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
Models
35
Best Score
66.9
Average
57.2
Std Dev
9.3
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.
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.
Built by @aellman
Also from the founder: BlobCap, a price index for AI training data deals, showing what AI labs actually pay for data.
2026 68 Ventures, LLC. All rights reserved.