← Forge leaderboard

Forge 2.0 · Cloud baseline

MiniMax M3.1 Flash

minimax/minimax-m3.1-flash:free

Median score
0.3750
Observed range
0.2134–0.5366
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

MiniMax M3.1 Flash (free), single model via OpenRouter

0.2134
Model build
43m 36s
Started
Open Build 1 checks and evidence →

MiniMax M3.1 Flash (free), single model via OpenRouter

0.5366
Model build
38m 4s
Started
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 currency0.90001.0000
T · Event pipeline0.71410.9196
R · Reconcile0.96660.8735
S · Storage0.75001.0000
B · Resolvers and permissions0.50000.9167
U · UI function0.06360.8544
V · Visual0.80001.0000
A · Rovo0.50000.9000
E · Excellence0.53510.8073
R1 · Migration1.00001.0000
R2 · Dosing0.63200.7500
R3 · Time limits1.00001.0000
R4 · Changing world0.56770.9049
R5 · Admin panel1.00001.0000
R6 · CI web trigger1.00001.0000
R7 · Custom field0.39690.6957
R8 · Forge LLM1.00001.0000
R9 · Boot budget0.66671.0000
R10 · Native JQL0.65740.9352
Comparison receipts
Task fingerprint
ef9776e6b12a87482319f25954a9d4969ed78b28d3b9ec7398933bb84b0da292
Captured comparison cohort
324358a3d769b853e1d155d034aa5e3053dd03f3d8a9afdef9202fd98a995ed1

How Forge 2.0 is scored