Models / nemotron-3-5-super-vl

Nemotron 3.5 Super VL

NVIDIA's model, with open weights. Forcebench has run it in 1 configuration on the Local board. API is models reached through a hosted service; Local, models served on Forcebench’s own hardware.

On the Local board

Models served on Forcebench’s own hardware. Nemotron 3.5 Super VL is ranked by its one configuration: the seventh-highest score of 16 models, not clearly different from 7 other models. Scores are within 3 attempts (c@3) with 95% intervals; each configuration is compared with the highest-scoring one by whether their 95% intervals overlap. Every configuration on the board →

47%
within 3 attempts (c@3), 95% CI 42–53 · thinking on · seventh-highest score of 16 models, not clearly different from 7 other models
10k
output tokens per task · median 6.9k, p90 25k
953 s
median per task, every attempt counted, on 1× NVIDIA DGX Spark (GB10, 128 GB) · 90th percentile 4056 s
4%
no answer within the 32,768-token budget
Every configuration of Nemotron 3.5 Super VL on the Local board
ConfigurationRank all configsWithin 3 attempts c@3 · 95% CITokens mean · median · p90No answerLatency median per task, every attempt counted
NVFP4 mixed precision (NVIDIA ModelOpt) · TensorFold (Zig) · thinking on · 1× NVIDIA DGX Spark (GB10, 128 GB)highest score14
47%95% CI 42–53
10k6.9k · 25k4%953 s

Latency depends on the hardware: compare it only between configurations on the same hardware.

Suites, at its highest-scoring configuration
thinking on · NVFP4 mixed precision (NVIDIA ModelOpt) · TensorFold (Zig) · 1× NVIDIA DGX Spark (GB10, 128 GB): within 3 attempts (c@3) on each suite with 95% intervals, against the median of the Local board's models, each at its highest-scoring configuration.
  • 95% interval
  • Local board median
Apex
60%, 95% interval 39–78%
Salesforce APIs
50%, 95% interval 29–71%
CI/CD
53%, 95% interval 31–74%
Salesforce CLI
40%, 95% interval 22–61%
Salesforce docs
24%, 95% interval 10–47%
fflib Enterprise Patterns
17%, 95% interval 6–39%
Flow
22%, 95% interval 9–45%
Governor limits & pushback
79%, 95% interval 57–91%
Lightning Web Components
83%, 95% interval 61–94%
Nonprofit Success Pack
61%, 95% interval 39–80%
Packaging
33%, 95% interval 16–56%
Permissions & access
53%, 95% interval 30–75%
Scratch org definitions
11%, 95% interval 3–33%
SOQL
85%, 95% interval 64–95%
Trigger Actions Framework
39%, 95% interval 20–61%
    Show the numbers
    Per-suite scores of Nemotron 3.5 Super VL's highest-scoring configuration on the Local board, with the board's median
    Suitec@3 95% CILocal medianTasks
    Apex
    60%95% CI 39–78
    		70%20
    Salesforce APIs
    50%95% CI 29–71
    		42%18
    CI/CD
    53%95% CI 31–74
    		44%17
    Salesforce CLI
    40%95% CI 22–61
    		38%20
    Salesforce docs
    24%95% CI 10–47
    		12%17
    fflib Enterprise Patterns
    17%95% CI 6–39
    		17%18
    Flow
    22%95% CI 9–45
    		17%18
    Governor limits & pushback
    79%95% CI 57–91
    		76%19
    Lightning Web Components
    83%95% CI 61–94
    		83%18
    Nonprofit Success Pack
    61%95% CI 39–80
    		56%18
    Packaging
    33%95% CI 16–56
    		28%18
    Permissions & access
    53%95% CI 30–75
    		57%15
    Scratch org definitions
    11%95% CI 3–33
    		11%18
    SOQL
    85%95% CI 64–95
    		85%20
    Trigger Actions Framework
    39%95% CI 20–61
    		42%18

    In the studies

    Private evaluations

    Want this for your team?

    Azul Labs runs Forcebench privately for two kinds of Salesforce team.

    Choosing a model to run yourself?

    A private benchmark of your shortlist

    Open-weight models at the quantisations and reasoning efforts you could run on infrastructure you control, tested on your kind of Salesforce work, with a written recommendation.

    • Private tasks written from your work only ever run on local models; they are never sent to an API.
    • Re-testing after any change of model, quantisation or engine is available.
    • Typical turnaround is 2–3 weeks; large models take about a day of machine time per configuration.
    Get a private benchmarkHow it works

    Building or buying a Salesforce AI tool?

    A private evaluation of your tool

    Your tool on held-out tasks it has never seen, against API baselines (models reached through a hosted service) and Local ones (served on Forcebench’s own hardware), with a written report on where it holds up and where it fails.

    • It can start as a smaller pilot, about 30 held-out tasks with your tool against two baselines, before a full evaluation.
    • Repeat evaluations after your releases are available.
    • Typical turnaround is 2–3 weeks.
    Ask about an evaluationHow it works

    Fixed fee, quoted up front. The quote depends on the number of tasks and the number of models, tools or configurations tested.

    Or email leo@azl.au · azl.au