AI BENCHY
Advertise here
#208

Nemotron 3.5 Lightning

NVIDIA Release: 2026-08-11 Tested on: 2026-08-11 18:28 nvidia/nemotron-3.5-lightning::medium
(high) (medium) (low) (none)

Summary

Nemotron 3.5 Lightning scores 5.2 on AI BENCHY and ranks #208. It has 9.9 reliability, a 47.0% pass rate, $0.193 total cost, and 69.64s average response time.

What makes Nemotron 3.5 Lightning unique: It stands out most in Instructions following, where it ranks #1, while Data parsing and extraction is its weakest area at #15. It uses unusually many reasoning tokens, which can help explain its slower or more expensive runs.

Score

5.2

Consistency

6.4

Total Cost (Current Price)

$0.193 ↕ New

Tested at: $0.000

Total Output Tokens

741,084

Total Input Tokens

126,321

Input Price

$0.100 / 1M

Output Price

$0.250 / 1M

Tests Correct

Wrong Tests: 17

Attempt pass rate: 47.0%

Flaky tests

10

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

Response Time (avg)

69.64s

Response Time (max): 437.11s

Response Time (total): 1532.18s

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price
2026-08-11 17:51 $0.000 / 1M $0.000 / 1M
2026-08-11 18:26 $0.100 / 1M $0.250 / 1M

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 6.9 7.9
Coding 4.4 5.1
Combined 6.2 5.8
Data parsing and extraction 3.7 1.7
Domain specific 2.9 7.2
General Intelligence 5.5 10.0
Instructions following 8.5 6.8
Puzzle Solving 4.2 4.4
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models