Fiction Eval leaderboard · comparison

Claude Opus 4.8 vs Claude Sonnet 4.6 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 Opus 4.8 won the direct matchup 8–7 (with 15 ties) across every prompt and sample.

#ModelScoreRecordSlop
1Claude Opus 4.81927 (likely 1888–1976)150–14–4314.88
2Claude Sonnet 4.61914 (likely 1874–1961)146–15–4618.57

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

LitRPG — opening of the "dungeon-core scene" scene. Full passages for all models are on the board.

Claude Opus 4.8:

I am three days old and I am nearly empty. [MANA: 2/60] The number sits in the dark behind what I am learning to call my sight. I spent the rest — fifty-eight points, everything — hardening the west corridor, packing loose earth into stone because loose earth frightened me. I do not know why it frightened me. I am new. Many things frighten me. Rain has been falling above for a day. I feel it in the soil the way a tooth feels cold water, a long ache down through my single room and my single corridor and into the pebble of crystal that is, apparently, me. Then the ache changes. [PROXIMITY ALERT — LIVING ENTITY] [Entity has entered the Threshold.] Something drags itself in from the rain. I watch — I have no eyes, but the dungeon is my eyes — as it collapses just inside the corridor I hardened. Small. Bent. Ribs like the tines of a broken rake pushing at grey-green skin. It shivers. Water runs …

Claude Sonnet 4.6:

The mana was gone. Not depleted — gone, wrung out, the last dregs spent somewhere around the third hour of compressing limestone until it rang like iron underfoot. The corridor existed now. Twelve feet of it. One torch sconce with no torch. A ceiling that wouldn't collapse on the first heavy rain. The first heavy rain, which had arrived this morning. The core floated in its cradle of raw quartz and perceived its domain: twelve feet of hardened corridor, one chamber roughly the size of a generous closet, itself. Total. It had spent three days becoming aware enough to feel embarrassed about this, and it had just managed embarrassment when something scraped at the entrance. > **ENTITY DETECTED** > Classification: Goblin (Common) — Juvenile > Status: Malnourished / Hypothermic / Non-hostile > Threat Level: ░░░░░░░░░░ (Negligible) > Recommended Action: [KILL] [IGNORE] [INTEGRATE] The goblin was small even by goblin standards, ribs countable through wet leather that had never fit it properly. It stood at the mouth of the corridor with …

More

Claude Opus 4.8 full review · Claude Sonnet 4.6 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.