Compare Models
Select models (max 7)
DeepSeek V3.2 (Nonthinking)DeepSeek V3.2 (Thinking)
 |  | |
|---|---|---|
| Vibe Code Bench v1.1Building web apps from scratch | N/A | 5.11%±2.13 |
Benchmarks
Vibe Code Bench v1.1 *
DeepSeek V3.2 (Nonthinking)
N/ADeepSeek V3.2 (Thinking)
0.00%± 2.13
(127/127)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, legal, and tax
•2026-11-09
Comparison by Industry
Model performance on different sections of the economy.
Legal
65.96%
vs.76.08%
Finance
N/A
vs.68.15%
Academic
79.66%
vs.82.61%
Coding
69.86%
vs.51.13%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
N/A
N/A
Cost / TestVals Index
N/A
vs.N/A
Input Cost/ 1M Tokens
$0.56
vs.$0.56
Input Cache Read/ 1M Tokens
$0.28
vs.$0.28
Output Cost/ 1M Tokens
$1.68
vs.$1.68
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Fireworks | Fireworks |
| Latency | N/A | N/A |
| Cost (In/Out) | $0.56 / $1.68 | $0.56 / $1.68 |
| Context Window | 160k | 160k |
| Max Output Token | 20k | 20k |
| Input Modality |