SchemaBridge Direct Gold Text - RSchema Hallucination: leaderboard
SchemaBridge evaluates relational-schema design, description and reconstruction. Experiment-specific cohorts retain their own populations. Graph edit distance, hallucination, structural F1, text similarity and identifier coverage are distinct measurements. Round-trip runs use a fixed GPT-4o Mini constructor with each named describer. This board reports four-dimensional hallucination ratio (0-1). Lower is better.
Metric: Four-dimensional hallucination ratio (0-1). Source: arxiv.org. Saturation forecast: Around 2032. 8 models tracked. Updated 14 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | deepseek-coder-6.7b-instruct | SchemaBridge run: Few-shot | 0.582 | |
| 2 | CodeLlama-13b-Instruct-hf | SchemaBridge run: Few-shot | 0.589 | |
| 3 | deepseek-coder-6.7B-instruct | 0.595 | #7426 | |
| 4 | GPT-5.4 Mini | 0.605 | #398 | |
| 5 | Claude Sonnet 4.6 | 0.635 | #165 | |
| 6 | Meta-Llama-3.1-8B-Instruct | SchemaBridge run: Few-shot | 0.638 | |
| 7 | CodeLlama-13B-Instruct-hf | 0.669 | #9043 | |
| 8 | Llama 3.1 8B Instruct | 0.696 | #4545 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=schemabridge-direct-gold-text-rschema-hallucination · How It Works · Data refreshed daily, snapshot 2026-11-16.