- Score
- 9.4 (+4.65 points)
- Total Cost (Current Price)
- $0.183 · 6.2% cheaper
- Response Time (avg)
- 6.24s · 92.4% faster
NVIDIA
Release: 2026-08-11
Tested on: 2026-10-01 03:45
nvidia/nemotron-3.5-lightning::medium
30B total (3B active)MoEWeights available
Summary
Nemotron 3.5 Lightning scores 4.7 on AI BENCHY and ranks #400. It has 9.8 reliability, a 47.8% pass rate, $0.195 total cost, and 81.93s average response time.
What makes Nemotron 3.5 Lightning unique: It stands out most in Anti-AI Tricks, where it ranks #1, while Agentic is its weakest area at #13. It uses unusually many reasoning tokens, which can help explain its slower or more expensive runs.
Recommended alternatives
We recommend choosing one of these models instead:
- Score
- 8.6 (+3.86 points)
- Total Cost (Current Price)
- $0.061 · 68.9% cheaper
- Response Time (avg)
- 7.51s · 90.8% faster
- Score
- 7.5 (+2.83 points)
- Total Cost (Current Price)
- $0.000 · 100.0% cheaper
- Response Time (avg)
- 29.38s · 64.1% faster
Model facts
Researched on 2026-08-12
- Parameters
- 30B total (3B active)
- Architecture
- MoE
- Availability
- Weights available
- License
- NVIDIA Open Model
4.7
Consistency
5.8
9.8
Total Output Tokens
732,696
Total Input Tokens
195,780
Input Price
$0.060 / 1M
Output Price
$0.160 / 1M
Cache Read Price
$0.030 / 1M
Cache Write Price
N/A
Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.
Flaky tests
12
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#400 Nemotron 3.5 Lightning
medium- Cost
- $0.000
- Time
- 130.5s
- Tokens
- 6,750 tok
Run history
| Tested on | Score | Reliability | Tests Correct | Total Cost | Compare |
|---|---|---|---|---|---|
| 2026-10-01 03:45 Re-test | 4.7 | 9.8 | $0.195 |