Cloud baseline
GLM 5.3 FlashX — 0.4939 on Forge 1.0
z-ai/glm-5.3-flashx · 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
- 0.4939
- Benchmark
- Forge 1.0
- Model build
- 25m 53s
Recorded inference cost
$2.19
From the saved OpenRouter generation billing summary (148 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 148 of this build's own generation ids with OpenRouter's generation records (148 billed, native token reconciliation passed). The earlier saved summary ($1.9790131, incomplete) was replaced; the benchmark score and run are unchanged.
Token usage
Tokens: 21.9M in · 118k out · 21.6M cached (exact, OpenRouter records)
22,018,476 tokens over 148 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: 70,194 (not added to the total).
z-ai/glm-5.3-flashx-20260918
In 21.9M · Out 118k · Cached 21.6M · Reasoning 70.2k · 147 calls
google/gemini-2.5-flash
In 883 · Out 4 · Cached 0 · Reasoning 0 · 1 call
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 × 0.8655 core + 0.12 × 0.93 gate × 0.55 excellence) × 0.6000 critical = 0.4939
Critical defects compound a multiplier on the whole score (pre-severity 0.8232):
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 0.7616 + excellence 0.0615.
Earned score 0.494 · Cap 0.799 · Final score 0.494
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 0.799
u_ledger_tablea_action_result - production robustness: maximum 0.809
b_no_permission_leakb_comment_exactly_onceu_llm_explainu_ledger_sortb_hidden_counta_action_permissionsl_scopes
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
1.005/5 functions bundle, load and export their handler
l lint warnings
1.000 distinct lint warning(s): []
l real packages
1.005/5 bundles resolve @forge/* at the kit pins only
l manifest rules
1.006/6 manifest rules met:
l scopes
0.75scopes: missing [], extra ['read:jira-user']
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
1.00dashboards:widget 2/2: {'custom_ui_resource': True, 'edit_resource': True}
k widget edit bridge
1.002/2 board picks reached the dashboard through the widget edit API (updateConfig/onProductSave)
k rovo skill
1.00rovo:skill 7/7:
k current apis
1.00current APIs 5/5:
k consumer shape
1.00consumer shape 3/3
k entity declared
1.00entities with a sprint-partitioned, ranged index: ['scope-change']
k rovo mcp
1.00rovo:mcp 4/4:
k llm model current
1.005 LLM call(s); model ids list() does not return: []; llm module with claude: True
k manifest semantics
1.00deploy readiness, manifest + permissions: 15 rules checked, none failing here
k runtime risks
1.00deploy readiness, predicted runtime failures: 10 rules checked, none failing here
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
1.0040/40 deliveries handed off correctly
t event rows
1.00event rows: 20/20 exact (precision 1.00, recall 1.00)
t no double count
1.00every change holds at most one ledger row in every phase (duplicated deliveries included)
t out of order
1.00permuted deliveries: 9/9 rows exact, 3/3 sprints with oracle numbers
t multi sprint parse
1.0027/27 multi-id Sprint changes recorded exactly
t reestimate followed
1.002/2 re-estimated sprints show the oracle numbers
t retry after honoured
1.00waited 30.0 virtual s in-invocation
t no user in async
1.00background work is asApp only
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
1.0058/58 historical changes recorded exactly after the first scheduled run
r removals found
1.009/9 removed-to-backlog changes found
r heal dropped
1.004/4 dropped changes healed exactly once; 0 other row(s) added
r pagination
1.00106/106 reads the site served in two or more pages walked to their end, each page once, continuing where the site left off (/rest/agile/1.0/board 3/3, /rest/agile/1.0/board/{id}/sprint 3/3, /rest/api/3/issue/{id}/changel
r rate limit
1.00backfill request 2: waited 2.0 virtual s in-invocation; backfill continuation page: waited 2.0 virtual s in-invocation; heal request 2: waited 2.0 virtual s in-invocation
r as app
1.00163/163 scheduled-run Jira calls asApp
r completes in timeout
1.003/3 scheduled invocations inside the module timeout
r idempotent rerun
1.000 entity write(s) on a no-change run over 82 rows
Forge KVS with the storage scope, ledger reads through the declared entity index in change-time order, no KVS limit errors.
