JevBench, a reproducible benchmark for typed decision models

benchmarkheaven.com · 1 day on the radar

RISING

Where is the demand coming from?

Mixed

Some genuine outside demand, some founder reach. This is the read that decides whether the traction would transfer to you.

Roughly what does it earn?

Not disclosedNo basis to estimate

We do not publish a figure until we have something to base it on. When we do, the method that produced it is shown alongside the range.

Could you build it?

Yes, in about 6 weeks

Nothing patented, no network effect, and no proprietary data set standing in the way.

What it is

JevBench (Benchmark Heaven) aggregates LLM benchmarks, pricing, and capability metrics across 863 models and 237 benchmarks to help developers choose the right model for their workload. The site surfaces cost-per-task trade-offs and regional deployment constraints, positioning itself as a reference layer for AI model evaluation.

The one thing to knowDespite strong domain relevance and technical depth, the product lacks any monetization signal, revenue claims, or founder presence; it reads as a reference utility rather than a commercial vehicle, limiting venture replication appeal.

Proof we found, with sources

HNThe Show HN post reached 56 points on Hacker News.23 Sept 2026 · source

HNThe Show HN post reached 53 points on Hacker News.23 Sept 2026 · source

HNThe Show HN post reached 53 points on Hacker News.22 Sept 2026 · source

HNThe Show HN post reached 45 points on Hacker News.22 Sept 2026 · source

HNThe Show HN post reached 43 points on Hacker News.22 Sept 2026 · source

HNThe Show HN post reached 36 points on Hacker News.22 Sept 2026 · source

HNThe Show HN post reached 32 points on Hacker News.22 Sept 2026 · source

HNThe Show HN post reached 26 points on Hacker News.22 Sept 2026 · source

The scores behind the verdict

Directional reads from public signals, 0 to 100

▸ Show the four scores

TractionWeak15 / 100

How much demand shows up from people outside the founder's own circle.

CopyabilityFair35 / 100

How feasible it is for a competent builder to ship something comparable.

Wedge potentialThin22 / 100

How much room is left for a new entrant: gaps, ignored segments, pricing openings.

MonetizationUnproven8 / 100

How much evidence there is that people actually pay: visible pricing, revenue claims, a paid tier in use.

How it works under the hood

The mechanism, the parts of the stack we can observe, and the piece that is genuinely hard to rebuild rather than merely fiddly…

How it gets customers

The channel that actually brings people in, and whether it transfers.
The loops that compound, and the ones that only work once.
Pricing and packaging, and the seam a new entrant can price into.

The opening we would take

Where the product is weak, and the specific angle a new entrant can launch into, with a bottom-line verdict…

Unlock the full brief

How it works under the hood, how it gets customers, where it is weak, and the opening we would take, with a bottom-line verdict.

One-time payment. Delivered in about a minute. Yours to keep.

Revenue, user and tactic numbers are evidence we found and attributed, with a confidence rating.
They are directional reads, never verified guarantees.