#241

Nemotron 3.5 Lightning

NVIDIA Release: 2026-08-11 Tested on: 2026-08-14 03:50 nvidia/nemotron-3.5-lightning::high

30B total (3B active)MoEWeights available

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

Summary

Nemotron 3.5 Lightning scores 5.6 on AI BENCHY and ranks #241. It has 9.9 reliability, a 50.0% pass rate, $0.134 total cost, and 58.26s average response time.

What makes Nemotron 3.5 Lightning unique: It stands out most in Combined, where it ranks #3, while Domain specific is its weakest area at #10. 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

5.6

Consistency

5.6

Reliability

9.9

Total Cost (Current Price)

$0.134 ↕ New

Tested at: $0.000

Total Output Tokens

654,597

Total Input Tokens

118,016

Input Price

$0.080 / 1M

Output Price

$0.200 / 1M

Tests Correct

Wrong Tests: 17

Attempt pass rate: 50.0%

Flaky tests

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

Response Time (avg)

58.26s

Response Time (max): 285.26s

Response Time (total): 1281.79s

Wrong answer: 11 Did not follow instructions: 4 Extra formatting: 1 Invalid tool call: 1

Hamster playing table tennis

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

#241 Nemotron 3.5 Lightning

high

Cost: $0.000
Time: 92.8s
Tokens: 11,343 tok

Run history

Tested on	Score	Reliability	Tests Correct	Total Cost	Compare
2026-08-14 03:50 Re-test	5.6	9.9		$0.134