Compare Models

Select models (max 7)
DeepSeek V4GLM 5.3 Flash
Benchmarks

Vals Index *

DeepSeek V4
N/A
GLM 5.3 Flash
0.00%± 1.25
(41/41)

Legal Research Bench *

DeepSeek V4
0.00%± 2.93
(98/98)
GLM 5.3 Flash
0.00%± 3.46
(98/98)

Finance Agent v2.1 *

DeepSeek V4
N/A
GLM 5.3 Flash
0.00%± 2.03
(44/44)

Tax Agent Bench *

DeepSeek V4
0.00%± 3.06
(89/89)
GLM 5.3 Flash
0.00%± 3.35
(89/89)

MedCode *

DeepSeek V4
0.00%± 2.12
(107/107)
GLM 5.3 Flash
N/A

Terminal-Bench-Science

DeepSeek V4
N/A
GLM 5.3 Flash
0.00%± 2.01
(47/47)

Code Migration v1.1 *

DeepSeek V4
N/A
GLM 5.3 Flash
0.00%± 2.99
(30/30)

Terminal-Bench 4.0

DeepSeek V4
0.00%± 1.34
(68/68)
GLM 5.3 Flash
0.00%± 2.67
(68/68)

Vibe Code Bench v1.1 *

DeepSeek V4
0.00%± 4.77
(132/132)
GLM 5.3 Flash
0.00%± 5.28
(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
51.70%
46.51%
Finance
48.62%
58.50%
Healthcare
57.80%
88.94%
Math
16.00%
21.00%
Science
N/A
2.86%
Academic
88.32%
86.14%
Education
N/A
89.25%
Coding
46.20%
48.12%
Cyber
N/A
28.98%
Social Mobility
62.92%
71.11%

Cost Analysis

Per task and per token model pricing.

Vals Index · USD
N/A
$2.049
Cost / TestVals Index
N/A
$2.049
Input Cost/ 1M Tokens
$1.32
$0.15
Input Cache Read/ 1M Tokens
$0.044
$0.03
Output Cost/ 1M Tokens
$3.96
$0.50

Model Metadata

Basic information about each model.

Model provider
DeepSeekDeepSeek
zAIzAI
LatencyN/A3830.63s
Cost (In/Out)$1.32 / $3.96$0.15 / $0.5
Context Window1M1M
Max Output Token384k128k
Input Modality