Compare Models
Select models (max 7)
DeepSeek V4 Flash 0731GLM 5.3 Flash
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | N/A | 50.86%±1.25 |
| Legal Research BenchAgentic US legal research | 30.29%±3.19 | 45.19%±3.46 |
| Finance Agent v2.1Core financial analyst tasks | N/A | 60.59%±2.03 |
| Tax Agent BenchAgentic US corporate tax research | 28.07%±3.16 | 31.55%±3.35 |
| MedCodeMedical billing code support | 41.41%±2.15 | N/A |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | 4.29%±2.44 | 2.86%±2.01 |
| Code Migration v1.1Rewriting programs in new languages | N/A | 51.65%±2.99 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 18.69%±3.54 | 37.37%±2.67 |
| Vibe Code Bench v1.1Building web apps from scratch | 74.74%±3.44 | 30.76%±5.28 |
Benchmarks
Vals Index *
DeepSeek V4 Flash 0731
N/AGLM 5.3 Flash
0.00%± 1.25
(26/26)Legal Research Bench *
DeepSeek V4 Flash 0731
0.00%± 3.19
(84/84)GLM 5.3 Flash
0.00%± 3.46
(84/84)Finance Agent v2.1 *
DeepSeek V4 Flash 0731
N/AGLM 5.3 Flash
0.00%± 2.03
(30/30)Tax Agent Bench *
DeepSeek V4 Flash 0731
0.00%± 3.16
(75/75)GLM 5.3 Flash
0.00%± 3.35
(75/75)MedCode *
DeepSeek V4 Flash 0731
0.00%± 2.15
(107/107)GLM 5.3 Flash
N/ATerminal-Bench-Science
DeepSeek V4 Flash 0731
0.00%± 2.44
(42/42)GLM 5.3 Flash
0.00%± 2.01
(42/42)Code Migration v1.1 *
DeepSeek V4 Flash 0731
N/AGLM 5.3 Flash
0.00%± 2.99
(28/28)Terminal-Bench 4.0
DeepSeek V4 Flash 0731
0.00%± 3.54
(54/54)GLM 5.3 Flash
0.00%± 2.67
(54/54)Vibe Code Bench v1.1 *
DeepSeek V4 Flash 0731
0.00%± 3.44
(118/118)GLM 5.3 Flash
0.00%± 5.28
(118/118)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-10-22
Comparison by Industry
Model performance on different sections of the economy.
Legal
54.00%
vs.46.51%
Finance
49.38%
vs.58.50%
Healthcare
60.89%
vs.88.94%
Math
56.00%
vs.21.00%
Science
34.37%
vs.2.86%
Academic
88.05%
vs.86.14%
Coding
50.41%
vs.44.55%
Cyber
72.08%
vs.34.31%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
N/A
$1.134
Cost / TestVals Index
N/A
vs.$1.134
Input Cost/ 1M Tokens
$0.44
vs.$0.075
Input Cache Read/ 1M Tokens
$0.014
vs.$0.015
Output Cost/ 1M Tokens
$1.32
vs.$0.25
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | DeepSeek | zAI |
| Latency | N/A | 3830.63s |
| Cost (In/Out) | $0.44 / $1.32 | $0.075 / $0.25 |
| Context Window | 1M | 1M |
| Max Output Token | 384k | 128k |
| Input Modality |