Flex Reserve funding: reconstruct in-red Overview balancesReconciliation & Settlement
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.
73%
Gemini 3.1 Pro
68%
GPT-5.5
65%
Claude Opus 4.8
0%
Gemini 3.5 Flash
Extended metrics
Median Time
Wall-clock minutes, median across trials. N = 10 trials per model.
4m
Gemini 3.1 Pro
3m
Gemini 3.5 Flash
3m
GPT-5.5
3m
Claude Opus 4.8
Tool Calls
Tool invocations, median across trials — counted from the trajectories. N = 10 trials per model.
45
Gemini 3.1 Pro
36
GPT-5.5
24
Claude Opus 4.8
20
Gemini 3.5 Flash
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.
| Verifier | GPT-5.5n=10 | Claude Opus 4.8n=10 | Gemini 3.1 Pron=10 | Gemini 3.5 Flashn=10 |
|---|---|---|---|---|
| checks (12) | ||||
| answer_audited_and_recon_match | 90% | 100% | 90% | 0% |
| answer_in_red_population | 20% | 50% | 90% | 0% |
| answer_stale_target_accounts | 50% | 20% | 30% | 0% |
| deliverable_jira_ticket_filed | 100% | 100% | 90% | 0% |
| deliverable_slack_channel_exists | 100% | 100% | 100% | 0% |
| deliverable_slack_message_content | 50% | 20% | 40% | 0% |
| floor_all_connectors | 100% | 100% | 100% | 0% |
| floor_read_source_confluence | 100% | 100% | 100% | 100% |
| floor_sql_investigation | 100% | 100% | 100% | 60% |
| floor_write_back | 100% | 100% | 100% | 0% |
| trace_all_connectors_and_trap | 90% | 100% | 100% | 0% |
| trace_flex_reserve_recon_method | 0% | 60% | 0% | 0% |