TerminalBench Leaderboard

Terminal-based benchmark testing AI ability to interact with command-line interfaces and solve system tasks.

Data from Artificial Analysis

As of November 21, 2026, the top-scoring model on TerminalBench is GPT-5.6 Sol at 65.9%, followed by Claude Fable 5 at 62.9% and GPT-5.5 at 60.6%. 232 models have been evaluated on this benchmark.

Last updated: November 21, 2026

8 Ways to Use Fewer Tokens

Models

232

Best Score

65.9

Average

20.3

Std Dev

16.7

Categories
Multi-turn
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
TerminalBench
Actions
$2.000
$10.000
65.9
$10.000
$50.000
62.9
$5.000
$30.000
60.6
$5.000
$25.000
58.3
$1.250
$7.500
57.6
$2.000
$12.000
57.6
$5.000
$25.000
54.5
$1.000
$6.000
53.8
$3.000
$15.000
53.0
$1.750
$14.000
53.0
$0.375
$2.250
52.3
$1.475
$4.425
50.8
$0.007
$0.950
50.8
$0.300
$1.200
49.2
$5.000
$25.000
48.5
$5.000
$25.000
47.0
$10.500
$84.000
47.0
$0.320
$1.280
47.0
$5.000
$25.000
46.2
$0.111
$1.322
46.2
$1.500
$9.000
46.2
$0.625
$5.000
45.5
$0.600
$3.000
44.7
$0.000
$0.000
43.9
$1.750
$14.000
43.2
$0.600
$1.920
43.2
$0.899
$2.825
43.2
$0.480
$1.800
43.2
$0.100
$0.625
42.4
$0.230
$0.960
42.4
$2.000
$12.000
41.7
$5.000
$25.000
40.9
$0.390
$0.900
40.9
$0.600
$1.920
39.4
$0.000
$0.000
39.4
$0.500
$3.000
38.6
$0.014
$0.029
38.6
$3.000
$15.000
37.9
$1.250
$10.000
37.9
$1.250
$10.000
37.9
$2.000
$8.000
37.1
$1.750
$14.000
37.1
$0.100
$0.100
36.4
$0.400
$1.760
36.4
$3.000
$15.000
35.6
$0.209
$0.310
35.6
$0.200
$1.150
35.6
$1.250
$10.000
34.8
$0.270
$0.400
34.8
$0.490
$2.500
34.8
$0.270
$0.950
34.8
$0.400
$2.000
34.8
$0.250
$0.900
34.8
$0.050
$0.700
34.8
$15.000
$75.000
34.3
$0.180
$0.600
34.1
$0.125
$1.000
33.3
$0.250
$2.000
33.3
$1.200
$4.000
33.3
$1.500
$7.500
33.3
$0.209
$0.310
32.6
$0.090
$0.300
32.6
$0.195
$0.900
32.6
$1.200
$4.000
32.6
$0.270
$1.000
31.8
$0.500
$3.000
31.8
$0.320
$1.400
31.8
$0.132
$0.528
31.8
$3.000
$15.000
31.1
$15.000
$75.000
31.1
$0.550
$2.200
31.1
$0.270
$0.410
31.1
$0.090
$0.290
31.1
$0.260
$0.900
31.1
$0.075
$0.625
31.1
$0.270
$1.000
30.3
$0.320
$1.400
30.3
$3.000
$15.000
28.8
$0.430
$1.750
28.8
$0.300
$1.200
28.8
$0.090
$0.290
28.0
$3.000
$15.000
27.3
$1.000
$5.000
27.3
$1.000
$5.000
27.3
$1.000
$10.000
26.5
$0.065
$0.750
26.5
$0.250
$0.750
26.5
$0.300
$1.200
25.8
$0.250
$0.950
25.0
$0.270
$0.410
25.0
$0.430
$1.750
25.0
$0.050
$0.190
25.0
$0.300
$1.500
25.0
$0.250
$0.950
24.2
$0.000
$0.000
24.2
$0.780
$3.900
24.2
$0.250
$1.500
24.2
$0.080
$0.120
24.2
$0.030
$0.100
23.5
$0.600
$2.500
23.5
$0.600
$2.200
22.0
$0.060
$0.400
22.0
$3.000
$15.000
21.2
$3.000
$15.000
21.2
$0.010
$0.030
21.2
$0.130
$0.850
20.4
$0.780
$3.900
20.4
$0.300
$0.900
18.9
$0.200
$0.500
18.9
$0.400
$0.900
18.9
$0.490
$2.500
18.9
$0.120
$0.800
18.2
$0.250
$0.500
17.4
$0.025
$0.200
17.4
$0.200
$1.500
17.4
$0.780
$3.900
17.4
$0.900
$0.900
16.7
$0.500
$2.150
15.9
$0.250
$1.000
