Compare Models
Select models (max 5)
DeepSeek V4 Pro 0813GLM 5.2
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 47.63%±1.12 | N/A |
| Legal Research BenchAgentic US legal research | 40.87%±3.42 | 31.25%±3.22 |
| Finance Agent (v2)Core financial analyst tasks | 50.39%±0.25 | 49.70%±0.88 |
| Tax Agent BenchAgentic US corporate tax research | 58.66%±3.14 | N/A |
| MedCodeMedical billing code support | 42.47%±2.16 | 40.77%±2.17 |
| Terminal-Bench ScienceExpert-authored scientific research workflows | 4.29%±2.44 | N/A |
| Code MigrationRewriting programs in new languages | 41.54%±4.30 | 37.87%±4.14 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 14.14%±2.02 | N/A |
| Vibe Code Bench v1.1Building web apps from scratch | 82.30%±3.15 | 63.96%±4.79 |
Benchmarks
Vals Index *
DeepSeek V4 Pro 0813
0.00%± 1.12
(43/43)GLM 5.2
N/ALegal Research Bench *
DeepSeek V4 Pro 0813
0.00%± 3.42
(73/73)GLM 5.2
0.00%± 3.22
(73/73)Finance Agent (v2) *
DeepSeek V4 Pro 0813
0.00%± 0.25
(74/74)GLM 5.2
0.00%± 0.88
(74/74)Tax Agent Bench *
DeepSeek V4 Pro 0813
0.00%± 3.14
(65/65)GLM 5.2
N/AMedCode *
DeepSeek V4 Pro 0813
0.00%± 2.16
(104/104)GLM 5.2
0.00%± 2.17
(104/104)Terminal-Bench Science
DeepSeek V4 Pro 0813
0.00%± 2.44
(38/38)GLM 5.2
N/ACode Migration *
DeepSeek V4 Pro 0813
0.00%± 4.30
(73/73)GLM 5.2
0.00%± 4.14
(73/73)Terminal-Bench 4.0
DeepSeek V4 Pro 0813
0.00%± 2.02
(43/43)GLM 5.2
N/AVibe Code Bench v1.1 *
DeepSeek V4 Pro 0813
0.00%± 3.15
(108/108)GLM 5.2
0.00%± 4.79
(108/108)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-10-02
Comparison by Industry
Model performance on different sections of the economy.
Legal
43.58%
vs.40.80%
Finance
58.73%
vs.61.52%
Healthcare
61.32%
vs.62.15%
Math
50.00%
vs.N/A
Science
4.29%
vs.N/A
Academic
89.70%
vs.86.16%
Coding
49.43%
vs.49.95%
Cyber
72.86%
vs.0.00%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$3.352
N/A
Cost / TestVals Index
$3.352
vs.N/A
Input Cost/ 1M Tokens
$1.32
vs.$1.40
Input Cache Read/ 1M Tokens
$0.044
vs.$0.26
Output Cost/ 1M Tokens
$3.96
vs.$4.40
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | DeepSeek | zAI |
| Latency | 3845.24s | N/A |
| Cost (In/Out) | $1.32 / $3.96 | $1.4 / $4.4 |
| Context Window | 1M | 1M |
| Max Output Token | 384k | 131k |
| Input Modality |