Compare Models

Select models (max 7)
Qwen 3.8 MaxDeepSeek V4 Pro 0813
Benchmarks

Vals Index *

Qwen 3.8 Max
N/A
DeepSeek V4 Pro 0813
0.00%± 1.04
(41/41)

Legal Research Bench *

Qwen 3.8 Max
0.00%± 3.47
(98/98)
DeepSeek V4 Pro 0813
0.00%± 3.42
(98/98)

Finance Agent v2.1 *

Qwen 3.8 Max
N/A
DeepSeek V4 Pro 0813
0.00%± 2.08
(44/44)

Tax Agent Bench *

Qwen 3.8 Max
0.00%± 3.37
(89/89)
DeepSeek V4 Pro 0813
0.00%± 3.09
(89/89)

MedCode *

Qwen 3.8 Max
0.00%± 2.03
(107/107)
DeepSeek V4 Pro 0813
0.00%± 2.16
(107/107)

Terminal-Bench-Science

Qwen 3.8 Max
0.00%± 4.03
(47/47)
DeepSeek V4 Pro 0813
0.00%± 2.44
(47/47)

Code Migration v1.1 *

Qwen 3.8 Max
N/A
DeepSeek V4 Pro 0813
0.00%± 2.23
(30/30)

Terminal-Bench 4.0

Qwen 3.8 Max
0.00%± 3.94
(68/68)
DeepSeek V4 Pro 0813
0.00%± 2.02
(68/68)

Vibe Code Bench v1.1 *

Qwen 3.8 Max
0.00%± 5.36
(132/132)
DeepSeek V4 Pro 0813
0.00%± 3.15
(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
67.11%
48.93%
Finance
59.41%
55.51%
Healthcare
62.81%
61.32%
Math
58.00%
50.00%
Science
13.98%
4.29%
Academic
90.11%
89.70%
Education
81.76%
N/A
Coding
53.24%
54.72%
Cyber
28.57%
37.38%
Social Mobility
73.02%
N/A

Cost Analysis

Per task and per token model pricing.

Vals Index · USD
N/A
$2.50
Cost / TestVals Index
N/A
$2.50
Input Cost/ 1M Tokens
$2.00
$1.32
Input Cache Write/ 1M Tokens
$2.50
N/A
Input Cache Read/ 1M Tokens
$0.25
$0.044
Output Cost/ 1M Tokens
$6.00
$3.96

Model Metadata

Basic information about each model.

Model provider
AlibabaAlibaba
DeepSeekDeepSeek
LatencyN/A3482.91s
Cost (In/Out)$2 / $6$1.32 / $3.96
Context Window1M1M
Max Output Token128k384k
Input Modality