Cloud baseline

Qwen4 Max — 0.7365 on Gauntlet 7.2

qwen/qwen4-max · scorer sb-7.2

Qwen4 Max, single model via OpenRouterqwen/qwen4-max · single agentNov 16, 2026
Overall
0.7365
Excellent
no
Benchmark
Gauntlet 7.2
Model build
72m 9s
Prompt tok
10.1M
Gen tok
191.8k

Recorded inference cost

$2.04

From the saved OpenRouter generation billing summary (75 recorded requests). Whether auxiliary model calls were included was not retained. Scoring reuses the saved build; this amount describes the original inference spend.

Token usage

Tokens: 10.1M in · 192k out · 9.8M cached (exact, OpenRouter records)

10,305,137 tokens over 75 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: 79,539 (not added to the total).

  • qwen/qwen4-max

    In 10.1M · Out 192k · Cached 9.8M · Reasoning 79.5k · 74 calls

  • google/gemini-2.5-flash

    In 974 · Out 5 · Cached 0 · Reasoning 0 · 1 call

Tier breakdown

A · structure & runtime1.00
B · behaviour1.00
C · vendor contract0.95
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 × 0.9787 core + 0.12 × 0.94 gate × 0.80 excellence) × 1.0000 critical = 0.9513

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 0.8613 + excellence 0.0900.

j_first_use 1.00j_workflow_journey 1.00j_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 0.00p_under_stream 1.00p_api_latency 1.00p_sync_wall 1.00

Earned score 0.951 · Admission ceiling 0.739 · Final score 0.737

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

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

3D interaction and overview legibility: t_brush_link, t_stream_diff, q_overview_legibility (maximum 0.739)

Event animation and backend recovery: an earlier admission band is incomplete (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
gemini197452690.6104.2
qwen47410,112,342191,81626253.551.1
fleet7510,113,316191,82125814.251.4

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
qwen/qwen4-max
Engine events
0
Repair rounds
0
Started
Nov 16, 2026, 10:36 AM
Finished
Nov 16, 2026, 11:55 AM
Call budget
With wrap-up nudge, version 2: as the call budget ran low, the agent harness told the model to start no new work and finish

How the benchmark is scored