Cloud baseline

Qwen3.8 Flash — 0.7961 on Forge 1.0

qwen/qwen3.8-flash · scorer forge-1.0

Qwen3.8 Flash, single model via OpenRouterqwen/qwen3.8-flash · single agentOct 5, 2026
Historic benchmarkForge 1.0 · not comparable with Forge 2.0

Forge 1.0 was frozen on 9 October 2026 and accepts no new runs; Forge 2.0 is its successor. The original results contained scorer faults. Corrections made from saved evidence on 15 October are dated on the affected run pages, with both original and corrected scores and the reason for the change. They reuse the original builds and observations; no benchmark or model was rerun, and the original inference charges remain. Uncorrected results retain known limitations: the top five original scores, 0.945 to 0.977, were too close to reliably rank the strongest models; two hourly-job tests missed Jira reads performed by a queue worker; and the old linter accepted an entity index with two range attributes that Forge refuses. Those remaining faults are not silently treated as fixed. Consult each run's correction note when comparing historical results. Forge 2.0 has separate results and a different task.

Overall
0.7961
Benchmark
Forge 1.0
Model build
55m 2s

Recorded inference cost

$0.47

From the saved OpenRouter generation billing summary (149 recorded requests). Includes auxiliary model calls made during the build. Scoring reuses the saved build; this amount describes the original inference spend.

  • Billing recovered 2026-10-18 from all 149 of this build's own generation ids with OpenRouter's generation records (149 billed, native token reconciliation passed). The earlier saved summary ($0.467769206, incomplete) was replaced; the benchmark score and run are unchanged.

Token usage

Tokens: 21M in · 194k out · 20.7M cached (exact, OpenRouter records)

21,152,362 tokens over 149 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: 140,053 (not added to the total).

  • qwen/qwen3.8-flash-20260826

    In 21M · Out 194k · Cached 20.7M · Reasoning 140k · 148 calls

  • google/gemini-2.5-flash

    In 883 · Out 4 · Cached 0 · Reasoning 0 · 1 call

Tier breakdown

L · Lint and bundles1.00
K · Platform currency0.89
T · Event pipeline1.00
R · Reconcile1.00
S · Storage1.00
B · Resolvers and permissions1.00
U · UI function0.803
V · Visual0.9529
A · Rovo1.00
E · Excellence0.8606

Scoring detail

How this score was built

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

Correctness combines the lowest score for each test across the scoring fixtures; economy measurements use their mean. The combined result can therefore be lower than every individual fixture’s final score. Critical defects reduce the weighted result before any score cap applies.

Earned credit before admission

(0.88 × 0.9537 core + 0.12 × 0.94 gate × 0.92 excellence) × 1.0000 critical = 0.9426

The core (88% of the total) is the weighted mean of the nine measured tiers. The last 12% is the excellence slice: it unlocks in proportion to the perfection conditions below (16 of 18 met here), then pays out at the excellence tier's own measured mean. Core 0.8393 + excellence 0.1033.

t_event_rows 1.00r_heal_dropped 1.00u_widget_numbers 1.00u_ledger_table 1.00b_comment_adf_as_user 1.00k_consumer_shape 1.00k_current_apis 1.00k_dashboard_widget 1.00k_entity_declared 1.00k_llm_model_current 0.00k_manifest_semantics 1.00k_rovo_mcp 1.00k_rovo_skill 1.00k_runtime_risks 0.90k_widget_edit_bridge 1.00v_console_clean 1.00v_csp_clean 1.00l_lint_warnings 1.00

Earned score 0.943 · Cap 0.799 · Final score 0.796

The final score is the lower of the earned score and the cap. Meeting a cap's conditions adds no points.

  • current platform, complete surfaces: maximum 0.799v_dark_mode
  • production robustness: maximum 0.839u_llm_explainu_widget_liveu_ledger_sortk_llm_model_current

The dashboard widget's numbers and chart, its board choice saved through the host, live updates through Forge Realtime, the sprint action's ledger table, sorting, issue links, comment flow, the Forge LLM explanation, close and not-started states.

u widget loadsdiagnostic, no weight

1.00

4/4 configured widget views render a sprint with its numbers

u widget numbers

1.00

widget numbers: 4.00/4 views exact (sprints by startDate, four §1 numbers each)

u widget chart

1.00

4/4 charts on one linear scale within 1px

u widget edit config

1.00

edit/config 6/6:

u ledger table

1.00

ledger tables: 3.00/3 exact (rows, cells, default order)

u ledger sort

0.3333

worst of 3 scoring sites (seed 3f1475b5b187cc56): 3/9 at-toggle states ordered with aria-sort (3 after another sort was active)

u issue router

1.00

3/3 issue keys open /browse/<KEY> through the Forge router

u comment flow

0.75

6/8 comment-flow steps right (select, success flag, forbidden error flag, modal works)

u modal close

1.00

3/3 close clicks reached bridge close

u not started

1.00

future sprint shows not-started only

u widget live

0.75

live widget 3/4: shows_new_numbers; 0 idle invoke(s), sprints right after the live changes 1/2

u llm explain

0.00

explain 0/5 over 5 scripted answers: 0:clean:one_llm_call_answered_clean, 1:digits:one_llm_call_answered_digits, 2:refusal:one_llm_call_answered_refusal, 3:malformed:one_llm_call_answered_malformed, 4:error:one_llm_call_

Graded browser recording

Loading duration…

Watch the full graded browser recording at its original speed: the dashboard widget, the sprint action and the not-started sprint, as the scorer drove them on the run's own seed. The test results and screenshots on this page provide the wider evidence. Pause or scrub to inspect a view.

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: dashboard widget (no config, edit + Save, light and dark, 380 and 1180 px, a second instance), sprint action modal (sort, router, select, comment post through the 429 retry, double click, forbidden post, close) and the not-started sprint

Screenshots

Browser screenshots of the built app, taken during grading. Each caption names the view.

1Every captured surface
2Widget edit view
3Widget before configuration
4Sprint not started
5Sprint action · dark

Run details

Model
qwen/qwen3.8-flash
Engine events
0
Repair rounds
0
Started
Oct 5, 2026, 05:05 PM
Finished
Oct 5, 2026, 06:21 PM

How the benchmark is scored