Agent Performance on ACEBench-zh
89.6AccuracyERNIE 5.0
Evaluation Results
| Method | Links | |
|---|---|---|
| ERNIE 5.02026.02 | 89.6 | |
| Gemini 2.5-Pro2026.02 | 87.5 | |
| Gemini 3-Pro2026.02 | 85 | |
| GPT-5 (High)2026.02 | 83.6 | |
| DS V3.2-Thinking2026.02 | 83.4 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| ERNIE 5.02026.02 | 89.6 | |
| Gemini 2.5-Pro2026.02 | 87.5 | |
| Gemini 3-Pro2026.02 | 85 | |
| GPT-5 (High)2026.02 | 83.6 | |
| DS V3.2-Thinking2026.02 | 83.4 |