MBPP Plus Leaderboard

Mostly Basic Python Problems Plus — tests Python code generation with enhanced test cases.

Data from LayerLens

As of November 21, 2026, the top-scoring model on MBPP Plus is Kimi K2.6 at 66.9%, followed by Qwen3 235B A22B at 66.2% and Qwen3 235B A22B at 66.2%. 35 models have been evaluated on this benchmark.

Last updated: November 21, 2026

8 Ways to Use Fewer Tokens

Models

35

Best Score

66.9

Average

57.2

Std Dev

9.3

Categories
Computer Science and Programming
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
MBPP Plus
Actions
$0.000
$0.000
66.9
$0.900
$0.900
66.2
$0.900
$0.900
66.2
$0.064
$0.224
63.4
$0.064
$0.224
63.4
$0.300
$0.900
63.2
$0.125
$1.000
63.2
$0.090
$0.900
63.2
$2.000
$8.000
63.0
$1.000
$10.000
63.0
$0.025
$0.200
63.0
$0.000
$0.000
62.7
$0.120
$0.500
62.6
$0.120
$0.500
62.6
$0.000
$0.000
61.9
$2.000
$8.000
61.6
$0.070
$0.280
61.1
$0.200
$0.600
60.1
$0.080
$0.160
59.8
$0.500
$2.150
59.5
$0.300
$2.500
57.7
$0.300
$2.500
57.7
$0.075
$0.200
56.6
$0.070
$0.140
55.0
$0.440
$2.200
54.5
$0.100
$0.300
54.0
$1.000
$5.000
53.4
$1.000
$5.000
53.4
$2.500
$10.000
53.2
$0.014
$0.028
51.1
$0.060
$0.240
50.8
$0.800
$3.200
49.2
$0.035
$0.140
47.9
$0.030
$0.050
26.5
$0.100
$0.280
24.1

Pricing from OpenRouter. Benchmarks from Artificial Analysis.

About MBPP Plus

Mostly Basic Python Problems Plus — tests Python code generation with enhanced test cases.

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

Frequently Asked Questions

Mostly Basic Python Problems Plus — tests Python code generation with enhanced test cases.
As of November 21, 2026, Kimi K2.6 leads the MBPP Plus leaderboard with a score of 66.9. Rankings change as new models are released and evaluated.
Currently 35 models have been evaluated on MBPP Plus, with an average score of 57.2 and standard deviation of 9.3.
Benchmark scores are updated when new evaluations are published by our data sources (Artificial Analysis and LayerLens). Pricing data is refreshed daily from OpenRouter.