Combined: Invalid tool call
Combined
Invalid tool call
See which AI models are most likely to hit Invalid tool call on Combined, so you can spot weak points faster. Sort by: Total Cost ↓.
Failure Reasons
Categories
128/128
Filter models
No models match the current search and filters.
| Rank | Model | Company | Invalid tool call Count | Category Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #22 | Gemini 3.8 Flash medium | 1 | 8.7 | $0.653 | 1/2 | 60.3s | |
| #174 | Gemini 3.1 Flash Lite Preview low | 1 | 3.0 | $0.646 | 0/2 | 160.6s | |
| #209 | Trinity Large Thinking low | Arcee AI | 2 | 5.2 | $0.625 | 0/2 | 291.0s |
| #176 | Gemini 3.1 Flash Lite low | 1 | 3.2 | $0.621 | 0/2 | 161.2s | |
| #289 | Trinity Large Thinking high | Arcee AI | 2 | 3.0 | $0.592 | 0/2 | 262.4s |
| #180 | Qwen3.6 27B medium | Qwen | 2 | 6.7 | $0.577 | 0/2 | 584.1s |
| #130 | KAT-Coder-Pro V2.5 high | Kwaipilot | 1 | 7.3 | $0.506 | 1/2 | 106.7s |
| #81 | Step 3.7 Flash medium | Stepfun | 1 | 7.3 | $0.495 | 1/2 | 80.9s |
| #166 | KAT-Coder-Pro V2.5 none | Kwaipilot | 1 | 4.1 | $0.487 | 0/2 | 183.1s |
| #148 | Kimi K2.5 medium | Moonshot AI | 1 | 6.7 | $0.479 | 1/2 | 89.2s |
| #71 | Muse Glimmer 30B xhigh | Meta | 1 | 6.0 | $0.471 | 0/2 | 272.7s |
| #107 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 1 | 6.9 | $0.459 | 1/2 | 175.8s |
| #169 | GLM 5V Turbo medium | Z.ai | 1 | 3.4 | $0.457 | 0/1 | 15.1s |
| #36 | Gemini 3.5 Flash low | 1 | 8.2 | $0.449 | 1/2 | 30.0s | |
| #104 | GPT-5.6 Terra low | OpenAI | 1 | 8.7 | $0.420 | 1/2 | 9.68s |