MMLU-Pro Leaderboard

Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains.

Data from Artificial Analysis

As of November 21, 2026, the top-scoring model on MMLU-Pro is Gemini 3 Pro Preview at 89.8%, followed by Claude Opus 4.5 at 89.5% and Gemini 3 Flash Preview at 89.0%. 195 models have been evaluated on this benchmark.

Last updated: November 21, 2026

8 Ways to Use Fewer Tokens

Models

195

Best Score

89.8

Average

74.6

Std Dev

11.8

Categories
General Knowledge
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
MMLU-Pro
Actions
$2.000
$12.000
89.8
$5.000
$25.000
89.5
$0.500
$3.000
89.0
$5.000
$25.000
88.9
$0.500
$3.000
88.2
$15.000
$75.000
88.0
$3.000
$15.000
87.5
$0.300
$1.200
87.5
$10.500
$84.000
87.4
$15.000
$75.000
87.3
$1.250
$10.000
87.1
$0.625
$5.000
87.0
$3.000
$15.000
86.6
$1.250
$10.000
86.5
$0.270
$0.400
86.3
$1.000
$10.000
86.2
$0.209
$0.310
86.2
$15.000
$75.000
86.0
$3.000
$15.000
86.0
$1.250
$10.000
86.0
$1.750
$14.000
85.9
$1.250
$10.000
85.8
$0.320
$1.400
85.6
$0.000
$0.000
85.4
$2.000
$8.000
85.3
$0.250
$0.950
85.1
$0.270
$1.000
85.1
$0.200
$0.500
85.0
$0.270
$0.410
85.0
$0.500
$2.150
84.9
$0.900
$0.900
84.9
$0.550
$2.200
84.8
$0.550
$2.190
84.4
$0.450
$0.900
84.3
$0.090
$0.290
84.3
$3.000
$15.000
84.2
$15.000
$60.000
84.1
$0.780
$3.900
84.1
$3.000
$15.000
83.7
$0.625
$5.000
83.7
$3.000
$15.000
83.7
$0.125
$1.000
83.7
$0.209
$0.310
83.7
$0.270
$1.000
83.6
$0.900
$0.900
83.6
$0.270
$0.410
83.6
$0.600
$2.200
83.5
$0.250
$0.950
83.3
$1.100
$4.400
83.2
$0.300
$2.500
83.2
$1.000
$3.000
82.9
$0.430
$1.750
82.9
$0.900
$0.900
82.8
$0.250
$0.500
82.8
$0.000
$0.000
82.8
$0.150
$0.900
82.4
$0.780
$3.900
82.4
$0.200
$0.880
82.3
$0.200
$1.100
82.2
$1.250
$10.000
82.0
$0.300
$1.200
82.0
$0.250
$2.000
82.0
$0.250
$1.000
81.9
$0.600
$2.500
81.9
$0.090
$0.900
81.9
$0.500
$0.900
81.8
$0.000
$0.000
81.6
$0.130
$0.850
81.5
$0.000
$0.000
81.4
$0.207
$0.828
81.3
$0.093
$0.373
81.1
$0.200
$0.600
80.9
$0.300
$2.500
80.9
$0.030
$0.100
80.8
$0.100
$0.400
80.8
$0.900
$0.900
80.7
$2.000
$8.000
80.6
$0.200
$0.900
80.5
$3.000
$15.000
80.3
$1.100
$4.400
80.2
$1.000
$5.000
80.0
$3.000
$15.000
79.9
$0.300
$0.900
79.9
$0.064
$0.224
79.8
$0.100
$0.400
79.6
$0.750
$0.800
79.5
$0.060
$0.240
79.4
$0.320
$1.400
79.4
$0.200
$1.500
79.3
$1.100
$4.400
79.1
$0.500
$0.900
79.1
$0.300
$0.900
78.8
$0.600
$1.800
78.8
$0.430
$1.750
78.4
$0.400
$1.600
78.1
$0.025
$0.200
78.0
$0.150
$0.600
77.9
$0.120
$0.500
77.7
$0.090
$0.300
77.7
$0.900
$0.900
77.6
$0.080
$0.200
77.4
$3.000
