Compare Models
Select models (max 5)
DeepSeek V4.1 Flash 1017Gemini 3.8 Flash
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 56.58%±1.27 | 54.89%±1.02 |
| Legal Research BenchAgentic US legal research | 45.19%±3.46 | 38.94%±3.39 |
| Finance Agent (v2)Core financial analyst tasks | 56.96%±2.05 | 61.44%±0.13 |
| Tax Agent BenchAgentic US corporate tax research | 44.35%±3.57 | 32.12%±3.37 |
| MedCodeMedical billing code support | N/A | 48.13%±2.18 |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | N/A | 8.57%±3.37 |
| Code MigrationRewriting programs in new languages | 44.21%±4.46 | 36.55%±4.18 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 31.82%±2.62 | 19.70%±2.31 |
| Vibe Code Bench v1.1Building web apps from scratch | 87.73%±2.75 | 78.65%±3.88 |
Benchmarks
Vals Index *
DeepSeek V4.1 Flash 1017
0.00%± 1.27
(50/50)Gemini 3.8 Flash
0.00%± 1.02
(50/50)Legal Research Bench *
DeepSeek V4.1 Flash 1017
0.00%± 3.46
(80/80)Gemini 3.8 Flash
0.00%± 3.39
(80/80)Finance Agent (v2) *
DeepSeek V4.1 Flash 1017
0.00%± 2.05
(80/80)Gemini 3.8 Flash
0.00%± 0.13
(80/80)Tax Agent Bench *
DeepSeek V4.1 Flash 1017
0.00%± 3.57
(71/71)Gemini 3.8 Flash
0.00%± 3.37
(71/71)MedCode *
DeepSeek V4.1 Flash 1017
N/AGemini 3.8 Flash
0.00%± 2.18
(107/107)Terminal-Bench-Science
DeepSeek V4.1 Flash 1017
N/AGemini 3.8 Flash
0.00%± 3.37
(41/41)Code Migration *
DeepSeek V4.1 Flash 1017
0.00%± 4.46
(79/79)Gemini 3.8 Flash
0.00%± 4.18
(79/79)Terminal-Bench 4.0
DeepSeek V4.1 Flash 1017
0.00%± 2.62
(50/50)Gemini 3.8 Flash
0.00%± 2.31
(50/50)Vibe Code Bench v1.1 *
DeepSeek V4.1 Flash 1017
0.00%± 2.75
(114/114)Gemini 3.8 Flash
0.00%± 3.88
(114/114)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-10-18
Comparison by Industry
Model performance on different sections of the economy.
Legal
27.18%
vs.45.31%
Finance
54.37%
vs.61.11%
Healthcare
N/A
vs.66.32%
Math
N/A
vs.48.00%
Science
N/A
vs.35.76%
Academic
N/A
vs.91.25%
Education
N/A
vs.35.06%
Coding
54.59%
vs.47.99%
Cyber
N/A
vs.27.41%
Social Mobility
N/A
vs.65.29%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$0.637
$5.713
Cost / TestVals Index
$0.637
vs.$5.713
Input Cost/ 1M Tokens
$0.30
vs.$1.50
Input Cache Read/ 1M Tokens
$0.006
vs.$0.15
Output Cost/ 1M Tokens
$1.20
vs.$7.50
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | DeepSeek | Google |
| Latency | 2193.12s | 3112.49s |
| Cost (In/Out) | $0.3 / $1.2 | $1.5 / $7.5 |
| Context Window | 1M | 1M |
| Max Output Token | 384k | 66k |
| Input Modality |