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

#ModelScoreOverall rank
1Qwen 2.5 72B Instruct78.7#1117
2Qwen 2.5 7B Instruct60.9#2723
3Skywork-Reward-V2-Qwen3-8B45.3
4Writing-Critic-7B42.7
5Skywork-Reward-V2-Llama-3.1-8B32.9

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.