Cloud baseline

Aion 3.5 — 0.0464 on Gauntlet 7.2

aion-labs/aion-3.5 · scorer sb-7.2

Aion 3.5, single model via OpenRouteraion-labs/aion-3.5 · single agentOct 7, 2026
Overall
0.0464
Excellent
no
Benchmark
Gauntlet 7.2
Model build
33m 57s
Prompt tok
1.1M
Gen tok
105.5k

Recorded inference cost

At least $1.59

From the saved OpenRouter generation billing summary (41 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: 1.2M in · 112k out · 1.1M cached (exact, OpenRouter records)

1,278,908 tokens over 41 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: 97,579 (not added to the total).

  • aion-labs/aion-3.5-20260923

    In 1.2M · Out 112k · Cached 1.1M · Reasoning 97.6k · 40 calls

  • google/gemini-2.5-flash

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

Tier breakdown

A · structure & runtime0.98
B · behaviour0.87
C · vendor contract0.79
D · finesse0.70

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 × 0.4041 core + 0.12 × 0.31 gate × 0.06 excellence) × 0.1296 critical = 0.0464

Critical defects compound a multiplier on the whole score (pre-severity 0.3577):

b_money_rendered 0.00 → ×0.60j_loads_data 0.00 → ×0.60j_workflow_journey 0.00 → ×0.60x_no_lost_write 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 (5 of 16 met here), then pays out at the excellence tier's own measured mean. Core 0.3556 + excellence 0.0021.

j_first_use 0.00j_workflow_journey 0.00j_error_state 0.00j_empty_state 1.00console_clean not measuredv_responsive_375 0.00v_dates_readable 0.00t_scene_binding 0.00x_conservation_residual 1.00r_no_row_loss 1.00p_drag_frames 0.00p_idle_flatness 0.00p_stream_apply 0.00p_under_stream 0.00p_api_latency 1.00p_sync_wall 1.00

Earned score 0.046 · Admission ceiling 0.599 · Final score 0.046

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_layout_basis, t_scene_binding, t_height_pixels, t_vs7dbg_truth (maximum 0.599)

3D interaction and overview legibility: t_draw_budget, 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, x_l5_group_atomicity, x_no_lost_write, r_b3_sigkill_resync, r_b7_partition (maximum 0.799)

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
aion391,143,866105,54116696.763.9
gemini197251344.434.2
fleet401,144,838105,54616457.062.8

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 1280x800 at 25 fps to fit 4 MiB, same 416.3 s; graded original sha256 5346145d337e516fe768933572749b7ee282ce7f6bfd0460a86b2151ab15facf

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
aion-labs/aion-3.5
Engine events
0
Repair rounds
0
Started
Oct 7, 2026, 05:11 AM
Finished
Oct 7, 2026, 06:00 AM

How the benchmark is scored