Claude or ChatGPT for writing in English?

The two most-asked-about assistants, judged on the same English prompts in blind duels: which one writes better, by how much, and for which kinds of text. Updated with every export of the ranking.

The verdict

GPT-6.1 Sol by OpenAI (thinking high) writes better English than Claude Fable 5.2 by Anthropic (thinking adaptive high) in our blind duels: rank 1 against rank 2 on the leaderboard, score 95.0 against 92.6.

Head to head, Claude takes 100.0% of the points over 1 direct duels (1 win, 0 ties, 0 losses). Claude leads in 2 of the 8 kinds of writing where both have been judged, ChatGPT in 6.

The two models on the leaderboard
ModelRankScoreDuels
Claude Claude Fable 5.2 💡 adaptive high292.6173
ChatGPT GPT-6.1 Sol 💡 high195.02,723

Each side is its best-ranked variant in this edition: Claude Fable 5.2 by Anthropic (thinking adaptive high) for Claude, GPT-6.1 Sol by OpenAI (thinking high) for ChatGPT. When a better variant of either arrives, this page follows it.

Kind of writing by kind of writing

Score and rank recomputed on the duels of each category alone; the leader is in colour. Click a kind of writing for its full ranking.

Kind of writing by kind of writing
Kind of writingClaudeChatGPTDirect duels
Articles, blogs and editorial93.4 #898.4 #1—
Dialogue and screenplay92.8 #1798.3 #1—
Explanation and popularization82.8 #1374.0 #22—
Fiction and narrative97.7 #896.6 #101–0–0
Marketing and sales92.7 #1194.7 #7—
Personal communication—97.3 #2—
Professional and administrative—85.1 #5—
Social media and short formats91.4 #1096.9 #1—
Speech and public speaking94.8 #898.5 #1—
Structured documents and reports73.2 #4096.5 #1—

Direct duels read wins–ties–losses for the first model. A dash means the model has not yet been judged in that category.

What each side stands for

“Claude” here is whichever Anthropic model currently ranks highest on the English leaderboard, and “ChatGPT” whichever OpenAI model does. Both companies ship several models at once, and the one you get in the app depends on your plan and on the day. The table above names the exact variants and the reasoning setting they ran with; the other variants of each family sit a few places apart on the full leaderboard.

What the numbers measure

Every score on this page comes from blind duels: two anonymous texts written for the same English prompt, an AI judge picking the better one without seeing the model names, thousands of times over. The direct record counts only the duels where these two exact variants met. The kind-of-writing table recomputes the ranking on the duels of one category alone, so an email is not judged by a short story.

How to choose

If the verdict is close, the kind of writing decides. Personal letters and emails, marketing copy and speeches tend to separate the two more than reports and explanations do. Look at the categories you write most, then read the example pair at the bottom: it is one real duel, with the published verdict, and a better guide to voice than any score.

Writing example

Write a very short piece of flash fiction (50–150 words) in the third person about a lighthouse keeper named Elena who, on a foggy night, spots a single small rowboat drifting toward the rocks. Convey her decision to leave the warmth of the tower and climb down to the shore, and end on an image that leaves the outcome slightly open. Focus on atmosphere, sensory detail, and restraint rather than a full plot. The tone should be quiet and evocative.

Published verdict: Claude (judged by Claude Opus 5.5).

Claude · Claude Fable 5.2 💡 adaptive high

The fog had swallowed the horizon by nine. Elena stood at the gallery rail with her tea going cold, watching the beam sweep through grey wool and return with nothing.

Then, something. A rowboat, small as a seed pod, turning slowly on the swell. No oars showing. It drifted toward the Teeth, where the water hissed white even on calm nights.

She set the cup on the sill. Behind her the stove ticked, and her chair held the shape of her evening.

The stairs were two hundred and twelve steps. She counted none of them. Outside, the air tasted of salt and iron, and the shingle slid under her boots.

At the waterline she raised the lantern. Out in the dark, wood knocked softly against stone.

ChatGPT · GPT-6.1 Sol 💡 high

The kettle had begun to whisper when Elena saw the rowboat. It slipped through the fog below the lighthouse, small and low in the water, one oar trailing beside it. Beyond the glass, the rocks appeared and vanished.

She watched for a hand, a lifted head. The boat turned slowly.

Elena took her coat from the chair. Warmth lingered in its lining as she descended the tower stairs, her palm sliding along the cold rail. At the bottom, salt dampened her face.

She climbed down to the shore and stood where the shingle gave way to black water. Somewhere close, wood knocked against stone.

She raised her lantern. In its trembling light, the loose oar swung toward her, then away.