WEval - Prompt-Level: leaderboard
WEval (2026) tests writing reward models and LLM judges on ranking candidate responses by how many of the specific requirements of a writing instruction each one satisfies. This board is the share of instructions, in percent, whose predicted ranking matches the gold ranking exactly; higher is better.
Metric: Prompt-level accuracy (%: share of instructions whose predicted ranking of the five responses equals the gold ranking exactly); WEval writing reward-model test: 2,750 writing instructions with five requirements each; for every instruction DeepSeek-R1 answers the full instruction and versions with 1 to 4 requirements dropped, and the gold ranking orders the five responses by how many requirements were kept; LLMs are prompted to rank the responses, reward models score them; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 5 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 2.5 72B Instruct | 78.7 | #1117 |
| 2 | Qwen 2.5 7B Instruct | 60.9 | #2723 |
| 3 | Skywork-Reward-V2-Qwen3-8B | 45.3 | |
| 4 | Writing-Critic-7B | 42.7 | |
| 5 | Skywork-Reward-V2-Llama-3.1-8B | 32.9 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=weval-prompt-level · How It Works · Data refreshed daily, snapshot 2026-11-21.