List your company

JSON Generation on JSON-mode-eval e=1.1

100Syntax AccuracyTruncProof
-2.9623.7750.577.23May 13, 2026

Evaluation results

MethodLinks
TruncProofBackbone=Gemma2-2B, Decoding Strategy=Greedy, Prompt Engineering=False2026.05100622125.73.9
TruncProofBackbone=Gemma2-2B, Decoding Strategy=BS, Prompt Engineering=False2026.05100853760.839
TruncProofBackbone=Gemma2-2B, Decoding Strategy=MCTS, Prompt Engineering=False2026.051008658518.1496.3
TruncProofBackbone=Llama2-7B-Chat-HF, Decoding Strategy=Greedy, Prompt Engineering=False2026.05100512191.4
TruncProofBackbone=Llama2-7B-Chat-HF, Decoding Strategy=BS, Prompt Engineering=False2026.0510067293719.4
TruncProofBackbone=Llama2-7B-Chat-HF, Decoding Strategy=MCTS, Prompt Engineering=False2026.051007041209.2191.6
OutlinesBackbone=Gemma2-2B, Decoding Strategy=Greedy, Prompt Engineering=False2026.05363322458.7436.9
OutlinesBackbone=Llama2-7B-Chat-HF, Decoding Strategy=Greedy, Prompt Engineering=True2026.0519175——
OutlinesBackbone=Llama2-7B-Chat-HF, Decoding Strategy=Greedy, Prompt Engineering=False2026.051813472.254.6
OutlinesBackbone=Gemma2-2B, Decoding Strategy=Greedy, Prompt Engineering=True2026.0517178——
SynCodeBackbone=Llama2-7B-Chat-HF, Decoding Strategy=Greedy, Prompt Engineering=True2026.0516145——
XGrammarBackbone=Llama2-7B-Chat-HF, Decoding Strategy=Greedy, Prompt Engineering=True2026.0516133——
SynCodeBackbone=Llama2-7B-Chat-HF, Decoding Strategy=Greedy, Prompt Engineering=False2026.051110418.40.8
XGrammarBackbone=Llama2-7B-Chat-HF, Decoding Strategy=Greedy, Prompt Engineering=False2026.05119218.30.7
OutlinesBackbone=Llama2-7B-Chat-HF, Decoding Strategy=BS, Prompt Engineering=False2026.051084598.8581.2
XGrammarBackbone=Llama2-7B-Chat-HF, Decoding Strategy=MCTS, Prompt Engineering=False2026.05983175.1157.5
No constraintBackbone=Gemma2-2B, Decoding Strategy=Greedy, Prompt Engineering=True2026.05884——
XGrammarBackbone=Gemma2-2B, Decoding Strategy=Greedy, Prompt Engineering=True2026.05884——
SynCodeBackbone=Llama2-7B-Chat-HF, Decoding Strategy=MCTS, Prompt Engineering=False2026.05884183.5165.9
SynCodeBackbone=Gemma2-2B, Decoding Strategy=Greedy, Prompt Engineering=True2026.05661——
SynCodeBackbone=Llama2-7B-Chat-HF, Decoding Strategy=BS, Prompt Engineering=False2026.0566458.741.1
XGrammarBackbone=Gemma2-2B, Decoding Strategy=Greedy, Prompt Engineering=False2026.0555322.10.3
XGrammarBackbone=Gemma2-2B, Decoding Strategy=MCTS, Prompt Engineering=False2026.05552293.3271.5
XGrammarBackbone=Llama2-7B-Chat-HF, Decoding Strategy=BS, Prompt Engineering=False2026.0553232.514.9
OutlinesBackbone=Gemma2-2B, Decoding Strategy=BS, Prompt Engineering=False2026.054424,347.84,326
SynCodeBackbone=Gemma2-2B, Decoding Strategy=Greedy, Prompt Engineering=False2026.0543023.51.7
SynCodeBackbone=Gemma2-2B, Decoding Strategy=MCTS, Prompt Engineering=False2026.05440438.6416.8
No constraintBackbone=Llama2-7B-Chat-HF, Decoding Strategy=Greedy, Prompt Engineering=False2026.0522017.6—
No constraintBackbone=Llama2-7B-Chat-HF, Decoding Strategy=Greedy, Prompt Engineering=True2026.05220——
No constraintBackbone=Gemma2-2B, Decoding Strategy=Greedy, Prompt Engineering=False2026.0511021.8—
SynCodeBackbone=Gemma2-2B, Decoding Strategy=BS, Prompt Engineering=False2026.051105432.2
XGrammarBackbone=Gemma2-2B, Decoding Strategy=BS, Prompt Engineering=False2026.0511034.312.5