Hosting = where inference runs; company = where the provider or lab is registered.
EU hosting means the route's inference runs inside the EU: an EU region, AWS Bedrock's EU cross-region (geo) profiles, Azure's Europe Data Zone, or a provider whose entire public fleet is documented as EU-hosted, each checked per model against the provider's documentation. Global deployments do not count, and neither does an EU billing region, an EU company or an EU control plane on its own. One disclosed company-policy exception stays in, marked “EU equivalent”.
Data confidentialitywhat the provider may do with your prompts
More settings
Evidence requirements (benchmark evidence, priced provider, measured task tokens) sit above the table they apply to.
“Hide deprecated” removes retired models (every Artificial Analysis configuration retired, on no current DesignArena board) and older retired configurations of current models. Applies to model tables, charts, price views & model offers; benchmark evidence stays unfiltered.
Compare Jev-compatible models by separate measures and their measurement conditions. A historical measurement is not a current rank.
Jev and SubQ Snap: published axes and category radars
Pick any two. Radars for the score axes, capability by subject topic and use cases, chance-corrected competence per request type on the open and sealed sets, and competence per tier on each set. Further out is better on every spoke; the link keeps the pair.
B: SubQ Snap— Closed API (weights not public) · Score 74.4 (ranked, not ranked)
The four score axes
0–100, the values in the table. An axis a system has no published value for is left as a gap (it counts as 0 in the composite).
Capability by subject topic
SubQ Snap: No per-category values are published for this system.
Linear signed scale: −100 at the centre, 0 on the bold middle ring, 100 at the rim.
What the decision is about — math and dates, coding, rules, money, support work, everyday messages, safety. Chance-corrected competence per category (0 = at or below chance; negative averages are reported as 0, 100 = perfect), Jev 1.13.0: S+P+L1+L2+L3; SubQ Snap: open+sealed items pooled; only categories with at least 30 items are spokes, smaller ones are listed below. Hover a category for its definition and item count.What each category means · items per category
Rules, policy & law — applying written rules: company policies, contracts, regulations, eligibility. 1616 items (151 open / 1465 sealed)
Coding & software — code, SQL, repositories, developer tools and IT systems. 382 items (62 open / 320 sealed)
Math & numbers — a calculation decides the answer: arithmetic, word problems, probability, dates, units. 370 items (37 open / 333 sealed)
Support & operations — support tickets, incidents, logistics, scheduling desks and routing work to a team. 160 items (21 open / 139 sealed)
Everyday language — short everyday messages: intents, assistant requests, reading a detail out of a text. 145 items (11 open / 134 sealed)
Safety & security — untrusted or injected instructions, fraud, moderation, access and security triage. 109 items (6 open / 103 sealed)
Use cases (TypeSafe categories)
SubQ Snap: No per-category values are published for this system.
Linear signed scale: −100 at the centre, 0 on the bold middle ring, 100 at the rim.
Linear signed scale: −100 at the centre, 0 on the bold middle ring, 100 at the rim.
