Tool Use on LG Agentic Eval
5.04Tool Use ScoreClaude 3.7 Sonnet
Evaluation Results
| Method | Links | |
|---|---|---|
| Claude 3.7 SonnetContext Window=32k2026.06 | 5.04 | |
| LuckyStar 111BContext Window=32k2026.06 | 4.85 | |
| Qwen3 235B A22BContext Window=32k2026.06 | 3.29 | |
| Command AContext Window=32k2026.06 | 2.67 | |
| GPT-4o (11/20)Context Window=32k2026.06 | 2.56 |