IFEval Leaderboard

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

8 Ways to Use Fewer Tokens

Models

31

Best Score

92.6

Average

73.0

Std Dev

21.6

Categories
Instruction Following
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
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.

About IFEval

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.

Frequently Asked Questions

Instruction Following Evaluation benchmark testing how well LLMs follow detailed formatting and content constraints.
As of November 21, 2026, Kimi K2.5 leads the IFEval leaderboard with a score of 92.6. Rankings change as new models are released and evaluated.
Currently 31 models have been evaluated on IFEval, with an average score of 73.0 and standard deviation of 21.6.
Benchmark scores are updated when new evaluations are published by our data sources (Artificial Analysis and LayerLens). Pricing data is refreshed daily from OpenRouter.