DataLearner logo

Nemotron 3.5 Super VL Benchmark Details

Nemotron 3.5 Super VL currently shows benchmark results led by GPQA Diamond (46 / 258, score 89.52), CritPt (74 / 206, score 10.86), BrowseComp (23 / 61, score 78). This page also compares it with 2 competitor models, including performance and pricing views when available.

Benchmark Results

Nemotron 3.5 Super VL

Benchmark Results

Thinking
Tool usage

Knowledge Exams

2 evaluations
Benchmark / mode
Score
Rank/total
HLE
unknown
31.79
3 / 3
HLE
unknown
29.20
131 / 243

Scientific Reasoning

2 evaluations
Benchmark / mode
Score
Rank/total
89.52
46 / 258
CritPt
unknown
10.86
74 / 206

Repository Engineering

3 evaluations
Benchmark / mode
Score
Rank/total
SWE-bench Verified
unknownTools
71.10
61 / 120
67.72
28 / 34
DeepSWE
unknownTools
24.65
98 / 103

Service Workflows

2 evaluations
Benchmark / mode
Score
Rank/total
73.19
23 / 32
τ³-Banking
unknownTools
18.88
97 / 171

Fact Finding

1 evaluations
Benchmark / mode
Score
Rank/total
BrowseComp
unknownTools
78
23 / 61

Long Reasoning

1 evaluations
Benchmark / mode
Score
Rank/total
AA-LCR
unknown
68.62
5 / 9

Desktop Workflows

1 evaluations
Benchmark / mode
Score
Rank/total
OSWorld-Verified
unknownTools
51.14
27 / 30

Agentic Development

1 evaluations
Benchmark / mode
Score
Rank/total
Terminal-Bench 2.1
unknownTools
60.67
57 / 67

Cross-industry Work

1 evaluations
Benchmark / mode
Score
Rank/total
GDPval-AA v2
unknownTools
1211
7 / 9

Documents & Charts

1 evaluations
Benchmark / mode
Score
Rank/total
CharXiv RQ
unknown
80.82
19 / 24

Visual Understanding

2 evaluations
Benchmark / mode
Score
Rank/total
MathVision
unknown
78.16
11 / 13
BabyVision
unknown
29.60
12 / 12

Video Understanding

1 evaluations
Benchmark / mode
Score
Rank/total
32.85
2 / 2

Competitor Comparison

Benchmark scores for Nemotron 3.5 Super VL compared against top models in its class

Nemotron 3.5 Super VLGLM-5.3-FlashQwen3.8-Flash-Next
Benchmark categories:
The chart shows each model’s highest score per benchmark within the current filter. Out-of-100 benchmarks use raw heights; out-of-range benchmarks are scaled within that benchmark while labels keep the original scores.

10 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.

BenchmarkNemotron 3.5 Super VLCurrentGLM-5.3-FlashQwen3.8-Flash-Next
HLE
Accuracy
Knowledge Exams
31.79Thinking Level · High
55.30Thinking Level · High | Tools
35.90Thinking Level · Extra High
CritPt
Score
Scientific Reasoning
10.86Thinking Level · High
15.40Thinking Enabled
11.10Thinking Enabled
GPQA Diamond
Accuracy
Scientific Reasoning
89.52Thinking Level · High
90.15Thinking Level · High
91.70Thinking Level · Extra High
DeepSWE
Pass@1 (DeepSWE v1.1)
Repository Engineering
24.65Thinking Enabled | Tools
63.39Thinking Level · High | Tools
58.70Thinking Level · Extra High | Tools
SWE-bench Multilingual
Accuracy
Repository Engineering
67.72Thinking Enabled | Tools
--
81.00Thinking Level · Extra High | Tools
τ³-Banking
Score
Service Workflows
18.88Thinking Enabled | Tools
47.20Thinking Enabled | Tools
45.40Thinking Enabled | Tools
Terminal-Bench 2.1
Accuracy
Agentic Development
60.67Thinking Enabled | Tools
84.30Thinking Level · High | Tools
--
CharXiv RQ
Score
Documents & Charts
80.82Thinking Level · High
89.40Thinking Level · High | Tools
90.60Thinking Level · Extra High | Tools
BabyVision
Accuracy
Visual Understanding
29.60Thinking Level · High
53.40Thinking Level · High
--
MathVision
Accuracy
Visual Understanding
78.16Thinking Level · High
--
95.70Thinking Level · Extra High | Tools

Standard API Pricing: Nemotron 3.5 Super VL vs. Peer Models

Shows standard text input and output pricing side by side for each model. If extended-context pricing exists, the chart keeps the base rate and explains the threshold below.

Source: DataLearnerAI. Standard text prices shown here use the default supplier.

These models use different currencies or billing units, so the page falls back to raw price values instead of a shared bar chart.

GLM-5.3-Flash
Supplier: 智谱AI
Standard input: $0.15 / 1M tokens
Standard output: $0.5 / 1M tokens
Qwen3.8-Flash-Next
Supplier: 阿里巴巴
Standard input: ¥1 / 1M tokens
Standard output: ¥3 / 1M tokens
ModelSupplierStandard inputStandard outputBase price applies to
GLM-5.3-Flash
智谱AI$0.15 / 1M tokens$0.5 / 1M tokens—
Qwen3.8-Flash-Next
阿里巴巴¥1 / 1M tokens¥3 / 1M tokens—