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

Deep Research and Analysis

Best for literature-style research, competitive analysis, technical due diligence, and multi-document synthesis. Weights reasoning, judgment, research synthesis, and large-context work. Speed and low cost are secondary.

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 INT + WIS. Gemini 3.1 Pro for deep research, long-context synthesis, and multimodal work when judgment and modalities matter as much as pure SWE points.

WIS · Judgment 95INT · Reasoning 93Following Complex Instructions 85

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

Fit
85.0
conf B
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
Gemini 3.1 Pro · API · High thinking
Fit 85.0 · $2/$12

Decisive Quest Fit lead — default seat for this job.

Ceiling / hard mode
GPT-5.6 Sol · API · Max effort
Fit 75.3 · $5/$30

Peer STR 95 — escalate hard coding or agentic work here.

Value / volume
DeepSeek V4 Pro · API · Max effort
Fit 62.0 · $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.

INT · Reasoning25%
WIS · Judgment22%
Research Synthesis18%
CHA · Collaboration10%
CON · Reliability8%
Large Context Work7%
Following Complex Instructions5%
Data Analysis5%
Constraints
  • Min context ≥ 128,000 tokens
  • Prefer builds that cite uncertainty; punish confident hallucination in copy.
#1 · Gemini 3.1 Pro · API · High thinking

Contribution breakdown

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

INT · Reasoning93 × 25%w
WIS · Judgment95 × 22%w
Research Synthesis85 × 18%w
CHA · Collaboration79 × 10%w
CON · Reliability42 × 8%w
Large Context Work· missing
Following Complex Instructions85 × 5%w
Data Analysis· missing
Coverage 88% of Quest weight has evidence
Full ranking

All scored candidates

Decisive lead on weighted fit. Strongest blend on INT + WIS. Gemini 3.1 Pro for deep research, long-context synthesis, and multimodal work when judgment and modalities matter as much as pure SWE points.

WIS · Judgment 95INT · Reasoning 93Following Complex Instructions 85

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

Fit
85.0
conf B

9.7 fit points behind Gemini 3.1 Pro · API · High thinking. Still solid where INT / WIS matter. You want OpenAI tooling + max-effort frontier performance on hard multi-step jobs.

CON · Reliability 95CHA · Collaboration 95INT · Reasoning 95

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

Fit
75.3
conf B · −9.7

10.6 fit points behind Gemini 3.1 Pro · API · High thinking. Still solid where INT / WIS matter. The job is hard enough that a wrong answer costs more than Opus tokens.

INT · Reasoning 85Research Synthesis 79CON · Reliability 76

Struggle · CHA · Collaboration is a relative soft spot (40 peer public)

Fit
74.4
conf A · −10.6

10.7 fit points behind Gemini 3.1 Pro · API · High thinking. Still solid where INT / WIS matter. You want near-frontier coding and agentic work with strong price and speed.

CHA · Collaboration 89Following Complex Instructions 78Research Synthesis 75

Struggle · EU-only deployments until regional GA

Fit
74.3
conf B · −10.7

23.0 fit points behind Gemini 3.1 Pro · API · High thinking. Still solid where INT / WIS matter. You want open-frontier capability at roughly an order of magnitude below Sol/Opus list prices.

WIS · Judgment 79Research Synthesis 74INT · Reasoning 46

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

Fit
62.0
conf A · −23.0

29.8 fit points behind Gemini 3.1 Pro · API · High thinking. Still solid where INT / WIS 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.

Data Analysis 83Following Complex Instructions 78CHA · Collaboration 70

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

Fit
55.2
conf A · −29.8
Primary Build

Capability snapshot

Peer publicbars = rank in scored peer set (≈40–95) · raw = absolute fusion under the bar
STRExecution
46.8raw 76.4B39.853.8
DEXTempo
95.0raw 78.0B85100
CONReliability
42.2raw 76.4B35.249.2
INTReasoning
92.8raw 88.1A88.896.8
WISJudgment
95.1raw 81.3A91.199.1
CHACollaboration
78.6raw 85.6A74.682.6

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

What matters most

  • Integrating conflicting sources
  • Calibrated uncertainty and clear caveats
  • Structured deliverables (memos, comparisons, decision briefs)

Common failure modes

  • Confident synthesis without grounding
  • Missing counter-arguments
  • Treating context window size as research quality