CoS-VQ BF16 - IFEval Prompt Strict: leaderboard
The CoS-VQ study reports these reference results for unquantized models on language modeling and zero-shot questions. Lower perplexity is better. Prompt-level strict accuracy (%).
Metric: Prompt-level strict accuracy (%). Source: arxiv.org. Saturation forecast: Estimated already saturated. 2 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Llama 3.1 70B Instruct | 83.55 | #559 |
| 2 | Llama 3.1 8B Instruct | 73.94 | #1035 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=cos-vq-bf16-ifeval-prompt-strict · How It Works · Data refreshed daily, snapshot 2026-10-29.