IBA-Bench - Exercise and Health: leaderboard
Metric: Checkpoint satisfaction (%; share of hidden preference checkpoints satisfied by the final action, exercise and health 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 March 2027. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 Mini | 78.3 |
| 2 | QwQ-32B | 75.2 |
| 3 | GPT-5.1 | 73.9 |
| 4 | Qwen 3 4B Instruct | 73.4 |
| 5 | DeepSeek V3.2 | 72.2 |
| 6 | DeepSeek V3 | 71.4 |
| 7 | GPT-4o | 69.5 |
| 8 | GPT-4o Mini | 68.1 |
| 9 | Qwen 2.5 7B Instruct | 67.1 |
| 10 | GLM-4 9B Chat | 65.4 |
Interactive version: theaggregate.ai/benchmark?slug=iba-bench-exercise-and-health · How It Works · Data refreshed daily, snapshot 2026-09-26.