Fiction Eval leaderboard · comparison

Claude Sonnet 4.6 vs GLM 5.2 for fiction writing

Judged blind on fresh genre scenes (LitRPG, cozy mystery, romance, thriller, xianxia…), July 2026 — three tries per model per scene, passages shown in both orders so position can't sway it, graded by a third AI that isn't either of them.

Head-to-head

Claude Sonnet 4.6 won the direct matchup 14–2 (with 13 ties) across every prompt and sample.

#ModelScoreRecordSlop
2Claude Sonnet 4.61914 (likely 1874–1961)146–15–4618.57
4GLM 5.21776 (likely 1732–1822)117–42–4217.53

The score is each model's overall strength across the whole 8-model field (like a chess rating); the range next to it is where the true score most likely sits. Slop is a separate count of AI tells (lower is cleaner) — it isn't part of the ranking.

The same scene, both models

Romance — opening of the "romance turn" scene. Full passages for all models are on the board.

Claude Sonnet 4.6:

The inventory had to be done by morning, and Reyes had locked them both in. Mara set another box on the folding table. Marcus didn't look up from his clipboard. The fluorescent light above them had been flickering for twenty minutes and neither of them had mentioned it. "Twelve boxes of the archive files," she said. "I have eleven." "Count again." He counted again. "Twelve." She pulled the next box. He made the mark. Outside, the building had gone completely quiet—the cleaning crew, the last of the associates, everyone gone home. The clock on the wall said 11:40. "You always do that," Marcus said. "Do what." "Say *count again* before I've even had a chance to—" He stopped. Made another mark. Mara lifted a box that was heavier than it looked and found her footing before she'd quite found her footing. She didn't drop it. Marcus had half-risen from his stool, one hand out, and when she steadied he sat back down and looked at his clipboard like it had …

GLM 5.2:

# The Inventory "You're counting wrong again." "I'm counting *correctly*. You're reading the sheet wrong." Mara shoved the clipboard at him. Dev took it, scanned the numbers, and shoved it back. They'd been in the stockroom for two hours. Two hours of fluorescent hum and dust and Dev's shoulder bumping hers every time he reached for the next shelf, which he was doing on purpose, she was sure of it, because he did everything on purpose. "Row seventeen," she said. "Fourteen units." "Twelve." "Dev. I can *see* fourteen boxes." "I can see fifteen. You miscounted." She turned to face him. He was already facing her, because of course he was. His eyes dropped to the clipboard in her hands, then back up. "Write down fourteen," she said. "Write down fifteen." "You're impossible." "You're stubborn." Those words had weight. They always had weight, between them. In the courtroom they landed like blows — her client's interests against his, his arguments against hers, each one sharpened to cut. Here, in the stockroom, …

More

Claude Sonnet 4.6 full review · GLM 5.2 full review · the July 2026 report · all comparisons

How it works: every pair of models is judged blind on the same scene, with the passages' order flipped so being shown first can't sway it, by GPT-5.4 — a family that isn't on the board, so nobody scores their own side. Each score carries a likely range; overlapping ranges are called a tie. Slop is scored separately by a fixed checklist, not an AI. Full board, every prompt, and the FAQ: thebookfactoryai.com/board. Get each new board by email on the model-drop list.

Writing a book of your own? Book Factory runs the same craft checks on full manuscripts.