← Forge leaderboard

Forge 2.0 · Cloud baseline

Hy4 flash

tencent/hy4-flash

Median score
0.3089
Observed range
0.1075–0.5103
Independent builds
2

The median summarizes these 2 independent model builds; the range shows the lowest and highest observed scores. These builds share the same task and captured comparison cohort. Each build retains its own score, checks and evidence. The observed range is not a confidence interval.

Individual builds

Hy4 flash, single model via OpenRouter

0.1075
Model build
26m 25s
Started
Call budget
with wrap-up nudge, version 2
Open Build 1 checks and evidence →

Hy4 flash, single model via OpenRouter

0.5103
Model build
27m 1s
Started
Call budget
with wrap-up nudge, version 2
Open Build 2 checks and evidence →

Tier comparison

Each column shows one build's own tier scores. The overall median is calculated from the overall build scores.

TierBuild 1Build 2
L · Lint and bundles1.00001.0000
K · Platform currency1.00000.9750
T · Event pipeline0.50630.9792
R · Reconcile0.73170.9981
S · Storage1.00001.0000
B · Resolvers and permissions0.56480.8611
U · UI function0.22790.7031
V · Visual1.00001.0000
A · Rovo0.50000.5000
E · Excellence0.25550.9494
R1 · Migration0.15961.0000
R2 · Dosing0.48510.9000
R3 · Time limits1.00001.0000
R4 · Changing world0.26190.7636
R5 · Admin panel0.93330.9667
R6 · CI web trigger0.80001.0000
R7 · Custom field0.82800.9198
R8 · Forge LLM0.66671.0000
R9 · Boot budget1.00001.0000
R10 · Native JQL0.38430.6250
Comparison receipts
Task fingerprint
89628fa17078cb49c9f601121bcb738042170646fe385702c8c45ef3fa2e647d
Captured comparison cohort
554e54c4a356d143291cc842e9b7b19e035ccd73b8582f8fe7dc13b39aac4f49

How Forge 2.0 is scored