ARC Challenge Leaderboard

AI2 Reasoning Challenge (Challenge set) — grade-school science questions requiring complex reasoning.

Data from LayerLens

As of November 21, 2026, the top-scoring model on ARC Challenge is GPT-5 at 96.3%, followed by GLM 5 at 96.0% and GLM 5 at 96.0%. 22 models have been evaluated on this benchmark.

Last updated: November 21, 2026

8 Ways to Use Fewer Tokens

Models

22

Best Score

96.3

Average

92.2

Std Dev

8.1

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 Challenge
Actions
$1.250
$10.000
96.3
$0.600
$1.920
96.0
$0.600
$1.920
96.0
$0.014
$0.029
95.4
$0.000
$0.000
95.3
$2.000
$8.000
95.1
$0.500
$2.150
95.1
$0.200
$0.600
95.0
$0.000
$0.000
94.8
$0.064
$0.224
94.7
$0.064
$0.224
94.7
$0.014
$0.028
94.0
$0.100
$0.300
93.9
$0.440
$2.200
93.9
$2.500
$10.000
93.7
$0.440
$2.200
93.4
$0.800
$3.200
92.7
$0.070
$0.140
92.6
$0.075
$0.200
91.8
$0.080
$0.160
91.0
$0.035
$0.140
86.9
$0.030
$0.050
56.3

Pricing from OpenRouter. Benchmarks from Artificial Analysis.

About ARC Challenge

AI2 Reasoning Challenge (Challenge set) — grade-school science questions requiring complex reasoning.

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

Frequently Asked Questions

AI2 Reasoning Challenge (Challenge set) — grade-school science questions requiring complex reasoning.
As of November 21, 2026, GPT-5 leads the ARC Challenge leaderboard with a score of 96.3. Rankings change as new models are released and evaluated.
Currently 22 models have been evaluated on ARC Challenge, with an average score of 92.2 and standard deviation of 8.1.
Benchmark scores are updated when new evaluations are published by our data sources (Artificial Analysis and LayerLens). Pricing data is refreshed daily from OpenRouter.