Knights and Knaves Leaderboard

Logic puzzle benchmark based on knights (truth-tellers) and knaves (liars) puzzles.

Data from LayerLens

As of November 21, 2026, the top-scoring model on Knights and Knaves is DeepSeek V4 Pro at 100.0%, followed by R1 0528 at 97.9% and GPT-OSS-20b at 94.0%. 15 models have been evaluated on this benchmark.

Last updated: November 21, 2026

8 Ways to Use Fewer Tokens

Models

15

Best Score

100.0

Average

55.0

Std Dev

27.6

Categories
Reasoning and Logic
Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Model
Input $/M
Output $/M
Knights and Knaves
Actions
$0.111
$1.322
100.0
$0.500
$2.150
97.9
$0.017
$0.085
94.0
$2.000
$8.000
77.1
$0.440
$2.200
60.7
$0.014
$0.028
60.3
$0.200
$0.600
59.4
$0.080
$0.160
57.6
$0.075
$0.200
55.6
$2.500
$10.000
39.1
$0.070
$0.140
38.3
$0.100
$0.300
30.7
$0.800
$3.200
28.3
$0.035
$0.140
19.3
$0.030
$0.050
6.1

Pricing from OpenRouter. Benchmarks from Artificial Analysis.

About Knights and Knaves

Logic puzzle benchmark based on knights (truth-tellers) and knaves (liars) puzzles.

This leaderboard shows all models with Knights and Knaves benchmark scores, ranked from highest to lowest. Pricing data is included to help you compare performance against cost.

Frequently Asked Questions

Logic puzzle benchmark based on knights (truth-tellers) and knaves (liars) puzzles.
As of November 21, 2026, DeepSeek V4 Pro leads the Knights and Knaves leaderboard with a score of 100.0. Rankings change as new models are released and evaluated.
Currently 15 models have been evaluated on Knights and Knaves, with an average score of 55.0 and standard deviation of 27.6.
Benchmark scores are updated when new evaluations are published by our data sources (Artificial Analysis and LayerLens). Pricing data is refreshed daily from OpenRouter.