Cloud baseline

GPT-6 Luna — 0.4797 on Gauntlet 7.2

openai/gpt-6-luna · scorer sb-7.2

GPT-6 Luna, single model via OpenRouteropenai/gpt-6-luna · single agentOct 4, 2026
Overall
0.4797
Excellent
no
Benchmark
Gauntlet 7.2
Model build
33m 30s
Prompt tok
12.9M
Gen tok
171.3k

Recorded inference cost

At least $0.23

From the saved OpenRouter generation billing summary (151 recorded requests). This is a lower bound; the billing record is incomplete. Includes auxiliary model calls made during the build. Scoring reuses the saved build; this amount describes the original inference spend.

  • The harness counted tokens no recovered generation id accounts for: prompt -972, completion -5

Token usage

Tokens: 12.9M in · 171k out · 12.8M cached (exact, OpenRouter records)

13,081,481 tokens over 151 model calls: every call of the run, the model's own and the harness's helper calls, counted from OpenRouter records. Reasoning tokens as the provider reports them: 112,739 (not added to the total).

  • openai/gpt-6-luna-20260922

    In 12.9M · Out 171k · Cached 12.8M · Reasoning 113k · 150 calls

  • google/gemini-2.5-flash

    In 972 · Out 5 · Cached 0 · Reasoning 0 · 1 call

Tier breakdown

A · structure & runtime1.00
B · behaviour0.99
C · vendor contract0.93
D · finesse0.93

Scoring detail

How this score was built

Per-check scorer output, as posted by the app. Expand a section to inspect its checks.

Earned credit before admission

(0.88 × 0.8191 core + 0.12 × 0.94 gate × 0.70 excellence) × 0.6000 critical = 0.4797

Critical defects compound a multiplier on the whole score (pre-severity 0.7996):

j_workflow_journey 0.00 → ×0.60

The core (88% of the total) is the weighted mean of the thirteen measured tiers. The last 12% is the excellence slice: it unlocks in proportion to the perfection conditions below (15 of 16 met here), then pays out at the excellence tier's own measured mean. Core 0.7208 + excellence 0.0787.

j_first_use 1.00j_workflow_journey 0.00j_error_state 1.00j_empty_state 1.00console_clean 0.00v_responsive_375 1.00v_dates_readable 1.00t_scene_binding 1.00x_conservation_residual 1.00r_no_row_loss 1.00p_drag_frames 1.00p_idle_flatness 1.00p_stream_apply 1.00p_under_stream 1.00p_api_latency 1.00p_sync_wall 1.00

Earned score 0.480 · Admission ceiling 0.669 · Final score 0.480

Final score is the lower of earned credit and the admission ceiling. Passing admission adds no points.

Visible: passedMatching: not metGood: not metVisual excellence: not metBackend excellence: passed

Tower structure, currency mapping and scene truth: s_tower_geometry, s_currency_collar (maximum 0.669)

3D interaction and overview legibility: t_pick_real_pass, q_overview_legibility, q_inspector_framing (maximum 0.739)

Event animation and backend recovery: m_committed_event_replay (maximum 0.899)

Token rates

Measured by the engine itself, one record per completed model call: prefill rate is prompt tokens over time-to-first-token, generation rate is completion tokens over the decode window. Medians per node.

NodeCallsPrompt tokGen tokPrefill tok/sGen tok/s
gemini197251641.951.0
gpt15012,909,185171,31922735.07000.0
fleet15112,910,157171,32422734.07000.0

Graded browser recording

Loading duration…

Watch the full graded browser recording at its original speed: the payment field, structure inspection, committed updates and replay. The check results and screenshots on this page provide the wider evidence. Pause or scrub to inspect a view.

Each tower represents a payment: height encodes its amount, cap color its status, and the collar its currency. The selected detailed tower is expected to animate its collar after a committed backend update or replay. These are the task requirements; the check results show what this app actually achieved.

Ready to play0:00 / —:—
Open recording file

Drag the timeline to seek. Keyboard: arrow keys move 5 seconds; Home and End jump to the start and end.

Full graded browser recording: payment field, structure inspection, committed updates and replay

Screenshots

Captured from the built application during browser grading. Captions identify the recorded views and checks; these images do not represent repair rounds.

1First captured render
2Latest captured render
3After sync
4Error state
5Mobile · 375px

Run details

Model
openai/gpt-6-luna
Engine events
0
Repair rounds
0
Started
Oct 2, 2026, 03:19 PM
Finished
Oct 2, 2026, 04:02 PM
Re-scored
Oct 4, 2026, 04:05 AM (same build, corrected scorer)

How the benchmark is scored