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. Sort by: Tests Correct ↑.
Failure Reasons
Categories
51/51
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) |
|---|---|---|---|---|---|---|---|
| #105 | Qwen3.8 Max (0902) low | Qwen | 1 | 0.6 | $1.131 | 0/1 | 136.0s |
| #121 | Particle-1 high | Particle AI | 1 | 0.6 | $0.170 | 0/1 | 54.8s |
| #124 | Ernie 5.5 Flash Preview high | Baidu | 1 | 0.6 | $0.000 | 0/1 | 64.0s |
| #127 | Gemini 3.5 Flash high | 1 | 0.3 | $2.737 | 0/1 | 87.3s | |
| #140 | Kimi K3.1 Pro high | Moonshot AI | 1 | 0.7 | $1.646 | 0/1 | 93.4s |
| #143 | Claude Opus 4.7 medium | Anthropic | 1 | 0.5 | $3.636 | 0/1 | 150.6s |
| #153 | GLM 5.3 FlashX max | Z.ai | 1 | 0.6 | $0.623 | 0/1 | 104.8s |
| #159 | Gemini 3.5 Flash medium | 1 | 0.3 | $1.316 | 0/1 | 84.5s | |
| #173 | GPT-6 Luna high | OpenAI | 1 | 0.5 | $0.074 | 0/1 | 82.8s |
| #189 | GPT-5.6 Luna medium | OpenAI | 1 | 0.7 | $0.065 | 0/1 | 58.1s |
| #197 | Inkling medium | Thinkingmachines | 1 | 0.5 | $0.527 | 0/1 | 45.9s |
| #205 | Gemini 3.5 Flash Lite medium | 1 | 0.5 | $0.440 | 0/1 | 86.9s | |
| #215 | Step 3.7 Flash low | Stepfun | 1 | 0.7 | $0.449 | 0/1 | 83.6s |
| #227 | Ember-1 low | Fireworks | 1 | 0.5 | $1.488 | 0/1 | 121.3s |
| #229 | Qwen3.5-122B-A10B medium | Qwen | 1 | 0.6 | $1.152 | 0/1 | 95.3s |