Price Per TokenPrice Per Token

LCR Leaderboard

Long Context Retrieval benchmark testing ability to find and use information in very long documents.

Data from Artificial Analysis

As of June 2, 2026, the top-scoring model on LCR is GPT-5.2-Codex at 75.7%, followed by GPT-5 at 75.6% and GPT-5.1 at 75.0%. 256 models have been evaluated on this benchmark.

Last updated: June 2, 2026

Models

256

Best Score

75.7

Average

39.8

Std Dev

23.8

Categories
Reasoning and Logic
Provider
Model
Input $/M
Output $/M
LCR
Actions
$1.750
$14.000
75.7
$1.250
$10.000
75.6
$1.250
$10.000
75.0
$0.207
$0.828
74.0
$5.000
$25.000
74.0
$1.750
$14.000
74.0
$2.500
$15.000
74.0
$0.435
$0.870
73.3
$1.250
$10.000
72.8
$10.500
$84.000
72.7
$2.000
$12.000
72.7
$1.500
$9.000
71.0
$2.000
$12.000
70.7
$5.000
$25.000
70.7
$3.000
$15.000
70.7
$1.000
$5.000
70.3
$5.000
$25.000
70.3
$0.684
$3.400
69.7
$2.000
$8.000
69.3
$1.500
$9.000
69.3
$1.250
$10.000
69.0
$0.270
$0.410
69.0
$1.250
$3.750
69.0
$0.279
$1.200
68.7
$3.000
$15.000
68.0
$0.250
$2.000
68.0
$0.000
$0.000
68.0
$1.250
$10.000
67.3
$2.000
$12.000
67.3
$0.195
$0.900
67.3
$2.500
$15.000
67.3
$0.100
$0.100
67.0
$5.000
$25.000
67.0
$0.260
$0.900
66.7
$0.400
$2.000
66.7
$0.550
$2.200
66.3
$15.000
$75.000
66.3
$0.500
$3.000
66.3
$0.435
$0.870
66.3
$1.000
$10.000
66.0
$0.250
$2.000
66.0
$0.780
$3.900
66.0
$0.150
$1.150
66.0
$3.000
$15.000
65.7
$0.390
$0.900
65.7
$5.000
$25.000
65.3
$0.400
$1.900
65.3
$0.250
$1.500
65.3
$0.270
$0.950
65.0
$0.229
$0.343
65.0
$3.000
$15.000
64.7
$0.200
$0.500
64.7
$0.100
$0.300
64.3
$0.400
$1.540
64.0
$1.250
$10.000
63.7
$0.140
$0.900
63.7
$1.750
$14.000
63.3
$0.600
$2.080
63.3
$0.100
$0.300
63.0
$0.098
$0.197
63.0
$0.250
$2.000
62.7
$0.140
$0.900
62.7
$0.980
$3.080
62.3
$0.120
$0.370
62.0
$0.300
$2.500
61.7
$2.000
$8.000
61.0
$0.255
$1.000
61.0
$1.200
$4.000
61.0
$3.000
$15.000
60.7
$1.200
$4.000
60.7
$0.098
$0.300
60.3
$15.000
$60.000
59.3
$0.270
$0.400
59.3
$0.080
$0.400
59.0
$0.100
$0.400
59.0
$0.290
$0.950
59.0
$0.400
$1.900
59.0
$0.040
$0.150
59.0
$1.250
$10.000
58.7
$0.260
$0.900
58.7
$3.000
$15.000
58.7
$5.000
$25.000
58.3
$0.390
$0.900
58.0
$0.780
$3.900
57.7
$3.000
$15.000
57.7
$0.684
$3.400
57.7
$0.140
$0.900
56.7
$0.260
$0.900
56.0
$0.195
$0.900
55.7
$0.060
$0.300
55.7
$0.104
$0.416
55.3
$0.140
$0.900
55.3
$0.550
$2.200
55.0
$0.500
$2.150
54.7
$3.000
$15.000
54.7
$0.400
$2.200
54.3
$0.430
$1.740
54.3
$0.090
$0.300
54.3
$0.210
$0.790
53.3
$1.500
$9.000
53.3
$0.550
$2.000
52.3
$0.600
$2.500
52.3
$0.400
$2.200
51.7
$0.100
$0.400
51.3
$0.090
$0.780
51.3
$3.000
$15.000
51.3
$0.550
$2.200
51.0
$0.039
$0.100
50.7
$0.250
$0.500
50.3
$3.000
$15.000
48.3
$0.600
$2.200
48.3
$0.200
$1.500
48.3
$0.100
$0.400
48.0
$0.500
$3.000
48.0
$2.500
$15.000
47.3
$0.780
$3.900
46.7
$0.150
$0.600
46.0
$0.300
$2.500
45.9
$0.210
$0.790
45.0
$0.435
$0.870
45.0
$3.000
$15.000
44.3
$0.980
$3.080
44.3
$1.250
$10.000
44.0
$0.125
$0.850
43.7
$0.039
$0.100
43.7
$1.000
$5.000
43.7
$0.270
$0.950
43.3
$0.270
$0.410
43.0
$0.090
$0.300
43.0
$0.400
$1.600
42.3
$0.220
$0.900
42.3
$0.050
$0.400
41.7
$0.200
$0.770
41.0
$0.130
$0.900
40.7
$0.300
$0.900
40.3