The real-world application area of each decision, after the TypeSafe use-case map; an item can count in two. Chance-corrected competence per category (0 = at or below chance; negative averages are reported as 0, 100 = perfect), Jev 1.13.0: S+P+L1+L2+L3; SubQ Snap: open+sealed items pooled; only categories with at least 30 items are spokes, smaller ones are listed below. Hover a category for its definition and item count.A point on the bold 0 ring printed 0.0 is a measured value, not a gap: these published cells clip below-chance results to 0, so 0 means at or below chance. Their score markers cannot fall inside that ring.What each category means · items per category
Model routing — deciding which LLM or model tier should handle a prompt; classifying a request's intent, domain, difficulty or risk to pick a model. 524 items (86 open / 438 sealed)
Legal and compliance — contracts, policies, regulations, eligibility rules, checking documents against written requirements. 515 items (74 open / 441 sealed)
Customer support — classifying tickets and customer intents, urgency, refunds, routing cases to a team, checking support replies. 240 items (37 open / 203 sealed)
Other — none of the above: general reasoning, arithmetic or date puzzles, everyday assistant requests without a business workflow. 174 items (24 open / 150 sealed)
E-commerce marketplaces — product listings, product attributes, orders and deliveries, seller catalog policy. 119 items (9 open / 110 sealed)
Risk assessment — estimating probabilities and severity of risks, incidents, vendor or underwriting risk. 118 items (8 open / 110 sealed)
Financial crime — suspicious transactions, KYC, fraud alerts, entity matching for investigations. 101 items (9 open / 92 sealed)
Feature extraction for predictive modeling — turning natural-language data into probabilistic features or estimates for a downstream prediction. 99 items (5 open / 94 sealed)
Lead generation — matching companies or inbound messages to an ideal customer profile, buyer intent, prioritising and routing sales leads. 95 items (4 open / 91 sealed)
Recruiting — resumes, applications, interview feedback, matching candidates to roles. 94 items (1 open / 93 sealed)
Graphs and knowledge graphs — entity types, relationships between records, contradictions between facts, multi-step lookups across linked facts. 94 items (3 open / 91 sealed)
Moderation and trust and safety — user content moderation: toxicity, harassment, spam, unsafe advice, personal data exposure. 93 items (7 open / 86 sealed)
Semantic code linting — checking code or writing against conventions and guidelines, as in CI review of code. 90 items (3 open / 87 sealed)
Search and retrieval — scoring query-to-candidate relevance, reranking results, selecting useful context for RAG. 90 items (5 open / 85 sealed)
Scientific discovery — screening papers, labelling research passages or survey answers, checking that citations support claims, methodology checks. 90 items (2 open / 88 sealed)
Advertising — ad creatives, campaign copy, brand safety, prohibited claims in ads. 88 items (3 open / 85 sealed)
Gaming — player reports, in-game chat, game support. 86 items (3 open / 83 sealed)
Demand forecasting — purchase intent, product interest, demand and supply signals for forecasting. 83 items (3 open / 80 sealed)
Competence per request type, open / sealed
Linear signed scale: −100 at the centre, 0 on the bold middle ring, 100 at the rim.
Chance-corrected competence for Choice, Noul and Score on the 300 open and 1200 sealed decisions.
Competence per tier — open set
Linear signed scale: −100 at the centre, 0 on the bold middle ring, 100 at the rim.
Per-tier competence, the three request types pooled by their published decision counts.
Competence per tier — sealed set
Linear signed scale: −100 at the centre, 0 on the bold middle ring, 100 at the rim.
Per-tier competence on the sealed decisions, types pooled the same way; item text stays private.
How the categories were made
O1S chance-corrected competence: equal mean across the request types present, clipped to 0–100. Zero means the equal-weight mean across present request types was at or below baseline; negative means are clipped. It does not mean every type scored zero. Choice uses a random-option baseline; Noul uses a fixed 50% accuracy baseline (abstentions count as wrong); Score uses the midpoint-guess error (random-guess fallback when every gold is at the midpoint). Compare models within a category; row pools and supported types can differ.
Categories use ruled subject-topic labels and authoring use-case precedence across the answered pool union, with stable item identities counted once.
Official O1S; recorded failures count where supported; no missing response is imputed; stable identity dedupe parent first.
S-based category cells pool recorded supported responses from S+P and the answered L1/L2/L3 supplements. API overlay category cells keep their separately recorded A4/A5+P union. Headline and per-type/tier scores are unchanged.
TypeSafe list tariff USD 0.042 per 1M input tokens, output free; measured on the v1.6.1 common cost basis (all items except those outside the Jev reference input range) from this run's token usage
Vendor-hosted api.subq.ai /v1/systemone API, model `subq-snap-preview`; latency measured from Sandy (Germany) on the official per-item latency subset without API adjustment. Full S1200+P300 draw of v1.6-regular-20261012 through the unchanged run_api_full_v161.py; the full-set exposure gate logged all 1,200 sealed items to provider `subq` before the first request (CoS deputy #18975; every sealed item of this draw was already retired). Native probabilities on all three question types, no generated tokens. Hosting implementation and deployed weights were not independently inspected. Florian's work order (X, 12 Oct 2026). SubQ retains API inputs indefinitely by default; acceptable only because this draw's items are already retired.
