Models / ling-3-0-flash

Ling 3.0 Flash

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

On the API board

Models reached through a hosted service. Ling 3.0 Flash is ranked by its one configuration: the 25th-highest score of 26 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 → Cost and speed →

36%
within 3 attempts (c@3), 95% CI 32–41 · thinking on · 25th-highest score of 26 models, not clearly different from 2 other models
4.9k
output tokens per task · median 1.9k, p90 11k
101 s
median per task, every attempt counted, including network and queueing · 90th percentile 653 s
2%
no answer within the 32,768-token budget
$0.0024
per task at the list price of 10 October 2026, every attempt counted
$0.0065
per solved task: the total cost over the tasks solved · cost and speed
Every configuration of Ling 3.0 Flash on the API board
ConfigurationRank all configsWithin 3 attempts c@3 · 95% CITokens mean · median · p90No answerLatency median per task, every attempt countedCost per taskCost per solved task
OpenRouter · BF16 · thinking onhighest score39
36%95% CI 32–41
4.9k1.9k · 11k2%101 s$0.0024$0.0065
Suites, at its highest-scoring configuration
thinking on · OpenRouter · BF16: within 3 attempts (c@3) on each suite with 95% intervals, against the median of the API board's models, each at its highest-scoring configuration.
  • 95% interval
  • API board median
Apex
75%, 95% interval 53–89%
Salesforce APIs
33%, 95% interval 16–56%
CI/CD
35%, 95% interval 17–59%
Salesforce CLI
15%, 95% interval 5–36%
Salesforce docs
0%, 95% interval 0–18%
fflib Enterprise Patterns
22%, 95% interval 9–45%
Flow
11%, 95% interval 3–33%
Governor limits & pushback
74%, 95% interval 51–88%
Lightning Web Components
72%, 95% interval 49–88%
Nonprofit Success Pack
44%, 95% interval 25–66%
Packaging
17%, 95% interval 6–39%
Permissions & access
33%, 95% interval 15–58%
Scratch org definitions
11%, 95% interval 3–33%
SOQL
75%, 95% interval 53–89%
Trigger Actions Framework
28%, 95% interval 13–51%
    Show the numbers
    Per-suite scores of Ling 3.0 Flash's highest-scoring configuration on the API board, with the board's median
    Suitec@3 95% CIAPI medianTasks
    Apex
    75%95% CI 53–89
    		90%20
    Salesforce APIs
    33%95% CI 16–56
    		72%18
    CI/CD
    35%95% CI 17–59
    		88%17
    Salesforce CLI
    15%95% CI 5–36
    		90%20
    Salesforce docs
    0%95% CI 0–18
    		29%17
    fflib Enterprise Patterns
    22%95% CI 9–45
    		61%18
    Flow
    11%95% CI 3–33
    		69%18
    Governor limits & pushback
    74%95% CI 51–88
    		89%19
    Lightning Web Components
    72%95% CI 49–88
    		100%18
    Nonprofit Success Pack
    44%95% CI 25–66
    		81%18
    Packaging
    17%95% CI 6–39
    		69%18
    Permissions & access
    33%95% CI 15–58
    		87%15
    Scratch org definitions
    11%95% CI 3–33
    		50%18
    SOQL
    75%95% CI 53–89
    		100%20
    Trigger Actions Framework
    28%95% CI 13–51
    		86%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