MQ
MODELQUEST
choose the right AI for the quest
← Quests
Quest Fitq_large_codebasepeer min-max inputs

Work in a Large Existing Codebase

Best when you need repository comprehension, constraint retention, careful edits, and verification — not the fastest chat reply. Optimised for mature codebases where understanding local patterns matters more than greenfield flair.

SharePost on X
How to read this

Fit score ≠ absolute IQ

  • Fit score is a weighted blend of this Quest’s attribute/skill weights (and optional cost/tempo soft prefs). Higher = better match for this job among scored Builds.
  • Attribute inputs are peer-public scores (roughly 40–95 within the current peer set). A low STR here can still be a strong absolute model — it just ranks lower among current scored peers on that axis.
  • Decisive means the leader is ≥4 fit points ahead of #2. Smaller gaps → pick on price, Party stack, or taste.

Peer set today: 6 scored Builds. Adding another re-ranks peers — re-run the engine after new evidence.

Recommendation

Best fit

Decisive lead on weighted fit. Strongest blend on STR + CON. OpenAI flagship Build for autonomous coding and professional workflows when ecosystem tools and max reasoning justify $5/$30.

CON · Reliability 95STR · Execution 95INT · Reasoning 95

Struggle · WIS · Judgment is a relative soft spot (40 peer public)

Fit
88.1
conf A
Party

Suggested multi-model stack

Most jobs want a Party — not one model forever. Primary handles the Quest; ceiling covers hard escalations; value handles volume and drafts.

Primary
GPT-5.6 Sol · API · Max effort
Fit 88.1 · $5/$30

Decisive Quest Fit lead — default seat for this job.

Ceiling / hard mode
Claude Opus 4.8 · API · High effort (default)
Fit 79.4 · $5/$25

Peer INT 85 — escalate hard reasoning or research here.

Value / volume
DeepSeek V4 Pro · API · Max effort
Fit 53.2 · $0.435/$0.87

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

This Quest

What we weight

Relative importance of each input in the Fit formula.

STR · Execution25%
CON · Reliability25%
INT · Reasoning20%
WIS · Judgment10%
Existing Codebase Work10%
Debugging5%
Refactoring3%
Large Context Work2%
Constraints
  • Min context ≥ 64,000 tokens
  • Prefer builds with strong verification habits over pure speed.
#1 · GPT-5.6 Sol · API · Max effort

Contribution breakdown

Peer-public input × Quest weight. Bars show weight mass; numbers show the score fed into Fit.

STR · Execution95 × 25%w
CON · Reliability95 × 25%w
INT · Reasoning95 × 20%w
WIS · Judgment40 × 10%w
Existing Codebase Work87 × 10%w
Debugging89 × 5%w
Refactoring90 × 3%w
Large Context Work· missing
Coverage 98% of Quest weight has evidence
Full ranking

All scored candidates

Decisive lead on weighted fit. Strongest blend on STR + CON. OpenAI flagship Build for autonomous coding and professional workflows when ecosystem tools and max reasoning justify $5/$30.

CON · Reliability 95STR · Execution 95INT · Reasoning 95

Struggle · WIS · Judgment is a relative soft spot (40 peer public)

Fit
88.1
conf A

8.7 fit points behind GPT-5.6 Sol · API · Max effort. Still solid where STR / CON matter. The job is hard enough that a wrong answer costs more than Opus tokens.

INT · Reasoning 85Debugging 84Existing Codebase Work 82

Struggle · Everyday chat and low-stakes drafts (use Sonnet/Flash)

Fit
79.4
conf A · −8.7

16.9 fit points behind GPT-5.6 Sol · API · Max effort. Still solid where STR / CON matter. You want near-frontier coding and agentic work with strong price and speed.

Debugging 82Existing Codebase Work 81WIS · Judgment 72

Struggle · EU-only deployments until regional GA

Fit
71.2
conf A · −16.9

22.0 fit points behind GPT-5.6 Sol · API · Max effort. Still solid where STR / CON matter. The quest is research, multimodal, or long-context — not pure SWE ceiling at any price.

WIS · Judgment 95INT · Reasoning 93Existing Codebase Work 80

Struggle · CON · Reliability is a relative soft spot (42 peer public)

Fit
66.1
conf B · −22.0

34.9 fit points behind GPT-5.6 Sol · API · Max effort. Still solid where STR / CON matter. You want open-frontier capability at roughly an order of magnitude below Sol/Opus list prices.

WIS · Judgment 79Existing Codebase Work 78Debugging 78

Struggle · CON · Reliability is a relative soft spot (40 peer public)

Fit
53.2
conf A · −34.9

40.8 fit points behind GPT-5.6 Sol · API · Max effort. Still solid where STR / CON matter. You want one primary Build for coding and writing that stays pleasant under human supervision, holds constraints, and rarely needs the top-tier price.

Debugging 72Existing Codebase Work 71WIS · Judgment 53

Struggle · STR · Execution is a relative soft spot (40 peer public)

Fit
47.3
conf A · −40.8
Primary Build

Capability snapshot

Peer publicbars = rank in scored peer set (≈40–95) · raw = absolute fusion under the bar
STRExecution
94.9raw 87.9A90.998.9
DEXTempo
58.3raw 58.0B48.368.3
CONReliability
95.2raw 87.5A91.299.2
INTReasoning
94.9raw 88.5A90.998.9
WISJudgment
39.9raw 55.8A35.943.9
CHACollaboration
95.0raw 91.0B85100

Peer public ranks feed Fit; raw aggregates stay absolute evidence fusion. Full sheet: Codex →

What matters most

  • Constraint retention across long sessions
  • Careful edits in unfamiliar modules
  • Tests and verification before claiming done

Common failure modes

  • Overengineering simple fixes
  • Context drift on multi-hour tasks
  • Premature victory without running checks