Instruction Following Evaluation benchmark testing how well LLMs follow detailed formatting and content constraints.
Data from LayerLens
As of November 21, 2026, the top-scoring model on IFEval is Kimi K2.5 at 92.6%, followed by Kimi K2.5 at 92.6% and Gemini 2.5 Pro at 90.8%. 31 models have been evaluated on this benchmark.
Last updated: November 21, 2026
Models
31
Best Score
92.6
Average
73.0
Std Dev
21.6
Provider | Model | Input $/M | Output $/M | IFEval | Actions |
|---|---|---|---|---|---|
$0.490 | $2.500 | 92.6 | |||
$0.490 | $2.500 | 92.6 | |||
$1.000 | $10.000 | 90.8 | |||
$0.320 | $1.400 | 90.8 | |||
$0.320 | $1.400 | 90.8 | |||
$0.100 | $0.320 | 90.0 | |||
$0.270 | $0.410 | 88.1 | |||
$0.270 | $0.410 | 88.1 | |||
$0.550 | $2.200 | 87.6 | |||
$0.340 | $0.390 | 86.7 | |||
$0.300 | $2.500 | 84.3 | |||
$0.300 | $2.500 | 84.3 | |||
$0.100 | $0.300 | 83.9 | |||
$0.300 | $0.900 | 82.8 | |||
$0.800 | $3.200 | 81.9 | |||
$0.080 | $0.160 | 81.9 | |||
$0.064 | $0.224 | 81.3 | |||
$0.064 | $0.224 | 81.3 | |||
$0.070 | $0.280 | 78.7 | |||
$0.100 | $0.280 | 76.6 | |||
$1.000 | $3.000 | 75.4 | |||
$1.000 | $3.000 | 75.4 | |||
$0.030 | $0.050 | 73.9 | |||
$0.200 | $0.200 | 61.5 | |||
$0.020 | $0.020 | 57.0 | |||
$0.020 | $0.040 | 49.2 | |||
$0.750 | $0.800 | 43.4 | |||
$0.300 | $0.300 | 41.9 | |||
$0.900 | $0.900 | 39.8 | |||
$0.040 | $0.040 | 24.0 | |||
$0.070 | $0.140 | 5.8 |
Pricing from OpenRouter. Benchmarks from Artificial Analysis.
Instruction Following Evaluation benchmark testing how well LLMs follow detailed formatting and content constraints.
This leaderboard shows all models with IFEval 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.