Fiction Eval leaderboard · comparison

Claude Sonnet 4.6 vs Grok 4.3 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 12–5 (with 13 ties) across every prompt and sample.

#ModelScoreRecordSlop
2Claude Sonnet 4.61914 (likely 1874–1961)146–15–4618.57
3Grok 4.31856 (likely 1815–1899)137–28–429.43

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 …

Grok 4.3:

The last of the posters slid into the box with a papery sigh. Elena flattened the flaps, the cardboard rasping under her palms. Across the narrow table Marcus counted out the rubber bands in neat stacks, his movements precise, the same way he’d once corrected her margins in front of the whole room. “Forty-three short,” he said. She didn’t look up. “You miscounted.” He set another band down, slower this time. “I don’t miscount.” The stockroom hummed with the fluorescent light. Somewhere above them a vacuum started and stopped. Elena reached for the next stack; her sleeve caught the corner of his sorted pile and sent three bands skittering across the laminate. Marcus didn’t move to retrieve them. Instead he watched the small black circles roll until they stopped against her wrist. “You always do that,” he said quietly. “Do what.” “Make more work than there needs to be.” Elena’s fingers stayed on the edge of the box. The rubber against her skin was cool, then warm where his gaze …

More

Claude Sonnet 4.6 full review · Grok 4.3 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.