Models / minimax-m3-1-flash

MiniMax M3.1 Flash

MiniMax'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. MiniMax M3.1 Flash is ranked by its one configuration: the tenth-highest score of 16 models, not clearly different from 9 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 →

42%
within 3 attempts (c@3), 95% CI 37–47 · high · tenth-highest score of 16 models, not clearly different from 9 other models
9.6k
output tokens per task · median 5.6k, p90 25k
958 s
median per task, every attempt counted, on 4× NVIDIA GB10, 128 GB each (3× DGX Spark, 1× Gigabyte AI TOP ATOM) · 90th percentile 5347 s
0%
no answer within the 32,768-token budget
Every configuration of MiniMax M3.1 Flash on the Local board
ConfigurationRank all configsWithin 3 attempts c@3 · 95% CITokens mean · median · p90No answerLatency median per task, every attempt counted
NVFP4 experts, MXFP8 (QAT) · vLLM · high · 4× NVIDIA GB10, 128 GB each (3× DGX Spark, 1× Gigabyte AI TOP ATOM)highest score18
42%95% CI 37–47
9.6k5.6k · 25k0%958 s

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

Suites, at its highest-scoring configuration
high · NVFP4 experts, MXFP8 (QAT) · vLLM · 4× NVIDIA GB10, 128 GB each (3× DGX Spark, 1× Gigabyte AI TOP ATOM): 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
55%, 95% interval 34–74%
Salesforce APIs
33%, 95% interval 16–56%
CI/CD
35%, 95% interval 17–59%
Salesforce CLI
40%, 95% interval 22–61%
Salesforce docs
12%, 95% interval 3–34%
fflib Enterprise Patterns
0%, 95% interval 0–18%
Flow
17%, 95% interval 6–39%
Governor limits & pushback
68%, 95% interval 46–85%
Lightning Web Components
83%, 95% interval 61–94%
Nonprofit Success Pack
50%, 95% interval 29–71%
Packaging
28%, 95% interval 13–51%
Permissions & access
67%, 95% interval 42–85%
Scratch org definitions
11%, 95% interval 3–33%
SOQL
85%, 95% interval 64–95%
Trigger Actions Framework
50%, 95% interval 29–71%
    Show the numbers
    Per-suite scores of MiniMax M3.1 Flash's highest-scoring configuration on the Local board, with the board's median
    Suitec@3 95% CILocal medianTasks
    Apex
    55%95% CI 34–74
    		70%20
    Salesforce APIs
    33%95% CI 16–56
    		42%18
    CI/CD
    35%95% CI 17–59
    		44%17
    Salesforce CLI
    40%95% CI 22–61
    		38%20
    Salesforce docs
    12%95% CI 3–34
    		12%17
    fflib Enterprise Patterns
    0%95% CI 0–18
    		17%18
    Flow
    17%95% CI 6–39
    		17%18
    Governor limits & pushback
    68%95% CI 46–85
    		76%19
    Lightning Web Components
    83%95% CI 61–94
    		83%18
    Nonprofit Success Pack
    50%95% CI 29–71
    		56%18
    Packaging
    28%95% CI 13–51
    		28%18
    Permissions & access
    67%95% CI 42–85
    		57%15
    Scratch org definitions
    11%95% CI 3–33
    		11%18
    SOQL
    85%95% CI 64–95
    		85%20
    Trigger Actions Framework
    50%95% CI 29–71
    		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