List your company

JSON Schema Generation on JSON Schema (test)

96.4AccuracyBest Local f-Ens.
78.82483.38787.9592.513Mar 5, 2026

Evaluation results

MethodLinks
Best Local f-Ens.Base Model=Qwen2026.0396.4
Best Global f-Ens.Base Model=Qwen, SMC Type=Token SMC, M=102026.0396
Best Global f-Ens.Base Model=Qwen, SMC Type=Token SMC, M=252026.0395.8
Prompt 1Base Model=Qwen2026.0395.6
Local Prob. Avg.Base Model=Qwen2026.0395.2
Prompt 2Base Model=Qwen2026.0393.8
Best Global f-Ens.Base Model=Qwen, SMC Type=Byte SMC, M=102026.0392.8
Best Cross-Model f-Ens.Base Models=Q+P, SMC Type=Byte SMC, M=10, Prompt=Prompt 12026.0392.6
Best Global f-Ens.Base Model=Llama, SMC Type=Token SMC, M=252026.0389.1
Best Global f-Ens.Base Model=Llama, SMC Type=Token SMC, M=102026.0388.9
Best Global f-Ens.Base Model=Llama, SMC Type=Byte SMC, M=102026.0388.9
Best Local f-Ens.Base Model=Llama2026.0388.6
Best Global f-Ens.Base Model=Phi, SMC Type=Token SMC, M=252026.0387.8
Best Global f-Ens.Base Model=Phi, SMC Type=Byte SMC, M=102026.0387.5
Best Global f-Ens.Base Model=Phi, SMC Type=Token SMC, M=102026.0387.4
Best Local f-Ens.Base Model=Phi2026.0387.2
Prompt 1Base Model=Llama2026.0386.3
Prompt 2Base Model=Llama2026.0384.3
Prompt 1Base Model=Phi2026.0383.5
Local Prob. Avg.Base Model=Llama2026.0383.4
Local Prob. Avg.Base Model=Phi2026.0382
Prompt 2Base Model=Phi2026.0379.5