Compare Models

Select models (max 5)
Nemotron 3.5 LightningClaude Haiku 5.5
Benchmarks

Vals Index *

Nemotron 3.5 Lightning
N/A
Claude Haiku 5.5
0.00%± 1.41
(45/45)

Legal Research Bench *

Nemotron 3.5 Lightning
0.00%± 1.16
(75/75)
Claude Haiku 5.5
0.00%± 3.44
(75/75)

Finance Agent (v2) *

Nemotron 3.5 Lightning
0.00%± 0.88
(76/76)
Claude Haiku 5.5
0.00%± 2.13
(76/76)

Tax Agent Bench *

Nemotron 3.5 Lightning
0.00%± 2.05
(67/67)
Claude Haiku 5.5
0.00%± 3.22
(67/67)

Code Migration *

Nemotron 3.5 Lightning
0.00%± 0.95
(74/74)
Claude Haiku 5.5
N/A

Terminal-Bench 4.0

Nemotron 3.5 Lightning
N/A
Claude Haiku 5.5
0.00%± 2.20
(45/45)

Vibe Code Bench v1.1 *

Nemotron 3.5 Lightning
0.00%± 0.00
(110/110)
Claude Haiku 5.5
0.00%± 1.73
(110/110)

Overall performance

Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law

2026-10-07

Comparison by Industry

Model performance on different sections of the economy.

Legal
1.44%
22.26%
Finance
16.16%
58.45%
Healthcare
4.27%
N/A
Math
0.00%
86.00%
Coding
13.94%
57.69%
Cyber
29.46%
N/A

Cost Analysis

Per task and per token model pricing.

Vals Index · USD
N/A
$2.991
Cost / TestVals Index
N/A
$2.991
Input Cost/ 1M Tokens
$0.05
$0.10
Input Cache Write/ 1M Tokens
N/A
$0.125
Input Cache Read/ 1M Tokens
$0.01
$0.01
Output Cost/ 1M Tokens
$0.20
$0.50

Model Metadata

Basic information about each model.

Model provider
NVIDIAFireworks
AnthropicAnthropic
LatencyN/A2836.53s
Cost (In/Out)$0.05 / $0.2$0.1 / $0.5
Context Window262k1M
Max Output Token131k128k
Input Modality