15.2
$1.100
$4.400
15.2
$0.000
$0.000
15.2
$0.070
$0.280
15.2
$0.000
$0.000
14.4
$0.300
$0.900
14.4
$2.000
$8.000
13.6
$0.300
$2.500
13.6
$0.450
$0.900
13.6
$0.060
$0.240
13.6
$15.000
$60.000
12.9
$1.250
$10.000
12.9
$0.100
$0.400
12.9
$0.300
$2.500
12.1
$0.200
$0.500
12.1
$0.060
$0.240
12.1
$3.000
$15.000
11.4
$1.000
$3.000
11.4
$0.900
$0.900
11.4
$0.017
$0.085
10.6
$0.440
$2.200
10.6
$1.000
$3.000
9.8
$0.150
$0.900
9.8
$0.400
$2.000
9.1
$0.207
$0.828
9.1
$0.200
$1.100
9.1
$2.500
$10.000
8.3
$0.500
$0.900
8.3
$0.100
$0.300
7.6
$0.400
$1.600
7.6
$0.090
$0.900
7.6
$0.100
$0.400
7.6
$0.500
$0.900
7.6
$0.150
$0.600
7.6
$1.500
$1.500
6.8
$1.100
$4.400
6.8
$0.200
$0.600
6.8
$0.120
$0.500
6.8
$0.075
$0.200
6.8
$0.600
$1.800
6.8
$0.200
$0.880
6.8
$2.500
$12.500
6.8
$0.300
$2.500
6.8
$2.000
$6.000
6.1
$0.800
$3.200
6.1
$0.550
$2.190
6.1
$1.100
$4.400
6.1
$0.900
$0.900
6.1
$0.900
$0.900
6.1
$0.900
$0.900
6.1
$0.070
$0.280
6.1
$0.090
$0.300
6.1
$0.150
$0.600
6.1
$0.080
$0.200
5.3
$0.600
$1.800
5.3
$0.200
$0.900
5.3
$0.900
$0.900
5.3
$0.000
$0.000
5.3
$0.288
$0.320
4.5
$0.880
$0.880
4.5
$0.200
$0.200
4.5
$0.100
$0.400
4.5
$0.093
$0.373
4.5
$0.200
$0.200
4.5
$0.150
$0.150
4.5
$0.200
$0.200
4.5
$0.070
$0.140
3.8
$0.150
$0.600
3.8
$0.080
$0.160
3.8
$0.100
$0.400
3.8
$0.080
$0.200
3.8
$0.440
$2.200
3.8
$0.000
$0.000
3.8
$0.117
$1.365
3.8
$0.060
$0.400
3.8
$0.340
$0.390
3.0
$0.100
$0.320
3.0
$0.064
$0.224
3.0
$0.000
$0.000
3.0
$0.300
$0.900
3.0
$0.800
$4.000
2.3
$0.200
$0.200
2.3
$0.200
$0.200
2.3
$0.120
$0.500
2.3
$0.000
$0.000
2.3
$0.100
$0.400
2.3
$2.000
$8.000
2.3
$0.180
$0.200
2.3
$0.035
$0.140
1.5
$0.750
$0.800
1.5
$0.100
$0.300
1.5
$0.200
$0.200
1.5
$0.060
$0.200
1.5
$0.150
$0.500
1.5
$0.250
$1.250
0.8
$0.510
$0.740
0.8
$0.020
$0.040
0.8
$0.060
$0.060
0.8
$0.060
$0.240
0.8
$2.500
$10.000
0.8
$0.050
$0.150
0.8
$0.040
$0.050
0.8
$0.060
$0.200
0.8
$0.120
$0.200
0.8
$0.040
$0.040
-
$0.020
$0.020
-
$0.050
$0.200
-
$0.093
$0.373
-
$0.010
$0.020
-
$0.200
$0.200
-
$0.100
$0.200
-
$0.150
$0.500
-
$0.200
$0.600
-
$0.200
$0.200
-

Pricing from OpenRouter. Benchmarks from Artificial Analysis.

About TerminalBench

Terminal-based benchmark testing AI ability to interact with command-line interfaces and solve system tasks.

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

Frequently Asked Questions

Terminal-based benchmark testing AI ability to interact with command-line interfaces and solve system tasks.
As of November 21, 2026, GPT-5.6 Sol leads the TerminalBench leaderboard with a score of 65.9. Rankings change as new models are released and evaluated.
Currently 232 models have been evaluated on TerminalBench, with an average score of 20.3 and standard deviation of 16.7.
Benchmark scores are updated when new evaluations are published by our data sources (Artificial Analysis and LayerLens). Pricing data is refreshed daily from OpenRouter.