#304

Nemotron 3.5 Lightning

NVIDIA Release: 2026-08-11 Tested on: 2026-08-14 03:47 nvidia/nemotron-3.5-lightning::none

30B total (3B active)MoEWeights available

(high) (medium) (low) (none)

Summary

Nemotron 3.5 Lightning scores 4.0 on AI BENCHY and ranks #304. It has 10.0 reliability, a 16.7% pass rate, $0.007 total cost, and 1.21s average response time.

What makes Nemotron 3.5 Lightning unique: It stands out most in Data parsing and extraction, where it ranks #2, while Tool Calling is its weakest area at #10. It is notably fast compared with similar models.

Model facts

Researched on 2026-08-12

Reported

Parameters: 30B total (3B active)
Architecture: MoE
Availability: Weights available
License: NVIDIA Open Model

Parameter source Availability source

Score

4.0

Consistency

9.2

Reliability

10.0

Total Cost (Current Price)

$0.007 ↕ New

Tested at: $0.000

Total Output Tokens

2,731

Total Input Tokens

74,074

Input Price

$0.080 / 1M

Output Price

$0.200 / 1M

Tests Correct

Wrong Tests: 19

Attempt pass rate: 16.7%

Flaky tests

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

1.21s

Response Time (max): 6.30s

Response Time (total): 26.62s

Wrong answer: 16 Invalid tool call: 2 Did not follow instructions: 1

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#304 Nemotron 3.5 Lightning

none

Cost: $0.000
Time: 101.6s
Tokens: 6,775 tok

Run history

Tested on	Score	Reliability	Tests Correct	Total Cost	Compare
2026-08-14 03:47 Re-test	4.0	10.0		$0.007