failure Reasons
39/39
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) |
|---|---|---|---|---|---|---|---|
| #417 | Command A+ none | Cohere | 1 | 0.3 | $0.000 | 0/1 | 81.9s |
| #420 | Nemotron 3 Nano Omni 30b A3b Reasoning medium | NVIDIA | 1 | 0.3 | $0.000 | 0/1 | 0ms |
| #422 | Nemotron 3 Nano Omni 30b A3b Reasoning default | NVIDIA | 1 | 0.3 | $0.000 | 0/1 | 0ms |
| #436 | LFM2-24B-A2B default | Liquid | 1 | 0.3 | $0.001 | 0/1 | 0ms |
| #341 | Mercury 2.5 Preview low | Inception | 1 | 0.3 | $0.015 | 0/1 | 1.57s |
| #386 | gpt-oss-120b none | OpenAI | 1 | 0.3 | $0.016 | 0/1 | 0ms |
| #433 | Step 3.5 Flash none | Stepfun | 1 | 0.3 | $0.020 | 0/1 | 0ms |
| #375 | Ring 2.6 1t default | Inclusionai | 1 | 0.3 | $0.026 | 0/1 | 0ms |
| #298 | Gemma 4 31B none | 1 | 0.3 | $0.031 | 0/1 | 0ms | |
| #199 | Mercury 2.5 Preview medium | Inception | 1 | 0.3 | $0.039 | 0/1 | 2.37s |
| #224 | Mercury 2.5 Preview high | Inception | 1 | 0.3 | $0.040 | 0/1 | 2.25s |
| #374 | Hy3 preview low | Tencent | 1 | 0.3 | $0.042 | 0/1 | 17.8s |
| #408 | Command A+ medium | Cohere | 1 | 0.3 | $0.064 | 0/1 | 78.4s |
| #167 | Qwen3.8 27B medium | Qwen | 1 | 0.3 | ~$0.073 | 0/1 | 0ms |
| #418 | Command A+ low | Cohere | 1 | 0.3 | $0.073 | 0/1 | 99.7s |