OpenAI HumanEval benchmark measuring Python code generation from function docstrings.
Data from LayerLens
As of November 21, 2026, the top-scoring model on HumanEval is Claude Sonnet 4.5 at 97.6%, followed by Claude Sonnet 4.5 at 97.0% and Claude Opus 4.5 at 97.0%. 43 models have been evaluated on this benchmark.
Last updated: November 21, 2026
Models
43
Best Score
97.6
Average
89.2
Std Dev
10.4
Provider | Model | Input $/M | Output $/M | HumanEval | Actions |
|---|---|---|---|---|---|
$3.000 | $15.000 | 97.6 | |||
$3.000 | $15.000 | 97.0 | |||
$5.000 | $25.000 | 97.0 | |||
$5.000 | $25.000 | 97.0 | |||
$5.000 | $25.000 | 97.0 | |||
$5.000 | $25.000 | 97.0 | |||
$0.600 | $1.920 | 97.0 | |||
$0.600 | $1.920 | 97.0 | |||
$1.000 | $5.000 | 96.3 | |||
$0.390 | $0.900 | 96.3 | |||
$0.064 | $0.224 | 95.7 | |||
$0.064 | $0.224 | 95.7 | |||
$0.625 | $5.000 | 94.5 | |||
$1.000 | $5.000 | 93.9 | |||
$0.209 | $0.310 | 93.9 | |||
$2.000 | $8.000 | 93.3 | |||
$0.120 | $0.500 | 93.3 | |||
$0.120 | $0.500 | 93.3 | |||
$0.500 | $2.150 | 93.3 | |||
$0.060 | $0.240 | 93.3 | |||
$0.060 | $0.240 | 93.3 | |||
$0.260 | $1.560 | 93.3 | |||
$0.300 | $0.900 | 92.7 | |||
$0.000 | $0.000 | 92.1 | |||
$0.060 | $0.400 | 92.1 | |||
$0.060 | $0.400 | 92.1 | |||
$0.900 | $0.900 | 90.2 | |||
$0.900 | $0.900 | 90.2 | |||
$0.500 | $1.500 | 90.2 | |||
$0.440 | $2.200 | 88.4 | |||
$0.014 | $0.028 | 87.2 | |||
$0.080 | $0.160 | 85.4 | |||
$0.440 | $2.200 | 85.4 | |||
$0.070 | $0.140 | 84.8 | |||
$0.200 | $0.600 | 84.8 | |||
$0.075 | $0.200 | 83.5 | |||
$2.500 | $10.000 | 82.9 | |||
$0.288 | $0.320 | 82.3 | |||
$0.100 | $0.300 | 81.1 | |||
$0.060 | $0.240 | 78.0 | |||
$0.800 | $3.200 | 76.8 | |||
$0.000 | $0.000 | 51.2 | |||
$0.030 | $0.050 | 47.6 |
Pricing from OpenRouter. Benchmarks from Artificial Analysis.
OpenAI HumanEval benchmark measuring Python code generation from function docstrings.
This leaderboard shows all models with HumanEval 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.