Compare Models

Select models (max 7)
DeepSeek V4.1 FlashKimi K3
Benchmarks

Vals Index *

DeepSeek V4.1 Flash
N/A
Kimi K3
0.00%± 1.00
(41/41)

Legal Research Bench *

DeepSeek V4.1 Flash
0.00%± 3.42
(98/98)
Kimi K3
0.00%± 3.46
(98/98)

Finance Agent v2.1 *

DeepSeek V4.1 Flash
0.00%± 2.02
(44/44)
Kimi K3
0.00%± 2.09
(44/44)

Tax Agent Bench *

DeepSeek V4.1 Flash
0.00%± 3.14
(89/89)
Kimi K3
0.00%± 3.39
(89/89)

MedCode *

DeepSeek V4.1 Flash
0.00%± 2.04
(107/107)
Kimi K3
0.00%± 2.20
(107/107)

Terminal-Bench-Science

DeepSeek V4.1 Flash
0.00%± 0.00
(47/47)
Kimi K3
0.00%± 1.43
(47/47)

Code Migration v1.1 *

DeepSeek V4.1 Flash
0.00%± 2.66
(30/30)
Kimi K3
0.00%± 3.78
(30/30)

Terminal-Bench 4.0

DeepSeek V4.1 Flash
0.00%± 1.75
(68/68)
Kimi K3
0.00%± 0.51
(68/68)

Vibe Code Bench v1.1 *

DeepSeek V4.1 Flash
0.00%± 2.89
(132/132)
Kimi K3
0.00%± 2.75
(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
63.42%
53.38%
Finance
53.27%
61.34%
Healthcare
63.34%
68.70%
Math
54.00%
87.00%
Science
29.65%
37.01%
Academic
N/A
89.68%
Education
85.38%
86.77%
Coding
45.77%
50.80%
Cyber
37.23%
50.14%
Social Mobility
69.99%
70.30%

Cost Analysis

Per task and per token model pricing.

Vals Index · USD
N/A
$7.169
Cost / TestVals Index
N/A
$7.169
Input Cost/ 1M Tokens
$0.30
$3.00
Input Cache Read/ 1M Tokens
$0.006
$0.30
Output Cost/ 1M Tokens
$1.20
$15.00

Model Metadata

Basic information about each model.

Model provider
DeepSeekDeepSeek
Moonshot AIKimi
LatencyN/A4496.01s
Cost (In/Out)$0.3 / $1.2$3 / $15
Context Window1M1M
Max Output Token384k1M
Input Modality