Docbench - SVG Subject Fidelity: leaderboard
Docbench in Gezel: fixed document-task adapters, parser/repair/retry behavior, native checks plus Claude Opus 5.5 rubric judge. Unusable outputs score zero. 32, 768 context except Apple 8, 192. Mostly Q4 is not affirmative precision evidence for each row; preserve explicit Q2/Q4 only. CLI/API labels are run configuration, not distinct public models. Native Apple Foundation Models row retained in pinned capture but not emitted until exact checkpoint identity is established. LLM-generated SVG/code and structured diagram outputs in the document workflow; source's native subject/composition rubrics and units, not image-model generation throughput. Metric: Native rubric score (0–10). Source: https://bendyline.com/posts/docbench.html
Metric: Native rubric score (0–10). Source: bendyline.com. Saturation forecast: Around February 2027. 10 models tracked. Updated 17 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.6 35B A3B | 6.3 | #484 |
| 2 | Qwen 3.8 27B (Q4) | 6.3 | |
| 3 | Gemma 4 12B | 5.1 | #931 |
| 4 | GPT-OSS-20B | 4.9 | #1163 |
| 5 | Gemma 4 E4B | 3.9 | #2142 |
| 6 | Qwen 3.5 4B | 3 | #1227 |
| 7 | Gemma 4 E2B | 2.3 | #4291 |
| 8 | LFM3-1.7B | 2.1 | #2069 |
| 9 | Qwen 3.5 0.8B | 1 | #8136 |
| 10 | MiniCPM5-1B | 0 | #9079 |
No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.
Interactive version: theaggregate.ai/benchmark?slug=docbench-svg-subject-fidelity · How It Works · Data refreshed daily, snapshot 2026-11-17.