Fiction Eval leaderboard · comparison

Claude Opus 4.8 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 Opus 4.8 won the direct matchup 10–5 (with 15 ties) across every prompt and sample.

#ModelScoreRecordSlop
1Claude Opus 4.81927 (likely 1888–1976)150–14–4314.88
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

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 …

Grok 4.3:

The crystal hung in its alcove, three days formed and still learning the weight of being. Mana trickled through its facets in thin, uncertain pulses. The last of it had gone into the corridor an hour ago—rough walls pulled tight, floor smoothed just enough that claws would not slip. The expenditure left it hollow. It did not yet have language for the feeling, only the absence. Rain hissed outside the cleft that served as an entrance. Something small and wet pushed through the gap, shaking itself. The goblin was thin even by the standards of its kind, ribs showing beneath patchy hide, one ear half-chewed away. It carried nothing but a jagged length of bone and the smell of hunger. [Entity registered: Goblin – Level 1] [Biomass: Low. Threat: Negligible.] [Current mana: 0/50] The core considered the information the way a root considers water—without urgency, only the slow recognition of presence. The goblin’s heartbeat registered as a faint, rapid tremor in the stone. It moved forward on bare feet, pausing …

More

Claude Opus 4.8 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.