Models / claude-sonnet-5

Claude Sonnet 5

Anthropic's model, with closed weights. Forcebench has run it in 4 configurations 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. Claude Sonnet 5 is ranked by the highest-scoring of its 4 configurations: the 13th-highest score of 26 models, not clearly different from 5 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 →

77%
within 3 attempts (c@3), 95% CI 73–81 · high · 13th-highest score of 26 models, not clearly different from 5 other models
2.4k
output tokens per task · median 978, p90 7.2k
11 s
median per task, every attempt counted, including network and queueing · 90th percentile 141 s
0%
no answer within the 32,768-token budget
$0.059
per task at the list price of 10 October 2026, every attempt counted
$0.076
per solved task: the total cost over the tasks solved · cost and speed
Every configuration
Within 3 attempts (c@3) with 95% intervals, highest first. Bars whose intervals overlap are not clearly different.
  • 95% interval
high Anthropichighest score
77%, 95% interval 73–81%
medium Anthropic
75%, 95% interval 71–79%
thinking off Anthropic
71%, 95% interval 67–76%
low Anthropic
69%, 95% interval 64–74%
    Show the numbers
    Every configuration of Claude Sonnet 5 on the API board
    ConfigurationRank all configsWithin 3 attempts c@3 · 95% CIAgainst the highest by 95% interval overlapTokens mean · median · p90No answerLatency median per task, every attempt countedCost per taskCost per solved task
    Anthropic · highhighest score21
    77%95% CI 73–81
    		—2.4k978 · 7.2k0%11 s$0.059$0.076
    Anthropic · medium24
    75%95% CI 71–79
    		not clearly different1.2k562 · 3.3k0%9.0 s$0.034$0.045
    Anthropic · thinking off26
    71%95% CI 67–76
    		not clearly different919586 · 2.1k0%8.0 s$0.023$0.032
    Anthropic · low28
    69%95% CI 64–74
    		not clearly different730408 · 2k0%5.8 s$0.022$0.032
    Suites, at its highest-scoring configuration
    high · Anthropic: 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
    90%, 95% interval 70–97%
    Salesforce APIs
    89%, 95% interval 67–97%
    CI/CD
    76%, 95% interval 53–90%
    Salesforce CLI
    90%, 95% interval 70–97%
    Salesforce docs
    24%, 95% interval 10–47%
    fflib Enterprise Patterns
    67%, 95% interval 44–84%
    Flow
    100%, 95% interval 82–100%
    Governor limits & pushback
    79%, 95% interval 57–91%
    Lightning Web Components
    100%, 95% interval 82–100%
    Nonprofit Success Pack
    83%, 95% interval 61–94%
    Packaging
    72%, 95% interval 49–88%
    Permissions & access
    80%, 95% interval 55–93%
    Scratch org definitions
    50%, 95% interval 29–71%
    SOQL
    100%, 95% interval 84–100%
    Trigger Actions Framework
    56%, 95% interval 34–75%
      Show the numbers
      Per-suite scores of Claude Sonnet 5's highest-scoring configuration on the API board, with the board's median
      Suitec@3 95% CIAPI medianTasks
      Apex
      90%95% CI 70–97
      		90%20
      Salesforce APIs
      89%95% CI 67–97
      		72%18
      CI/CD
      76%95% CI 53–90
      		88%17
      Salesforce CLI
      90%95% CI 70–97
      		90%20
      Salesforce docs
      24%95% CI 10–47
      		29%17
      fflib Enterprise Patterns
      67%95% CI 44–84
      		61%18
      Flow
      100%95% CI 82–100
      		69%18
      Governor limits & pushback
      79%95% CI 57–91
      		89%19
      Lightning Web Components
      100%95% CI 82–100
      		100%18
      Nonprofit Success Pack
      83%95% CI 61–94
      		81%18
      Packaging
      72%95% CI 49–88
      		69%18
      Permissions & access
      80%95% CI 55–93
      		87%15
      Scratch org definitions
      50%95% CI 29–71
      		50%18
      SOQL
      100%95% CI 84–100
      		100%20
      Trigger Actions Framework
      56%95% CI 34–75
      		86%18

      By reasoning effort

      The same configuration at several efforts, each against its lowest reasoning effort on the same tasks (a paired 95% interval), and charted against the effort tier and against the output tokens it costs. These scores are pass@1, the first answer alone: a paired comparison needs both efforts' answers to the same tasks, and not every effort has had its retries. Lite-subset sweeps (4 tasks per suite) are never plotted with the full benchmark. The effort study has every model.

      Claude Sonnet 5 by reasoning effort, full benchmark: each effort against the sweep's lowest reasoning effort
      Configuration · effort · full benchmarkpass@1 95% CIAgainst the lowest reasoning effort same tasks, pairedTokens
      thinking off
      58%95% CI 52–63
      		no clear difference (+3 pts, 95% CI −2 pts to +7 pts); this data can't rule out a change of up to 7 points919
      lowbaseline
      55%95% CI 50–61
      		—730
      medium
      60%95% CI 55–65
      		no clear difference (+5 pts, 95% CI ±0 pts to +9 pts); this data can't rule out a change of up to 9 points1.2k
      high
      65%95% CI 60–70
      		clearly higher (+10 pts, 95% CI +5 pts to +14 pts)2.4k
      Score by effort tier · full benchmark
      Overall pass@1; vertical bars are 95% confidence intervals.
      Claude Sonnet 5, full benchmark: pass@1 by reasoning effort tierClaude Sonnet 5: off 58%, low 55%, medium 60%, high 65%0%25%50%75%100%Thinking offLowMediumHighReasoning effort tierpass@1Claude Sonnet 5
      Show the numbers
      ModelEffort (tier)pass@195% CITasksNo answerTokens: meanmedianLatency: median per answer
      Claude Sonnet 5thinking off58%52–632720%9195866.6 s
      Claude Sonnet 5low55%50–612720%7304085.0 s
      Claude Sonnet 5medium60%55–652720%1.2k5627.2 s
      Claude Sonnet 5high · vendor default65%60–702720%2.4k9789.8 s
      Score against output tokens · full benchmark
      Each point is one effort setting. Further right means more output tokens per task. The numbers are under the chart above.
      Claude Sonnet 5, full benchmark: pass@1 against mean output tokens per taskClaude Sonnet 5: 919 tokens 58%, 730 tokens 55%, 1.2k tokens 60%, 2.4k tokens 65%0%25%50%75%100%1k2kMean output tokens per task (log scale)pass@1lowthinking offmediumhighClaude Sonnet 5

      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