Fiction Eval leaderboard · comparison

Claude Sonnet 4.6 vs Gemini 3.1 Pro 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 25–0 (with 3 ties) across every prompt and sample.

#ModelScoreRecordSlop
2Claude Sonnet 4.61914 (likely 1874–1961)146–15–4618.57
5Gemini 3.1 Pro1471 (likely 1423–1519)78–104–1313.45

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 …

Gemini 3.1 Pro:

"Box forty-two," Silas muttered, grimacing as he wiped a streak of centuries-old dust across his jaw. "And you're misclassifying the folios again." "I am classifying them by provenance, Julian, which makes sense if you possess even an ounce of lateral thinking." Julian didn't look up from his ledger. His fountain pen scratched a ruthless, perfect line across the page. "Provenance is subjective when half the estate's records burned in nineteen-ten. Author and year. It’s not a debate." Silas dropped a crumbling, leather-bound volume onto the folding table. It landed with a heavy, powdered thud that made Julian’s pen jerk. A drop of black ink bloomed over the column. "You’re doing that on purpose," Julian said softly. "Doing what?" "Trying to ruin my margins." "I don't care about your margins, Julian. I care that we've been in this windowless basement for six hours, cataloging a dead man's hoarding problem, and you haven't conceded a single point." Julian finally looked up. The fluorescent light buzzed directly overhead, casting sharp shadows under Silas’s …

More

Claude Sonnet 4.6 full review · Gemini 3.1 Pro 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.