DataLearner logo

Nemotron 3.5 Lightning Benchmark Details

Nemotron 3.5 Lightning currently shows benchmark results led by PinchBench v2 (6 / 45, score 86.40), GPQA Diamond (287 / 462, score 74.30), HLE (385 / 563, score 10.60).

Benchmark Results

Nemotron 3.5 Lightning

Benchmark Results

Thinking
Tool usage

General Knowledge

1 evaluations
Benchmark / mode
Score
Rank/total
HLE
Thinking Enabled
10.60
385 / 563

Other

1 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Thinking Enabled
74.30
287 / 462

Writing and Creative Capabilities

1 evaluations
Benchmark / mode
Score
Rank/total
Creative Writing
Standard Mode
1276.50
74 / 106

AI Agent - Tool Usage

2 evaluations
Benchmark / mode
Score
Rank/total
Terminal-Bench 2.1
Thinking EnabledTools
24.30
160 / 192
Terminal-Bench 4.0
Thinking EnabledTools
0.50
81 / 86

Coding and Software Engineer

1 evaluations
Benchmark / mode
Score
Rank/total
SciCode
Thinking Enabled
32.10
121 / 130

Agent Level Benchmark

1 evaluations
Benchmark / mode
Score
Rank/total
τ³-Banking
Thinking EnabledTools
8.90
137 / 164

Multimodal Understanding

1 evaluations
Benchmark / mode
Score
Rank/total
GDP.pdf
Thinking Enabled
3
101 / 118

Claw-style Agent Evaluation

1 evaluations
Benchmark / mode
Score
Rank/total
86.40
6 / 45