BBEH Leaderboard

Big Bench Extra Hard — even more challenging reasoning tasks pushing the limits of language model capabilities.

Data from LayerLens

As of November 21, 2026, the top-scoring model on BBEH is DeepSeek V4 Flash (Non-Reasoning) at 67.3%, followed by DeepSeek V4 Pro at 64.9% and GPT-5 at 64.1%. 24 models have been evaluated on this benchmark.

Last updated: November 21, 2026

8 Ways to Use Fewer Tokens

Models

24

Best Score

67.3

Average

28.6

Std Dev

18.6

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
BBEH
Actions
$0.014
$0.029
67.3
$0.111
$1.322
64.9
$1.250
$10.000
64.1
$0.125
$1.000
54.9
$5.000
$25.000
49.2
$5.000
$25.000
49.2
$3.000
$15.000
37.1
$0.025
$0.200
29.3
$0.060
$0.400
26.6
$0.060
$0.400
26.6
$0.200
$0.600
25.6
$0.100
$0.300
19.5
$0.500
$1.500
18.7
$2.000
$8.000
17.7
$2.500
$10.000
17.1
$0.800
$3.200
15.9
$0.014
$0.028
15.4
$0.075
$0.200
14.2
$0.440
$2.200
14.1
$0.340
$0.390
14.0
$0.035
$0.140
13.2
$1.000
$3.000
11.2
$1.000
$3.000
11.2
$0.070
$0.140
10.1

Pricing from OpenRouter. Benchmarks from Artificial Analysis.

About BBEH

Big Bench Extra Hard — even more challenging reasoning tasks pushing the limits of language model capabilities.

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

Frequently Asked Questions

Big Bench Extra Hard — even more challenging reasoning tasks pushing the limits of language model capabilities.
As of November 21, 2026, DeepSeek V4 Flash (Non-Reasoning) leads the BBEH leaderboard with a score of 67.3. Rankings change as new models are released and evaluated.
Currently 24 models have been evaluated on BBEH, with an average score of 28.6 and standard deviation of 18.6.
Benchmark scores are updated when new evaluations are published by our data sources (Artificial Analysis and LayerLens). Pricing data is refreshed daily from OpenRouter.