s storage scope
1.00KVS used, no 403 from the KVS proxy
s entity index used
1.0054/54 ledger reads are entity queries on the sprint index
s index order
1.003/3 tables list changes in change-time order
s limits
1.00no KVS limit errors
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
1.0034/34 invokes returned a defined, structured result; a Jira 500 on getSprint's read: handled
b no permission leak
0.00hidden issue data shown to a person: ['sprint-action-749-light-800x600: SEC-340', 'sprint-action-749-light-800x600: SEC-401', 'sprint-action-749-light-800x600: SEC-449', 'sprint-action-749-light-800x600: data-change-id 8
b hidden count
0.1111worst of 3 scoring sites (seed dd0b1b05f0a815e9): 1/9 hidden counts equal the oracle
b comment adf as user
0.6667worst of 3 scoring sites (seed 133ce75a81764f1a): 4/6 comments are ADF as the viewer naming key, sprint and creep; ['SEC-449 status 404 via user', 'SEC-449 status 404 via user']
b comment exactly once
0.00worst of 3 scoring sites (seed 133ce75a81764f1a): not exactly once: ['post@749: 0 comment(s), 0 success flag(s)', 'doubleClick@749: 0 comment(s), 0 success flag(s)']
b realtime payload clean
1.0020/20 realtime payloads hold sprint ids only
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
1.004/4 configured widget views render a sprint with its numbers
u widget numbers
1.00widget numbers: 4.00/4 views exact (sprints by startDate, four §1 numbers each)
u widget chart
1.004/4 charts on one linear scale within 1px
u widget edit config
1.00edit/config 6/6:
u ledger table
0.1445worst of 3 scoring sites (seed dd0b1b05f0a815e9): ledger tables: 0.43/3 exact (rows, cells, default order)
u ledger sort
0.00worst of 3 scoring sites (seed dd0b1b05f0a815e9): 0/6 at-toggle states ordered with aria-sort
u issue router
1.003/3 issue keys open /browse/<KEY> through the Forge router
u comment flow
0.875worst of 3 scoring sites (seed 133ce75a81764f1a): 7/8 comment-flow steps right (select, success flag, forbidden error flag, modal works)
u modal close
1.003/3 close clicks reached bridge close
u not started
1.00future sprint shows not-started only
u widget live
1.00live widget 4/4: ; 0 idle invoke(s), sprints right after the live changes 2/2
u llm explain
0.913worst of 3 scoring sites (seed 133ce75a81764f1a): explain 21/23 over 5 scripted answers: 0:clean:ids_are_cited_visible_ones, 1:digits:ids_are_cited_visible_ones
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
1.0017/17 surfaces themed with --ds-text* at >= 4.5:1
v dark mode
1.0017/17 surfaces paint a --ds-surface* background in their mode
v csp clean
1.000 CSP violation(s), 0 failed asset request(s)
v console clean
1.000 console/page error(s) on nominal scenarios: []
v widget sizes
1.004/4 widget sizes without horizontal overflow, every sprint visible, no number clipped
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
0.00worst of 3 scoring sites (seed dd0b1b05f0a815e9): 0/3 active sprints answered exactly
a action errors
1.002/2 bad sprintId inputs return {error} without throwing
a action permissions
0.1667worst of 3 scoring sites (seed dd0b1b05f0a815e9): 1/6 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
0.25mean over 3 scoring sites: backfill 118 Jira calls / optimum 15 (incl. 2 forced 429 repeat(s)) = 7.87x
e event economy
0.3969mean over 3 scoring sites: 91 Jira calls / optimum 24 (23 delivered relevant change(s) x 1 read + 1 forced 429 repeat) = 3.79x; 1.0 at <= 1.46x
e ui round trips
1.00mean over 3 scoring sites: round trips before first paint: {'widget-view': 0, 'widget-edit': 1, 'sprint-action': 1}
Run notes and corrections
Scorer correction (2026-10-15): 0.2963 → 0.4939 from the same saved build. The original scorer applied a duplicate-comment penalty when an action failed its comment-count or success-flag check, even though no duplicate was recorded. All retained fixtures recorded at most one comment per action. The failed comment-action checks and original admission ceiling remain in the score. No model, benchmark, candidate application or browser probe was rerun. Original inference charges are unchanged. Legacy observation files lacked an embedded original observation hash; this correction uses their retained native build, fixture identities and original functional-grade matches.
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: 4e8d445360b8e1515c058d3b86c95e11589f4273f4640682cc49a599a997e036
Screenshots
Browser screenshots of the built app, taken during grading. Each caption names the view.
Run details
- Model
- z-ai/glm-5.3-flashx
- Engine events
- 0
- Repair rounds
- 0
- Started
- Oct 7, 2026, 06:12 AM
- Finished
- Oct 7, 2026, 06:46 AM
- Re-scored
- Oct 15, 2026, 07:14 AM (same build, corrected scorer)