Cloud baseline
Ling 3.0 Flash — 0.0387 on Forge 1.0
inclusionai/ling-3.0-flash · scorer forge-1.0
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
- 0.0387
- Benchmark
- Forge 1.0
- Model build
- 14m 6s
Recorded inference cost
$0.10
From the saved OpenRouter generation billing summary (151 recorded requests). Whether auxiliary model calls were included was not retained. Scoring reuses the saved build; this amount describes the original inference spend.
- Billing recovered 2026-10-18 from all 151 of this build's own generation ids with OpenRouter's generation records (151 billed, native token reconciliation passed). The earlier saved summary ($0.093507189, incomplete) was replaced; the benchmark score and run are unchanged.
Token usage
Tokens: 21.5M in · 103k out · 21.2M cached (exact, OpenRouter records)
21,581,975 tokens over 151 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: 49,519 (not added to the total).
inclusionai/ling-3.0-flash-20260723
In 21.5M · Out 103k · Cached 21.2M · Reasoning 49.5k · 151 calls
Tier breakdown
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 × 0.0733 core + 0.12 × 0.15 gate × 0.00 excellence) × 0.6000 critical = 0.0387
Critical defects compound a multiplier on the whole score (pre-severity 0.0645):
t_no_double_count: no additional penalty (vacuous:precondition: >= 1 ledger row); wrong numbers — a change counted twice.
r_backfill_complete: no additional penalty (root:l_bundles_load); data loss — changes silently missing.
b_no_permission_leak: no additional penalty (root:l_bundles_load); data leak — hidden issues shown to a person.
b_comment_exactly_once: no additional penalty (root:l_bundles_load); duplicate side effect on a customer's Jira.
u_widget_loads: no additional penalty (root:l_bundles_load); dead primary flow — no data on the dashboard.
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 (2 of 18 met here), then pays out at the excellence tier's own measured mean. Core 0.0645 + excellence 0.0000.
Earned score 0.039 · Cap 0.499 · Final score 0.039
The final score is the lower of the earned score and the cap. Meeting a cap's conditions adds no points.
- deployable: maximum 0.499
l_bundles_load - working ledger: maximum 0.699
u_widget_loadst_event_rowsr_backfill_completes_storage_scopes_entity_index_used - current platform, complete surfaces: maximum 0.799
k_dashboard_widgetk_widget_edit_bridgeu_widget_edit_configu_ledger_tablea_action_resultv_theme_tokensv_dark_mode - production robustness: maximum 0.799
t_no_double_countt_out_of_ordert_retry_after_honouredr_heal_droppedr_rate_limitr_paginationb_no_permission_leakb_comment_exactly_onceb_realtime_payload_cleanu_llm_explainu_widget_livev_csp_cleanv_console_cleanu_ledger_sorts_index_orderb_hidden_counta_action_permissionsl_scopesk_llm_model_current
Forge's own linter reports no errors (warnings cost points), every manifest function bundles and loads, packages resolve at the kit's pins, the manifest rules the linter misses, and only the scopes the app's calls need.
l deployable
1.00lint: 0 errors, every stage reached
l bundles load
0.000/6 functions bundle, load and export their handler; failing: {'triggerHandler': 'TypeError: forge.define is not a function', 'consumerHandler': 'TypeError: forge.define is not a function', 'scheduledHandler': 'TypeError
l lint warnings
0.00vacuous — precondition unmet: >= 1 function loads
l real packages
1.006/6 bundles resolve @forge/* at the kit pins only
l manifest rules
0.00vacuous — precondition unmet: >= 1 resource and >= 1 function
l scopes
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
Current modules and APIs: dashboards:widget with its edit API, the rovo:skill and rovo:mcp wiring, a Forge LLM model the platform lists as active, no /rest/api/3/search, no @forge/api storage, a nodejs22.x or nodejs24.x runtime, the consumer shape, the declared KVS entity, and deploy readiness: a manifest and permissions real Forge would accept and no code predicted to fail there.
k dashboard widget
0.00dashboards:widget 0/2: {'custom_ui_resource': False, 'edit_resource': False}
k widget edit bridge
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
k rovo skill
1.00rovo:skill 7/7:
k current apis
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
k consumer shape
0.6667consumer shape 2/3
k entity declared
0.00required app surface absent: app.storage.entities
k rovo mcp
1.00rovo:mcp 4/4:
k llm model current
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
k manifest semantics
0.00vacuous — precondition unmet: >= 1 function and >= 1 product call observed
k runtime risks
0.00vacuous — precondition unmet: >= 1 function and >= 1 product call observed
Issue updates flow trigger to queue to consumer: one ledger row per change under duplicate, reordered and dropped deliveries, multi-sprint changelog values, re-estimates followed, Retry-After honoured, no user context in background work.
