Compare Models

Select models (max 7)
Kimi K3Hy4 Preview
Benchmarks

Vals Index *

Kimi K3
0.00%± 1.00
(41/41)
Hy4 Preview
0.00%± 1.13
(41/41)

Legal Research Bench *

Kimi K3
0.00%± 3.46
(98/98)
Hy4 Preview
0.00%± 3.46
(98/98)

Finance Agent v2.1 *

Kimi K3
0.00%± 2.09
(44/44)
Hy4 Preview
0.00%± 2.06
(44/44)

Tax Agent Bench *

Kimi K3
0.00%± 3.39
(89/89)
Hy4 Preview
0.00%± 3.38
(89/89)

MedCode *

Kimi K3
0.00%± 2.20
(107/107)
Hy4 Preview
0.00%± 2.13
(107/107)

Terminal-Bench-Science

Kimi K3
0.00%± 1.43
(47/47)
Hy4 Preview
0.00%± 1.43
(47/47)

Code Migration v1.1 *

Kimi K3
0.00%± 3.78
(30/30)
Hy4 Preview
0.00%± 3.59
(30/30)

Terminal-Bench 4.0

Kimi K3
0.00%± 0.51
(68/68)
Hy4 Preview
0.00%± 1.34
(68/68)

Vibe Code Bench v1.1 *

Kimi K3
0.00%± 2.75
(132/132)
Hy4 Preview
0.00%± 4.04
(132/132)

Overall performance

Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, legal, and tax

2026-11-16

Comparison by Industry

Model performance on different sections of the economy.

Legal
53.38%
45.90%
Finance
61.34%
54.40%
Healthcare
68.70%
63.42%
Math
87.00%
75.00%
Science
37.01%
35.34%
Academic
89.68%
N/A
Education
86.77%
N/A
Coding
50.80%
38.05%
Cyber
50.14%
33.82%
Social Mobility
70.30%
68.61%

Cost Analysis

Per task and per token model pricing.

Vals Index · USD
$7.169
$1.568
Cost / TestVals Index
$7.169
$1.568
Input Cost/ 1M Tokens
$3.00
$0.834
Input Cache Read/ 1M Tokens
$0.30
$0.042
Output Cost/ 1M Tokens
$15.00
$2.501

Model Metadata

Basic information about each model.

Model provider
Moonshot AIKimi
TencentOpenrouter
Latency4496.01s3562.64s
Cost (In/Out)$3 / $15$0.834 / $2.501
Context Window1M1M
Max Output Token1M64k
Input Modality