Cloud baseline

Qwen3.8 Max Prime — 0.8364 on Gauntlet 7.2

qwen/qwen3.8-max-prime · scorer sb-7.2

Qwen3.8 Max Prime, single model via OpenRouterqwen/qwen3.8-max-prime · single agentOct 6, 2026
Overall
0.8364
Excellent
no
Benchmark
Gauntlet 7.2
Model build
79m 9s
Prompt tok
20.5M
Gen tok
329.3k

Recorded inference cost

$16.68

From the saved OpenRouter generation billing summary (95 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: 20.5M in · 329k out · 19.8M cached (exact, OpenRouter records)

20,825,936 tokens over 95 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: 189,922 (not added to the total).

  • qwen/qwen3.8-max-prime-20260923

    In 20.5M · Out 329k · Cached 19.8M · Reasoning 190k · 94 calls

  • google/gemini-2.5-flash

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

Tier breakdown

A · structure & runtime1.00
B · behaviour1.00
C · vendor contract0.93
D · finesse0.90

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 × 0.9490 core + 0.12 × 0.96 gate × 1.00 excellence) × 1.0000 critical = 0.9499

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 0.8351 + excellence 0.1148.

j_first_use 1.00j_workflow_journey 1.00j_error_state 0.30j_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 0.950 · Admission ceiling 0.839 · Final score 0.836

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

Visible: passedMatching: passedGood: passedVisual excellence: not metBackend excellence: not met

Event animation and backend recovery: m_committed_event_replay, r_b6_outbox_atomic, r_notifier_exactly_once (maximum 0.839)

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
gemini197251396.635.5
qwen3.89420,495,671329,28879143.380.9
fleet9520,496,643329,29379094.680.1

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.

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

Run details

Model
qwen/qwen3.8-max-prime
Engine events
0
Repair rounds
0
Started
Oct 6, 2026, 09:54 PM
Finished
Oct 6, 2026, 11:21 PM

How the benchmark is scored