Hemingway-Bench: leaderboard

Surge AI compares model writing through pairwise preferences. The board reports native Elo ratings and confidence intervals, preserving each reasoning setting.

Metric: Elo (writing preference). Source: surgehq.ai. 47 models tracked.

Top models

#ModelSettingScoreOverall rank
1Claude Fable 5Adaptive Reasoning, High Effort1110#28
2Gemini 3.7 FlashThinking, Medium1105#38
3Claude Fable 5.1Adaptive Reasoning, High Effort1095#17
4Gemini 3.8 FlashThinking, Medium1093#39
5Gemini 3.6 FlashThinking, Medium1075#79
6Gemini 3.1 ProThinking, High1073
7Gemini 3.5 FlashThinking, Medium1071#107
8Kimi K31069#59
9GPT-5.6 SolThinking, Medium1057#33
10Gemini 3 ProThinking, High1056#145
11GLM-5.3Thinking, Max1053#73
12Gemini 3 FlashThinking, High1052#174
13Claude Opus 5Adaptive Reasoning, High Effort1047#23
14DeepSeek V4 ProThinking, High1046#198
15Claude Opus 4.6Thinking, High1045#114

No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.

Interactive version: theaggregate.ai/benchmark?slug=hemingway-bench · How It Works · Data refreshed daily, snapshot 2026-11-17.