IBA-Bench - Writing and Design: leaderboard
Metric: Checkpoint satisfaction (%; share of hidden preference checkpoints satisfied by the final action, writing and design domain; mean of three LLM judges: DeepSeek-V3.2, Qwen3-4B-Instruct and Qwen3-30B-A3B-Instruct; retrieval-augmented baseline with bge-m3 top-3 chunks). Source: arxiv.org. Saturation forecast: Around December 2026. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.1 | 72.9 |
| 2 | GPT-5 Mini | 70.5 |
| 3 | QwQ-32B | 68.7 |
| 4 | DeepSeek V3.2 | 68.1 |
| 5 | Qwen 3 4B Instruct | 65.2 |
| 6 | DeepSeek V3 | 65.1 |
| 7 | GPT-4o | 63.5 |
| 8 | GPT-4o Mini | 57.7 |
| 9 | Qwen 2.5 7B Instruct | 52.7 |
| 10 | GLM-4 9B Chat | 51.4 |
Interactive version: theaggregate.ai/benchmark?slug=iba-bench-writing-and-design · How It Works · Data refreshed daily, snapshot 2026-09-26.