DTBench - Indirect Extraction Recall: leaderboard
Metric: Recall (%) on DTBench's 4,518 capability-demanding ground-truth cells (values needing transformation, reasoning, distractor robustness, faithfulness to missing evidence or conflict resolution), exact match after normalization and row alignment; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash | 80.9 | #93 |
| 2 | GPT-5 | 75.12 | #91 |
| 3 | DeepSeek V3.2 | 74.91 | #198 |
| 4 | GPT-5 Mini | 73.88 | #176 |
| 5 | Qwen 3 32B | 43.25 | #424 |
| 6 | Qwen 3 4B | 19.33 | #823 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=dtbench-indirect-extraction-recall · How It Works · Data refreshed daily, snapshot 2026-10-11.