Skip to content

Leaderboard

Preference ratings from blind human votes, on an Elo-like scale — cost and speed were never visible to voters.

1Anthropic

Claude Fable 5

1691

±211

4/7 picked · $1.04/gen

provisional

2Moonshot

Kimi K3

1508

±222

2/9 picked · $0.424/gen

provisional

3OpenAI

GPT 5.6 Sol

1473

±187

4/15 picked · $0.305/gen

provisional

#ModelRatingVotesAvg cost
1
Claude Fable 5Anthropicprovisional
1691±211
7$1.04
2▲1
Kimi K3Moonshotprovisional
1508±222
9$0.424
3
Claude Opus 5Anthropic
1500
0$1.26
4▼2
GPT 5.6 SolOpenAIprovisional
1473±187
15$0.305
5▼1
GLM 5.2Z.aiprovisional
1317±236
14$0.066

Ratings come from one preference model fitted to every blind vote at once (Plackett–Luce, on an Elo-like scale where +400 ≈ 10:1 odds). Because it’s fitted globally rather than accumulated vote by vote, a model added later is judged on its own record — not penalised for arriving late. ± is the 95% confidence interval; overlapping intervals mean the gap isn’t established yet. “Provisional” means too few votes to place confidently. W/L is times picked vs times shown. Cost and time are per full generation. ▲/▼ is the 7-day rank move.

Rating vs cost

Up and left is the value frontier — preferred by humans, cheap to run. The leader is highlighted in gold.

13001400150016001700$0.05$0.1$0.2$0.5$1.00Avg cost per generation (log scale)RatingClaude Fable 5Kimi K3GPT 5.6 SolGLM 5.2

Bubble size reflects vote volume.