AIME 2024 Leaderboard

American Invitational Mathematics Examination 2024 problems testing olympiad-level mathematical reasoning.

Data from Artificial Analysis

As of November 21, 2026, the top-scoring model on AIME 2024 is GPT-5 at 95.7%, followed by Grok 4 at 94.3% and o4 Mini at 94.0%. 110 models have been evaluated on this benchmark.

Last updated: November 21, 2026

8 Ways to Use Fewer Tokens

Models

110

Best Score

95.7

Average

40.2

Std Dev

31.3

Categories
Mathematical Problem Solving
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
AIME 2024
Actions
$1.250
$10.000
95.7
$3.000
$15.000
94.3
$1.100
$4.400
94.0
$0.450
$0.900
94.0
$0.250
$0.500
93.3
$0.200
$0.900
90.7
$2.000
$8.000
90.3
$0.500
$2.150
89.3
$1.000
$10.000
88.7
$0.600
$2.200
87.3
$1.250
$10.000
87.0
$1.100
$4.400
86.0
$0.000
$0.000
86.0
$0.000
$0.000
84.7
$0.625
$5.000
84.3
$0.300
$2.500
84.3
$0.900
$0.900
84.0
$0.064
$0.224
80.7
$2.000
$8.000
79.0
$0.900
$0.900
78.0
$3.000
$15.000
77.3
$1.100
$4.400
77.0
$0.080
$0.200
76.3
$15.000
$75.000
75.7
$0.120
$0.500
75.3
$0.200
$0.200
74.7
$0.090
$0.300
72.7
$15.000
$60.000
72.3
$0.000
$0.000
71.7
$0.100
$0.400
70.3
$0.550
$2.200
69.3
$0.300
$0.300
68.7
$0.550
$2.190
68.3
$0.130
$0.850
67.3
$0.750
$0.800
67.0
$0.200
$0.200
65.7
$15.000
$75.000
56.3
$0.250
$1.000
52.0
$0.300
$2.500
50.0
$0.100
$0.400
50.0
$0.900
$0.900
49.3
$1.000
$1.000
48.7
$3.000
$15.000
48.7
$0.300
$0.900
47.7
$0.440
$2.200
44.0
$2.000
$8.000
43.7
$0.400
$1.600
43.0
$3.000
$15.000
40.7
$0.200
$0.600
39.0
$0.150
$0.600
33.0
$3.000
$15.000
33.0
$0.900
$0.900
32.7
$0.075
$0.200
32.3
$0.075
$0.300
30.3
$0.064
$0.224
30.3
$0.100
$0.320
30.0
$0.070
$0.280
29.7
$3.000
$15.000
29.0
$0.100
$0.300
28.3
$0.080
$0.200
28.0
$0.120
$0.500
26.0
$0.080
$0.160
25.3
$0.880
$0.880
24.7
$0.200
$0.200
24.3
$0.100
$0.400
23.7
$1.040
$4.160
23.3
$3.000
$15.000
22.3
$0.050
$0.150
22.0
$1.500
$1.500
21.3
$0.200
$0.200
21.3
$0.000
$0.000
19.3
$0.340
$0.390
17.3
$2.500
$12.500
17.0
$0.288
$0.320
16.0
$3.000
$15.000
15.7
$5.000
$15.000
15.0
$0.070
$0.140
14.3
$0.000
$0.000
13.7
$0.200
$0.600
13.0
$0.660
$0.800
12.0
$0.033
$0.130
12.0
$2.500
$10.000
11.7
$0.150
$0.600
11.7
$2.000
$6.000
11.0
$0.900
$0.900
11.0
$0.800
$3.200
10.7
$0.060
$0.240
10.7
$2.500
$10.000
9.7
$0.060
$0.060
9.3
$2.000
$6.000
9.3
$0.100
$0.300
9.3
$0.035
$0.140
8.0
$0.040
$0.064
8.0
$0.020
$0.040
7.7
$2.000
$6.000
7.0
$0.030
$0.050
6.7
$0.400
$2.000
6.7
$0.040
$0.050
6.3
$2.000
$8.000
5.7
$0.200
$0.200
5.3
$0.800
$4.000
3.3
$0.100
$0.280
2.3
$0.250
$1.250
1.0
$0.070
$0.280
0.3
$0.140
$0.420
-
$0.500
$1.500
-
$1.200
$1.200
-
$0.510
$0.740
-
$0.040
$0.040
-
$0.020
$0.020
-

Pricing from OpenRouter. Benchmarks from Artificial Analysis.

About AIME 2024

American Invitational Mathematics Examination 2024 problems testing olympiad-level mathematical reasoning.

This leaderboard shows all models with AIME 2024 benchmark scores, ranked from highest to lowest. Pricing data is included to help you compare performance against cost.

Frequently Asked Questions

American Invitational Mathematics Examination 2024 problems testing olympiad-level mathematical reasoning.
As of November 21, 2026, GPT-5 leads the AIME 2024 leaderboard with a score of 95.7. Rankings change as new models are released and evaluated.
Currently 110 models have been evaluated on AIME 2024, with an average score of 40.2 and standard deviation of 31.3.
Benchmark scores are updated when new evaluations are published by our data sources (Artificial Analysis and LayerLens). Pricing data is refreshed daily from OpenRouter.