Compare Models
Select models (max 5)
Nemotron 3 UltraDeepSeek V4.1 Flash 1017
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | N/A | 56.58%±1.27 |
| Legal Research BenchAgentic US legal research | 15.38%±2.51 | 45.19%±3.46 |
| Finance Agent (v2)Core financial analyst tasks | 37.67%±0.15 | 56.96%±2.05 |
| Tax Agent BenchAgentic US corporate tax research | N/A | 44.35%±3.57 |
| MedCodeMedical billing code support | 38.62%±2.00 | N/A |
| Code MigrationRewriting programs in new languages | 4.91%±1.59 | 44.21%±4.46 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | N/A | 31.82%±2.62 |
| Vibe Code Bench v1.1Building web apps from scratch | 7.64%±2.78 | 87.73%±2.75 |
Benchmarks
Vals Index *
Nemotron 3 Ultra
N/ADeepSeek V4.1 Flash 1017
0.00%± 1.27
(50/50)Legal Research Bench *
Nemotron 3 Ultra
0.00%± 2.51
(80/80)DeepSeek V4.1 Flash 1017
0.00%± 3.46
(80/80)Finance Agent (v2) *
Nemotron 3 Ultra
0.00%± 0.15
(80/80)DeepSeek V4.1 Flash 1017
0.00%± 2.05
(80/80)Tax Agent Bench *
Nemotron 3 Ultra
N/ADeepSeek V4.1 Flash 1017
0.00%± 3.57
(71/71)MedCode *
Nemotron 3 Ultra
0.00%± 2.00
(107/107)DeepSeek V4.1 Flash 1017
N/ACode Migration *
Nemotron 3 Ultra
0.00%± 1.59
(79/79)DeepSeek V4.1 Flash 1017
0.00%± 4.46
(79/79)Terminal-Bench 4.0
Nemotron 3 Ultra
N/ADeepSeek V4.1 Flash 1017
0.00%± 2.62
(50/50)Vibe Code Bench v1.1 *
Nemotron 3 Ultra
0.00%± 2.78
(114/114)DeepSeek V4.1 Flash 1017
0.00%± 2.75
(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
32.62%
vs.27.18%
Finance
47.50%
vs.54.37%
Healthcare
38.62%
vs.N/A
Academic
85.94%
vs.N/A
Coding
33.50%
vs.54.59%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
N/A
$0.637
Cost / TestVals Index
N/A
vs.$0.637
Input Cost/ 1M Tokens
N/A
vs.$0.30
Input Cache Read/ 1M Tokens
N/A
vs.$0.006
Output Cost/ 1M Tokens
N/A
vs.$1.20
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Nvidia | DeepSeek |
| Latency | N/A | 2193.12s |
| Cost (In/Out) | N/A | $0.3 / $1.2 |
| Context Window | 1M | 1M |
| Max Output Token | 128k | 384k |
| Input Modality |