Models / nemotron-3-5-bolt

Nemotron 3.5 Bolt

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 Bolt is ranked by its one configuration: the 16th-highest score of 16 models, not clearly different from 2 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 →

24%
within 3 attempts (c@3), 95% CI 20–28 · thinking on · 16th-highest score of 16 models, not clearly different from 2 other models
15k
output tokens per task · median 12k, p90 33k
2098 s
median per task, every attempt counted, on 1× NVIDIA DGX Spark (GB10, 128 GB) · 90th percentile 5773 s
17%
no answer within the 32,768-token budget
Every configuration of Nemotron 3.5 Bolt on the Local board
ConfigurationRank all configsWithin 3 attempts c@3 · 95% CITokens mean · median · p90No answerLatency median per task, every attempt counted
IQ2_XXS + NVFP4 + Q8_0 mixed (NVIDIA ModelOpt) · TensorFold (Zig) · thinking on · 1× NVIDIA DGX Spark (GB10, 128 GB)highest score30
24%95% CI 20–28
15k12k · 33k17%2098 s

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

Suites, at its highest-scoring configuration
thinking on · IQ2_XXS + NVFP4 + Q8_0 mixed (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
40%, 95% interval 22–61%
Salesforce APIs
22%, 95% interval 9–45%
CI/CD
29%, 95% interval 13–53%
Salesforce CLI
5%, 95% interval 1–24%
Salesforce docs
0%, 95% interval 0–18%
fflib Enterprise Patterns
0%, 95% interval 0–18%
Flow
11%, 95% interval 3–33%
Governor limits & pushback
58%, 95% interval 36–77%
Lightning Web Components
6%, 95% interval 1–26%
Nonprofit Success Pack
50%, 95% interval 29–71%
Packaging
17%, 95% interval 6–39%
Permissions & access
20%, 95% interval 7–45%
Scratch org definitions
6%, 95% interval 1–26%
SOQL
80%, 95% interval 58–92%
Trigger Actions Framework
17%, 95% interval 6–39%
    Show the numbers
    Per-suite scores of Nemotron 3.5 Bolt's highest-scoring configuration on the Local board, with the board's median
    Suitec@3 95% CILocal medianTasks
    Apex
    40%95% CI 22–61
    		70%20
    Salesforce APIs
    22%95% CI 9–45
    		42%18
    CI/CD
    29%95% CI 13–53
    		44%17
    Salesforce CLI
    5%95% CI 1–24
    		38%20
    Salesforce docs
    0%95% CI 0–18
    		12%17
    fflib Enterprise Patterns
    0%95% CI 0–18
    		17%18
    Flow
    11%95% CI 3–33
    		17%18
    Governor limits & pushback
    58%95% CI 36–77
    		76%19
    Lightning Web Components
    6%95% CI 1–26
    		83%18
    Nonprofit Success Pack
    50%95% CI 29–71
    		56%18
    Packaging
    17%95% CI 6–39
    		28%18
    Permissions & access
    20%95% CI 7–45
    		57%15
    Scratch org definitions
    6%95% CI 1–26
    		11%18
    SOQL
    80%95% CI 58–92
    		85%20
    Trigger Actions Framework
    17%95% CI 6–39
    		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