Agentic: Invalid tool call
Agentic
Invalid tool call
See which AI models are most likely to hit Invalid tool call on Agentic, so you can spot weak points faster.
Failure Reasons
Categories
44/44
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) |
|---|---|---|---|---|---|---|---|
| #46 | Claude Opus 5 medium | Anthropic | 1 | 7.4 | $2.896 | 0/1 | 87.6s |
| #52 | Gemini 3.7 Flash low | 1 | 6.4 | $0.293 | 0/1 | 62.6s | |
| #61 | Qwen3.8 Max (0902) low | Qwen | 1 | 6.1 | $1.131 | 0/1 | 136.0s |
| #67 | Gemini 3.5 Flash high | 1 | 4.1 | $2.672 | 0/1 | 84.7s | |
| #85 | Claude Sonnet 5.5 high | Anthropic | 1 | 7.4 | $1.197 | 0/1 | 53.6s |
| #87 | Claude Opus 4.7 medium | Anthropic | 1 | 5.2 | $3.636 | 0/1 | 150.6s |
| #89 | Gemini 3.5 Flash medium | 1 | 3.8 | $1.308 | 0/1 | 83.6s | |
| #97 | GLM 5.3 FlashX max | Z.ai | 1 | 6.1 | $0.623 | 0/1 | 104.8s |
| #106 | GPT-6 Luna medium | OpenAI | 1 | 7.4 | $0.048 | 0/1 | 71.7s |
| #110 | GPT-6 Luna high | OpenAI | 1 | 5.2 | $0.074 | 0/1 | 82.8s |
| #121 | GPT-5.4 Mini medium | OpenAI | 1 | 7.4 | $0.965 | 0/1 | 84.3s |
| #122 | GPT-5.6 Luna medium | OpenAI | 1 | 7.4 | $0.101 | 0/1 | 58.1s |
| #130 | Inkling medium | Thinkingmachines | 1 | 4.7 | $0.540 | 0/1 | 45.9s |
| #138 | Gemini 3.5 Flash Lite medium | 1 | 4.7 | $0.440 | 0/1 | 86.9s | |
| #146 | Step 3.7 Flash low | Stepfun | 1 | 7.4 | $0.449 | 0/1 | 83.6s |