ZoomGain Release Evaluation - HR 4K: leaderboard
ZoomGain Release Evaluation - HR 4K: Native benchmark accuracy or held-out macro mean (%). ZoomGain arXiv 2611.14076v1: ZoomGainBench bilingual fine-grained perception scores, weighted within-language by category counts. Table 3 author experiments train Qwen3.5-4B and 9B on 9K ZoomGain samples; official inclusionAI release identifies them as ZoomGain-4B/9B. ZwZ-retrained controls do not identify released checkpoints and are held. Table 3 Gemini-3-Flash (51.27) conflicts with Table 2 Gemini-3.6-Flash; that row is held, never inferred equivalent. Qwen3-VL labels are held absent Instruct/Thinking binding. Other source-named released models retain their exact labels and unreported effort.
Metric: Native benchmark accuracy or held-out macro mean (%). Source: arxiv.org. Saturation forecast: Around February 2027. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GLM-5.3 Flash | 87 | #119 |
| 2 | Qwen 3.5 397B A17B | 86.5 | #242 |
| 3 | Qwen 3.5 122B A10B | 86.5 | #329 |
| 4 | Qwen 3.5 9B | 82.13 | #803 |
| 5 | Qwen 3.5 4B | 81.25 | #1180 |
| 6 | GPT-5.1 | 67 | #225 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=zoomgain-release-evaluation-hr-4k · How It Works · Data refreshed daily, snapshot 2026-11-12.