$15.000
77.2
$0.900
$0.900
76.4
$0.150
$0.600
76.4
$0.150
$0.500
76.3
$1.040
$4.160
76.2
$0.900
$0.900
76.2
$0.400
$0.900
76.2
$0.440
$2.200
76.0
$1.000
$5.000
76.0
$0.100
$0.400
75.9
$0.200
$0.200
75.9
$0.150
$0.500
75.9
$3.000
$15.000
75.5
$0.100
$0.300
75.2
$0.300
$0.900
75.2
$0.600
$1.800
75.1
$0.117
$1.365
74.9
$0.017
$0.085
74.8
$0.090
$0.290
74.4
$0.200
$0.200
74.3
$0.200
$0.200
74.3
$0.000
$0.000
74.3
$0.300
$2.500
74.3
$0.060
$0.200
74.2
$0.300
$0.300
73.9
$0.060
$0.200
73.9
$2.500
$12.500
73.3
$1.500
$1.500
73.2
$0.200
$0.500
73.0
$1.000
$3.000
72.9
$0.064
$0.224
72.7
$0.075
$0.300
72.4
$0.100
$0.400
72.4
$0.288
$0.320
72.0
$0.070
$0.140
71.4
$0.100
$0.320
71.3
$2.500
$10.000
71.2
$0.120
$0.500
71.0
$0.400
$2.000
70.8
$0.070
$0.280
70.6
$2.000
$6.000
70.1
$0.000
$0.000
69.8
$2.000
$6.000
69.7
$0.900
$0.900
69.7
$5.000
$15.000
69.4
$0.200
$0.200
69.3
$0.800
$3.200
69.1
$0.880
$0.880
69.0
$1.000
$1.000
68.9
$0.180
$0.200
68.6
$2.000
$6.000
68.3
$0.440
$2.200
68.3
$0.075
$0.200
68.1
$0.340
$0.390
67.6
$0.080
$0.200
67.5
$0.200
$0.200
67.2
$0.080
$0.160
66.9
$0.093
$0.373
66.4
$0.100
$0.300
65.9
$0.100
$0.400
65.7
$0.120
$0.200
65.5
$0.040
$0.064
65.2
$0.200
$0.200
64.9
$0.150
$0.600
64.8
$0.200
$0.200
64.3
$0.150
$0.150
64.2
$0.660
$0.800
63.5
$0.800
$4.000
63.4
$0.033
$0.130
63.3
$0.070
$0.280
62.2
$0.200
$0.600
61.1
$0.050
$0.150
59.5
$0.060
$0.240
59.0
$0.060
$0.240
57.9
$2.000
$8.000
57.7
$0.510
$0.740
57.4
$0.100
$0.280
57.1
$30.000
$60.000
56.2
$1.200
$1.200
53.7
$0.035
$0.140
53.1
$0.100
$0.200
52.2
$0.500
$1.500
51.5
$0.050
$0.200
51.1
$0.010
$0.020
50.5
$0.000
$0.000
48.8
$0.020
$0.040
47.6
$0.200
$0.200
47.3
$0.060
$0.060
46.4
$0.500
$1.000
46.2
$0.040
$0.050
41.7
$0.040
$0.040
40.5
$0.140
$0.420
38.7
$0.030
$0.050
34.7
$0.020
$0.020
20.0

Pricing from OpenRouter. Benchmarks from Artificial Analysis.

About MMLU-Pro

Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains.

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

Frequently Asked Questions

Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains.
As of November 21, 2026, Gemini 3 Pro Preview leads the MMLU-Pro leaderboard with a score of 89.8. Rankings change as new models are released and evaluated.
Currently 195 models have been evaluated on MMLU-Pro, with an average score of 74.6 and standard deviation of 11.8.
Benchmark scores are updated when new evaluations are published by our data sources (Artificial Analysis and LayerLens). Pricing data is refreshed daily from OpenRouter.