Cost basis (estimated)
Operator's own published standard usage tariff: USD 0.05 per 1M INPUT tokens with no output billing. Two vendor sources, both snapshotted: the pricing section of https://subq.ai/ read on 14 Oct 2026 08:10Z ('In $0.05 per 1M tokens Input / Out Free Output') and the vendor's own launch post 'Introducing SubQ Snap' ('SubQ Snap is priced at $0.05 per million input tokens, with no charge for output tokens'), which also dates the tariff to the product's launch; Subquadratic's Alexander Whedon separately confirmed the figure in writing to Florian on 14 Oct 2026 01:16 Berlin (board #19133). Counted under interpretation I-1 (a manufacturer's standard, non-promotional launch list price counts from day 1 - the reading that already admitted kushal-gemma4-31b-it-autoloops). DISCLOSED: Snap is in a capacity-limited public preview - first come, first served, with a waitlist once capacity is reached - so this is the vendor's stated usage price for a product that is not yet openly bookable by everyone; CoS deputy decision #19174 rules explicitly that I-1 covers this tariff during that public preview, on the condition that the capacity limit and waitlist are stated here, as they are. The same pricing section offers 'Free 100M tokens for the first 10,000 users': that is a promotional trial credit and is deliberately NOT used - a free tier is priced at the published paid tariff, never as cost 0. The tariff is multiplied by this row's OWN measured input tokens (1,943,705 over 1,500 answered rows, mean 1,296) and divided by the 1,485 items of the common cost basis the scorer uses. The output term is zero twice over: the tariff bills no output, and the vendor's own usage meter reports 0 output tokens on all 1,500 rows. Gate chain: CoS deputy #18975 made the cost axis conditional on a separate frozen-pricing change passing re-freeze, unchanged-row proof and independent review; the chief of staff asked for it in #19133; the scoped change adds this one key to pricing_v15.LAUNCH_LIST_PRICE_API and nothing else (r113/pricing/CANDIDATE.diff; unchanged-row proof r113/receipts/PRICING-EQUIV-R113.json and two rounds of independent review, r113/review-pricing/REVIEW.json (REVISE) and r113/review-pricing-r2/REVIEW.json (PASS); the findings about this row's text and the builder's gates are applied here, the two about the publication layer are on the build sheet). INSIDE THE OFFICIAL COST CAP on the common basis: USD 0.025716 per 1,000 decisions is 0.398x the official cap USD 0.064595. Over all 1,500 items the row cost USD 0.064790 (1.003x the cap) and was disclosed as ranked over the cap in v1.6.29; that disclosure is superseded. COMMON COST BASIS (v1.6.30): cost per 1,000 decisions is computed on the common 1,485 items of this draw, leaving out the 15 very long items (at least 76,358 input tokens as counted by the rows that answered them). They are the 15 items the Jev reference refused with max_tokens_exceeded, which the other rows that did not answer them refused or failed on; their tokens count for no row, whether the row refused or answered them, and a refused item still counts as a wrong answer for Intelligence. This row: USD 0.025716 per 1,000 decisions (0.398x the official cost cap USD 0.064595), against USD 0.064790 over all 1,500 items (v1.6.29).
Latency adjustment
none (API)
Frequently asked questions
What does JevBench show for Jev and SubQ Snap?
Jev 1.13.0 has Capability 77.1 and is the unranked reference (the open-weights board ranks 139 open-weights systems; hosted API offerings are ranked on the API leaderboard). SubQ Snap (preview, SubQ) has Capability 81.5. API offering, ranked on the API leaderboard in v1.6.39. Historical scores use their original method and are not ranked against the current release.
How does Capability differ from Composite?
Capability is the mean of Intelligence and Calibration; headline ranks require both official cost and median-latency caps. Composite additionally scores Speed and Cost and is secondary.
Can I compare the prices as actual bills?
Jev 1.13.0 (TypeSafe AI): not published, $0.032 per 1,000 decisions. SubQ Snap (preview, SubQ): estimated, $0.026 per 1,000 decisions. Estimates and self-reported vendor prices are not measured charges.
Is SubQ Snap open source?
The published licence note for SubQ Snap (preview, SubQ) is Proprietary hosted API (no weights release). Jev 1.13.0 is listed as proprietary API. Check the linked sources for terms.