Best Model Under a Fixed Budget
Best when price is a hard or soft constraint. Soft-weights cost heavily while still requiring a floor of execution, reasoning, reliability, and tempo so the “cheapest” model is not automatically the winner. Users should refine budget in Quest inputs; engine may apply price caps as hard filters.
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.
Leading option (no decisive winner)
Leads this Quest among scored Builds — gap is modest. Strongest blend on Low cost preference + STR. Gemini 3.1 Pro for deep research, long-context synthesis, and multimodal work when judgment and modalities matter as much as pure SWE points.
Struggle · CON · Reliability is a relative soft spot (42 peer public)
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.
Best weighted Fit among scored Builds (gap is modest — Party the rest).
Peer INT 72 — escalate hard reasoning or research here.
Cheapest list stack among remaining candidates ($0.435/$0.87) for volume or drafts.
What we weight
Relative importance of each input in the Fit formula.
- Max input price ≤ $3/MTok
- Always show price and speed implications next to the recommendation.
- If all frontier builds are filtered out, say so and offer a paid unlock path.
Contribution breakdown
Peer-public input × Quest weight. Bars show weight mass; numbers show the score fed into Fit.
All scored candidates
Leads this Quest among scored Builds — gap is modest. Strongest blend on Low cost preference + STR. Gemini 3.1 Pro for deep research, long-context synthesis, and multimodal work when judgment and modalities matter as much as pure SWE points.
Struggle · CON · Reliability is a relative soft spot (42 peer public)
0.5 fit points behind Gemini 3.1 Pro · API · High thinking. Still solid where Low cost preference / STR matter. You want near-frontier coding and agentic work with strong price and speed.
Struggle · EU-only deployments until regional GA
15.0 fit points behind Gemini 3.1 Pro · API · High thinking. Still solid where Low cost preference / STR matter. You want open-frontier capability at roughly an order of magnitude below Sol/Opus list prices.
Struggle · CON · Reliability is a relative soft spot (40 peer public)
16.0 fit points behind Gemini 3.1 Pro · API · High thinking. Still solid where Low cost preference / STR 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.
Struggle · STR · Execution is a relative soft spot (40 peer public)
Capability snapshot
Peer public ranks feed Fit; raw aggregates stay absolute evidence fusion. Full sheet: Codex →
What matters most
- Capability retained after price filter
- Transparent $/quality tradeoffs
- When stepping up a tier is worth it
Common failure modes
- Recommending free/local without capability floor
- Ignoring output-token cost on verbose models
- Hiding that “good enough” may still need a flagship for hard tasks