Tool Use on τ²-Bench telecom
98.7ScoreGPT-5.2 High
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-5.2 High2026.06 | 98.7 | |
| Claude-Opus-4.52026.06 | 98.2 | |
| Claude-Sonnet-4.52026.06 | 98 | |
| Gemini-3-pro High2026.06 | 98 | |
| Gemini-3-Flash High2026.06 | 94.7 | |
| Seed2.0 Pro2026.06 | 94.2 | |
| Seed2.0 Lite2026.06 | 92.1 |