t trigger handoff
0.00vacuous — precondition unmet: a trigger exists and >= 1 push observed
t event rows
0.00event rows: 0/27 exact (precision 0.00, recall 0.00)
t no double count
0.00vacuous — precondition unmet: >= 1 ledger row
t out of order
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
t multi sprint parse
0.000/27 multi-id Sprint changes recorded exactly
t reestimate followed
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
t retry after honoured
0.00vacuous — precondition unmet: the consumer-path fault fired
t no user in async
0.00vacuous — precondition unmet: >= 1 background Jira call
The first scheduled run backfills every change since each active sprint started, removals included; later runs heal what the event stream missed, page through results in each endpoint's own style, wait out rate limits and finish inside the module timeout.
r backfill complete
0.000/52 historical changes recorded exactly after the first scheduled run
r removals found
0.000/7 removed-to-backlog changes found
r heal dropped
0.000/4 dropped changes healed exactly once; 0 other row(s) added
r pagination
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
r rate limit
0.00vacuous — precondition unmet: the reconcile fault fired
r as app
0.00vacuous — precondition unmet: >= 1 scheduled-run Jira read
r completes in timeout
0.00vacuous — precondition unmet: a scheduled trigger made >= 1 Jira call
r idempotent rerun
0.00vacuous — precondition unmet: >= 1 ledger row
Forge KVS with the storage scope, ledger reads through the declared entity index in change-time order, no KVS limit errors.
s storage scope
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
s entity index used
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
s index order
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
s limits
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
Every invoked resolver exists and answers structured errors, nobody sees changes to issues they cannot browse (not on screen, not in an LLM prompt, not in a Realtime payload), the hidden-change count is right, and each click posts exactly one ADF comment as the viewer.
b invoke contract
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
b no permission leak
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
b hidden count
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
b comment adf as user
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
b comment exactly once
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
b realtime payload clean
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
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
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
u widget numbers
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
u widget chart
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
u widget edit config
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
u ledger table
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
u ledger sort
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
u issue router
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
u comment flow
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
u modal close
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
u not started
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
u widget live
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
u llm explain
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
Atlassian design tokens with 4.5:1 contrast in light and dark, a painted surface, no Content Security Policy violations or console errors, and the widget readable at 380 px wide.
v theme tokens
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
v dark mode
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
v csp clean
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
v console clean
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
v widget sizes
0.00the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
The get-sprint-scope action returns exact numbers and the visible changes for the invoking person, returns errors instead of throwing, and the skill's SKILL.md tells the agent how to use it.
a action result
0.000/3 active sprints answered exactly
a action errors
0.000/2 bad sprintId inputs return {error} without throwing
a action permissions
0.000/6 per-person answers list exactly what that person may browse
a skill instructions
1.00SKILL.md body 5/5: result fields named ['sprintName', 'committed', 'added', 'removed', 'creepPercent', 'hiddenChanges', 'changes']
Few Jira requests in the backfill and per event, few round trips before each surface paints, and a scheduled run with nothing new writes nothing — paid only in proportion to the excellence gate.
e reconcile economy
0.00mean over 3 scoring sites: backfill incomplete — economy is not credited on unfinished work
e event economy
0.00mean over 3 scoring sites: event rows inexact — economy is not credited on unfinished work
e ui round trips
0.00mean over 3 scoring sites: the app's manifest names resource 'widget' in a module but declares no such resource under `resources` (declared: none), so the surface cannot be opened
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.
Drag the timeline to seek. Keyboard: arrow keys move 5 seconds; Home and End jump to the start and end.
SHA-256: 5bd964cd3a9d15c4da884117c661e93433546cfd555d290da98c8a22c62c9b24
Run details
- Model
- inclusionai/ling-3.0-flash
- Engine events
- 0
- Repair rounds
- 0
- Started
- Oct 6, 2026, 03:59 AM
- Finished
- Oct 6, 2026, 04:15 AM
- Re-scored
- Oct 6, 2026, 05:41 AM (same build, corrected scorer)