#316

Nemotron 3.5 Lightning

NVIDIA Release: 2026-08-11 Tested on: 2026-08-14 03:48 nvidia/nemotron-3.5-lightning::low

30B total (3B active)MoEWeights available

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

Summary

Nemotron 3.5 Lightning scores 4.8 on AI BENCHY and ranks #316. It has 9.8 reliability, a 42.4% pass rate, $0.140 total cost, and 59.81s average response time.

What makes Nemotron 3.5 Lightning unique: It stands out most in Combined, where it ranks #1, while Data parsing and extraction is its weakest area at #13. It uses unusually many reasoning tokens, which can help explain its slower or more expensive runs.

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

4.8

Consistency

6.8

Reliability

9.8

Total Cost (Current Price)

$0.140 ↕ New

Tested at: $0.000

Total Output Tokens

665,174

Total Input Tokens

138,792

Input Price

$0.080 / 1M

Output Price

$0.200 / 1M

Tests Correct

Wrong Tests: 17

Attempt pass rate: 42.4%

Flaky tests

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

Response Time (avg)

59.81s

Response Time (max): 312.21s

Response Time (total): 1315.80s

Wrong answer: 14 Did not follow instructions: 2 Invalid tool call: 1

Hamster playing table tennis

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

#316 Nemotron 3.5 Lightning

low

Cost: $0.000
Time: 32.2s
Tokens: 6,089 tok

Run history

Tested on	Score	Reliability	Tests Correct	Total Cost	Compare
2026-08-14 03:48 Re-test	4.8	9.8		$0.140