Cloud baseline

GPT Terra Latest — 0.5781 on Gauntlet 7.2

~openai/gpt-terra-latest · scorer sb-7.2

GPT Terra Latest, single model via OpenRouter~openai/gpt-terra-latest · single agentOct 6, 2026
Overall
0.5781
Excellent
no
Benchmark
Gauntlet 7.2
Model build
5m 36s
Prompt tok
2.1M
Gen tok
29.9k

Recorded inference cost

$0.91

From the saved OpenRouter generation billing summary (49 recorded requests). Includes auxiliary model calls made during the build. Scoring reuses the saved build; this amount describes the original inference spend.

  • Billing recovered in a subsequent one-time historical lookup on 2026-10-18. All original generation records were found; the original saved summary remains archived.

Token usage

Tokens: 2.1M in · 29.9k out · 2M cached (exact, OpenRouter records)

2,118,841 tokens over 49 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: 2,895 (not added to the total).

  • openai/gpt-5.6-terra-20260709

    In 2.1M · Out 29.9k · Cached 2M · Reasoning 2.9k · 48 calls

  • google/gemini-2.5-flash

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

Tier breakdown

A · structure & runtime1.00
B · behaviour0.94
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 × 0.6568 core + 0.12 × 0.71 gate × 0.49 excellence) × 0.9429 critical = 0.5837

Critical defects compound a multiplier on the whole score (pre-severity 0.6191):

j_workflow_journey 0.86 → ×0.94

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 (10 of 16 met here), then pays out at the excellence tier's own measured mean. Core 0.5780 + excellence 0.0411.

j_first_use 1.00j_workflow_journey 0.86j_error_state 0.00j_empty_state 1.00console_clean 7.00v_responsive_375 0.00v_dates_readable 1.00t_scene_binding 0.43x_conservation_residual 1.00r_no_row_loss 1.00p_drag_frames 1.00p_idle_flatness 1.00p_stream_apply 0.00p_under_stream 1.00p_api_latency 1.00p_sync_wall 1.00

Earned score 0.584 · Admission ceiling 0.599 · Final score 0.578

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

Visible: not metMatching: not metGood: not metVisual excellence: not metBackend excellence: not met

Visible data-backed 3D: s_visible_surface (maximum 0.599)

Tower structure, currency mapping and scene truth: s_visible_surface, s_tower_geometry, s_currency_collar, t_scene_binding, t_height_pixels, t_vs7dbg_truth (maximum 0.599)

3D interaction and overview legibility: t_pick_buffer, t_pick_real_pass, t_click_semantics, t_camera_math, t_coast_identity, t_coast_reality, t_labels_culling, t_brush_link, t_stream_diff, q_overview_legibility, q_inspector_framing (maximum 0.699)

Event animation and backend recovery: m_committed_event_replay, r_b6_outbox_atomic (maximum 0.869)

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
gemini197251089.769.4
gpt482,087,94729,91715434.41390.4
fleet492,088,91929,92215147.9545.5

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.

Graded browser recording re-encoded to 946x592 at 25 fps to fit 4 MiB, same 461.9 s; graded original sha256 cc55f3dad3d15571e838667ad7123e550754bf3a505f117158854e47f3acc65b

Screenshots

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

1Initial app view
2Error state
3Payment workflow
4First captured render
5Latest captured render

Run details

Model
~openai/gpt-terra-latest
Engine events
0
Repair rounds
0
Started
Oct 6, 2026, 05:39 PM
Finished
Oct 6, 2026, 06:06 PM

How the benchmark is scored