CompanyBench

Mobile check deposit clearing-time auditDeposits & Funding

15 verifiers · 9 LLM-graded

EnvironmentsFreshdeskJiraSlackZeta3 SQL

TaxonomyDeposits & FundingDeposits & Funding

How each model performed on this task. Every chart states its N, and the reward carries a 95% confidence interval once there is more than one trial to measure.

Core metrics

Check Pass %

Mean share of the task's checks passing, averaged over trials. N = 10 trials per model.

  1. 74%

    Claude Opus 4.8

  2. 67%

    GPT-5.5

  3. 47%

    Gemini 3.1 Pro

  4. 22%

    Gemini 3.5 Flash

Extended metrics

Median Time

Wall-clock minutes, median across trials. N = 10 trials per model.

  1. 32m

    GPT-5.5

  2. 4m

    Claude Opus 4.8

  3. 4m

    Gemini 3.5 Flash

  4. 3m

    Gemini 3.1 Pro

Tool Calls

Tool invocations, median across trials — counted from the trajectories. N = 10 trials per model.

  1. 140

    GPT-5.5

  2. 29

    Gemini 3.5 Flash

  3. 27

    Claude Opus 4.8

  4. 25

    Gemini 3.1 Pro

Verifier × model pass rate

How often each verifier passed, per model. Green is passing, red is failing — a red band across a row is a verifier nothing clears.

VerifierGPT-5.5n=10Claude Opus 4.8n=10Gemini 3.1 Pron=10Gemini 3.5 Flashn=10
checks (15)
answer_cleared_timing_metrics90%80%50%40%
answer_in_scope_deposit_count50%50%50%0%
answer_promised_date_accuracy80%100%40%20%
answer_stuck_exposure_metrics40%70%50%40%
answer_stuck_reconciliation_split50%70%60%20%
deliverable_jira_ticket_filed80%100%10%20%
deliverable_jira_unfunded_item70%70%10%20%
deliverable_slack_channel_exists100%100%100%20%
deliverable_slack_message_content40%30%50%20%
answer_ui_recommendation90%100%100%40%
floor_read_source_ticket100%100%100%100%
floor_sql_investigation100%100%100%100%
floor_write_back70%100%100%20%
trace_all_connectors_and_trap70%100%90%20%
trace_check_deposit_lifecycle_method10%30%0%0%

Failure modes on this task

35 tagged verifier failures, by the stage they were assigned to. Higher is worse.

Failure stageGPT-5.5Claude Opus 4.8Gemini 3.1 ProGemini 3.5 Flash
Answer1 mode781010