# Angelo benchmark results: rc6-opus

The raw results behind https://angelo.studio/benchmark, for one model (opus), from one measurement campaign
(tests/python/angelo_agent/final_runs.py in the Angelo repository; doc/angelo/final_runs.rst).

Generated by tools/bench-results.mjs in the website repository. Local paths, the account's user name,
connection, session and other IDs, e-mail addresses and Claude Code's own tool list are removed or replaced
by placeholders such as <local path> and <id>. Transcripts, logs and the campaign's own configuration are not
included. Costs are Claude Code's own estimates at list prices, not a bill: both sides ran on a subscription.

- head-to-head/everyday/SUMMARY.md (11,909 bytes): The five everyday tasks, both sides: the report.
- head-to-head/everyday/results.json (207,129 bytes): The five everyday tasks, both sides: every request of every trial.
- head-to-head/session/SUMMARY.md (27,095 bytes): The 40-task session, both sides: the report.
- head-to-head/session/results.json (1,236,975 bytes): The 40-task session, both sides: every request of every trial.
- head-to-head/scenes/camera/ONESHOT-REPORT.md (9,104 bytes): Scene “camera”: the report, every trial of both sides.
- head-to-head/scenes/camera/scorecard.json (294,727 bytes): Scene “camera”: each trial's checks, path and scene hygiene.
- head-to-head/scenes/camera/results.json (95,469 bytes): Scene “camera”: every request of every trial.
- head-to-head/scenes/cube/ONESHOT-REPORT.md (9,303 bytes): Scene “cube”: the report, every trial of both sides.
- head-to-head/scenes/cube/scorecard.json (295,986 bytes): Scene “cube”: each trial's checks, path and scene hygiene.
- head-to-head/scenes/cube/results.json (100,192 bytes): Scene “cube”: every request of every trial.
- head-to-head/scenes/footbridge/ONESHOT-REPORT.md (9,294 bytes): Scene “footbridge”: the report, every trial of both sides.
- head-to-head/scenes/footbridge/scorecard.json (297,709 bytes): Scene “footbridge”: each trial's checks, path and scene hygiene.
- head-to-head/scenes/footbridge/results.json (104,111 bytes): Scene “footbridge”: every request of every trial.
- head-to-head/scenes/footbridge-arched/ONESHOT-REPORT.md (9,450 bytes): Scene “footbridge-arched”: the report, every trial of both sides.
- head-to-head/scenes/footbridge-arched/scorecard.json (298,702 bytes): Scene “footbridge-arched”: each trial's checks, path and scene hygiene.
- head-to-head/scenes/footbridge-arched/results.json (103,288 bytes): Scene “footbridge-arched”: every request of every trial.
- head-to-head/scenes/lighting/ONESHOT-REPORT.md (10,938 bytes): Scene “lighting”: the report, every trial of both sides.
- head-to-head/scenes/lighting/scorecard.json (299,685 bytes): Scene “lighting”: each trial's checks, path and scene hygiene.
- head-to-head/scenes/lighting/results.json (103,795 bytes): Scene “lighting”: every request of every trial.
- gate/default/SUMMARY.md (10,979 bytes): Release gate, Angelo only: the five everyday tasks and a staged preview.
- gate/default/results.json (76,882 bytes): Release gate, Angelo only: the five everyday tasks and a staged preview.
- gate/long/SUMMARY.md (22,027 bytes): Release gate, Angelo only: the 40-task session.
- gate/long/results.json (278,801 bytes): Release gate, Angelo only: the 40-task session.
- gate/smoke-ask/SUMMARY.md (10,831 bytes): Release gate smoke: the everyday tasks in Ask mode.
- gate/smoke-ask/results.json (33,108 bytes): Release gate smoke: the everyday tasks in Ask mode.
- gate/smoke-gate7/results.json (35,705 bytes): Release gate smoke: seven gate tasks.
- gate/smoke-survey/results.json (39,545 bytes): Release gate smoke: eight survey questions.
- gate/GATE-STATUS.json (579 bytes): Every gate step's pass count and median time.
- journal.jsonl (28,139 bytes): Every trial with the machine's load, and every pause for a busy machine.

The pictures of what each side produced are on the page, one per trial and view:
/media/bench/rc6-opus/<scene>/<side>-<trial>-<view>-<width>.webp