MQ
MODELQUEST
choose the right AI for the quest
← Quests
Quest Forgeinteractive · peer min-max inputs

Forge your own Quest

None of the preset Quests match your job? Dial in the weights and constraints yourself. The ranking recomputes live — no page reload — using the same Fit engine as the curated Quests.

SharePost on X
How to read this

Fit score ≠ absolute IQ

Attribute inputs are peer-public scores (≈40–95 within the current scored set), so a low bar can still be a strong absolute model — it just ranks lower among today's peers on that axis. Weights are relative; only their proportions matter.

Presets

Start from a shape

Weights

What matters for your job

Preferences

Soft tie-breakers

Constraints

Hard filters

Live ranking

Best fit for your weights

CON · Reliability 95CHA · Collaboration 95STR · Execution 95
Fit
82.5
conf B
WIS · Judgment 95DEX · Tempo 95INT · Reasoning 93
Fit
72.8
conf B · −9.7
CHA · Collaboration 89DEX · Tempo 77WIS · Judgment 72
Fit
72.6
conf B · −9.9
INT · Reasoning 85STR · Execution 78CON · Reliability 76
Fit
70.9
conf B · −11.6
WIS · Judgment 79INT · Reasoning 46STR · Execution 45
Fit
49.2
conf B · −33.3
CHA · Collaboration 70DEX · Tempo 62WIS · Judgment 53
Fit
47.9
conf A · −34.6

Fit = weighted blend of peer-public scores (≈40–95). Recomputes live across 6 scored Builds.

Party

Suggested multi-model stack

Primary
GPT-5.6 Sol · API · Max effort
Fit 82.5 · $5/$30

Decisive Quest Fit lead — default seat for this job.

Ceiling / hard mode
Gemini 3.1 Pro · API · High thinking
Fit 72.8 · $2/$12

Peer INT 93 — escalate hard reasoning or research here.

Value / volume
DeepSeek V4 Pro · API · Max effort
Fit 49.2 · $0.435/$0.87

Cheapest list stack among remaining candidates ($0.435/$0.87) for volume or drafts.