JSON Schema Generation on JSON Schema (test)
96.4AccuracyBest Local f-Ens.
Evaluation Results
| Method | Links | |
|---|---|---|
| Best Local f-Ens.Base Model=Qwen2026.03 | 96.4 | |
| Best Global f-Ens.Base Model=Qwen, SMC Type=Token SMC, M=102026.03 | 96 | |
| Best Global f-Ens.Base Model=Qwen, SMC Type=Token SMC, M=252026.03 | 95.8 | |
| Prompt 1Base Model=Qwen2026.03 | 95.6 | |
| Local Prob. Avg.Base Model=Qwen2026.03 | 95.2 | |
| Prompt 2Base Model=Qwen2026.03 | 93.8 | |
| Best Global f-Ens.Base Model=Qwen, SMC Type=Byte SMC, M=102026.03 | 92.8 | |
| Best Cross-Model f-Ens.Base Models=Q+P, SMC Type=Byte SMC, M=10, Prompt=Prompt 12026.03 | 92.6 | |
| Best Global f-Ens.Base Model=Llama, SMC Type=Token SMC, M=252026.03 | 89.1 | |
| Best Global f-Ens.Base Model=Llama, SMC Type=Token SMC, M=102026.03 | 88.9 | |
| Best Global f-Ens.Base Model=Llama, SMC Type=Byte SMC, M=102026.03 | 88.9 | |
| Best Local f-Ens.Base Model=Llama2026.03 | 88.6 | |
| Best Global f-Ens.Base Model=Phi, SMC Type=Token SMC, M=252026.03 | 87.8 | |
| Best Global f-Ens.Base Model=Phi, SMC Type=Byte SMC, M=102026.03 | 87.5 | |
| Best Global f-Ens.Base Model=Phi, SMC Type=Token SMC, M=102026.03 | 87.4 | |
| Best Local f-Ens.Base Model=Phi2026.03 | 87.2 | |
| Prompt 1Base Model=Llama2026.03 | 86.3 | |
| Prompt 2Base Model=Llama2026.03 | 84.3 | |
| Prompt 1Base Model=Phi2026.03 | 83.5 | |
| Local Prob. Avg.Base Model=Llama2026.03 | 83.4 | |
| Local Prob. Avg.Base Model=Phi2026.03 | 82 | |
| Prompt 2Base Model=Phi2026.03 | 79.5 |