Tool Calling on ToolCall-15
63AccuracyNemotron-Super-120B
Evaluation Results
| Method | Links | |
|---|---|---|
| Nemotron-Super-120BDeployment=Local model2026.05 | 63 | |
| Best LocalConfig=Oracle local routing frontier2026.05 | 63 | |
| Qwen3.5-35BDeployment=Local model2026.05 | 60 | |
| Qwen3.5-122BDeployment=Local model2026.05 | 60 | |
| Claude Opus 4.6Deployment=Cloud baseline2026.05 | 53.3 | |
| Gemini 3.1 ProDeployment=Cloud baseline2026.05 | 53.3 | |
| Qwen3.5-9BDeployment=Local model2026.05 | 53.3 | |
| Qwen3.5-27BDeployment=Local model2026.05 | 53.3 | |
| Granite 3.3 8BDeployment=Local model2026.05 | 49 | |
| GPT 5.4Deployment=Cloud baseline2026.05 | 46.6 | |
| Granite 4.0 H-SmallDeployment=Local model2026.05 | 42 | |
| Gemma4-E4BDeployment=Local model2026.05 | 28 | |
| Gemma4-26BDeployment=Local model2026.05 | 28 |