CalBench - Varied Costs - Burden Unfairness: leaderboard
Metric: Burden unfairness (standard deviation). Source: arxiv.org. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 4 Maverick Instruct | 0.63 |
| 2 | Qwen 3.6 Plus | 0.66 |
| 3 | Gemini 3 Flash (Preview) | 0.72 |
| 4 | Gemini 3.1 Pro (Preview) | 0.75 |
| 5 | Claude Sonnet 4.6 | 0.91 |
| 6 | DeepSeek V4 Pro | 0.96 |
| 7 | GPT-5.4 Mini | 1.38 |
Interactive version: theaggregate.ai/benchmark?slug=calbench-varied-costs-burden-unfairness · How It Works · Data refreshed daily, snapshot 2026-09-19.