$0.050
$0.400
40.0
$0.200
$0.200
40.0
$0.110
$0.800
40.0
$0.780
$3.900
39.7
$0.060
$0.300
39.7
$1.100
$4.400
39.3
$0.229
$0.343
39.0
$1.750
$14.000
38.0
$0.040
$0.150
38.0
$0.200
$0.200
37.7
$0.600
$2.080
37.0
$0.400
$1.540
36.3
$0.250
$0.750
36.3
$15.000
$75.000
36.0
$0.060
$0.400
35.0
$0.435
$0.870
35.0
$0.100
$0.400
34.0
$15.000
$75.000
33.7
$0.050
$0.200
33.7
$0.098
$0.197
33.3
$0.200
$1.100
32.3
$0.200
$0.880
31.7
$0.100
$0.400
31.3
$0.104
$0.416
31.3
$0.100
$0.300
31.3
$0.071
$0.100
31.2
$0.029
$0.140
31.0
$0.117
$1.365
31.0
$0.029
$0.140
30.7
$2.500
$12.500
30.0
$0.400
$0.900
30.0
$0.200
$0.770
29.0
$0.070
$0.270
29.0
$0.400
$2.000
28.7
$0.100
$0.400
28.3
$0.400
$2.000
28.0
$0.430
$1.740
26.3
$0.080
$0.300
25.8
$0.900
$0.900
25.0
$1.250
$10.000
25.0
$0.010
$0.030
25.0
$0.900
$0.900
24.3
$0.150
$0.150
24.0
$0.130
$0.520
23.7
$0.800
$4.000
23.3
$0.043
$0.172
22.7
$0.040
$0.160
22.7
$0.100
$0.400
22.0
$0.000
$0.000
22.0
$0.200
$0.200
22.0
$0.900
$0.900
21.7
$0.250
$1.250
21.0
$0.040
$0.160
21.0
$1.000
$3.000
20.7
$0.360
$0.400
20.3
$0.050
$0.400
20.0
$1.000
$3.000
20.0
$0.200
$0.500
20.0
$0.100
$0.300
19.7
$0.400
$2.000
19.7
$0.800
$3.200
19.0
$2.500
$10.000
18.0
$0.060
$0.240
17.7
$0.300
$2.500
17.7
$0.075
$0.200
17.3
$2.000
$8.000
17.3
$0.100
$0.400
17.0
$0.070
$0.280
17.0
$0.100
$0.400
17.0
$0.200
$0.200
17.0
$0.020
$0.050
15.7
$0.080
$0.200
15.3
$0.100
$0.320
15.0
$0.060
$0.400
14.7
$0.300
$0.900
12.3
$0.060
$0.060
11.7
$0.100
$0.400
11.3
$0.700
$0.800
11.0
$2.000
$6.000
10.3
$0.035
$0.140
9.7
$0.290
$0.290
9.7
$0.200
$0.200
7.3
$0.900
$0.900
7.0
$0.040
$0.130
6.7
$0.130
$0.400
6.7
$0.050
$0.200
6.7
$0.340
$0.390
6.3
$0.080
$0.160
5.7
$0.040
$0.080
5.7
$2.000
$6.000
5.3
$0.020
$0.020
5.0
$0.900
$0.900
2.3
$0.030
$0.050
2.0
$0.130
$0.400
2.0
$2.000
$6.000
1.7
$0.510
$0.740
-
$0.040
$0.040
-
$0.065
$0.140
-
$0.050
$0.080
-
$0.050
$0.200
-
$0.455
$0.900
-
$0.455
$0.900
-
$0.080
$0.280
-
$0.080
$0.280
-
$0.080
$0.200
-
$0.080
$0.200
-
$0.050
$0.200
-
$0.050
$0.200
-
$0.080
$0.280
-
$0.080
$0.280
-
$0.200
$0.200
-
$0.060
$0.120
-
$0.600
$1.800
-
$0.600
$1.800
-
$0.010
$0.020
-
$0.120
$0.200
-
$0.100
$0.200
-
$0.150
$0.500
-
$0.150
$0.500
-
$0.200
$0.600
-
$0.200
$0.200
-

Pricing from OpenRouter. Benchmarks from Artificial Analysis.

Get our weekly newsletter on pricing changes, new releases, and tools.

Join the Price Per Token Community
8 Ways to Use Fewer Tokens

About LCR

Long Context Retrieval benchmark testing ability to find and use information in very long documents.

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

Frequently Asked Questions

Long Context Retrieval benchmark testing ability to find and use information in very long documents.
As of June 2, 2026, GPT-5.2-Codex leads the LCR leaderboard with a score of 75.7. Rankings change as new models are released and evaluated.
Currently 256 models have been evaluated on LCR, with an average score of 39.8 and standard deviation of 23.8.
Benchmark scores are updated when new evaluations are published by our data sources (Artificial Analysis and LayerLens). Pricing data is refreshed daily from OpenRouter.