ARC Easy Leaderboard

AI2 Reasoning Challenge (Easy set) — grade-school science questions.

Data from LayerLens

As of November 21, 2026, the top-scoring model on ARC Easy is Qwen3 32B at 99.1%, followed by Qwen3 32B at 99.1% and Mistral Medium 3 at 99.1%. 20 models have been evaluated on this benchmark.

Last updated: November 21, 2026

8 Ways to Use Fewer Tokens

Models

20

Best Score

99.1

Average

97.4

Std Dev

4.4

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
ARC Easy
Actions
$0.064
$0.224
99.1
$0.064
$0.224
99.1
$0.440
$2.200
99.1
$2.000
$8.000
99.0
$0.000
$0.000
98.9
$0.300
$2.500
98.9
$0.300
$2.500
98.9
$0.800
$3.200
98.8
$2.500
$10.000
98.8
$0.500
$2.150
98.7
$0.100
$0.300
98.6
$0.200
$0.600
98.6
$0.014
$0.028
98.6
$0.080
$0.160
98.2
$0.070
$0.140
97.9
$0.075
$0.200
97.8
$0.100
$0.280
97.6
$0.060
$0.240
97.5
$0.035
$0.140
95.8
$0.030
$0.050
78.6

Pricing from OpenRouter. Benchmarks from Artificial Analysis.

About ARC Easy

AI2 Reasoning Challenge (Easy set) — grade-school science questions.

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

Frequently Asked Questions

AI2 Reasoning Challenge (Easy set) — grade-school science questions.
As of November 21, 2026, Qwen3 32B leads the ARC Easy leaderboard with a score of 99.1. Rankings change as new models are released and evaluated.
Currently 20 models have been evaluated on ARC Easy, with an average score of 97.4 and standard deviation of 4.4.
Benchmark scores are updated when new evaluations are published by our data sources (Artificial Analysis and LayerLens). Pricing data is refreshed daily from OpenRouter.