Benchmarks
More
OverviewBenchmaxxingCompareChartsCost vs CapabilityProviders per ModelProvider explorerGatewaysEU & SovereignJev-class modelsImage JevBenchAbout
JevBench by Benchmark Heaven · v1.4.2.2 · individual system

classifier.dev (fast tier)

Service built on Jev · by mrmps (@michael_chomsky) · API endpoint saw sealed item text

JevBench v1.4.2.2 score

70.8

Honorable mention, not ranked — runs on Jev (TypeSafe) — listed, not ranked.

Shown, not ranked. The marked tick is Jev 1.13.0 (63.3).

Published axes

intelligence
51.6
calibration
72.4
speed
87.6
cost
84.3

Against Jev 1.13.0

Four radars compare this fixed pair across the score axes, accuracy per tier, and accuracy by family on the hard tier and sealed set. Further out is better on every spoke.

  • A: classifier.dev — Service built on Jev · Score 70.8 (honorable mention, not ranked)
  • B: Jev 1.13.0 — Jev (TypeSafe, closed) · Score 63.3 (#4)

The four score axes

Radar: the four score axes, two systemsThe four score axes, classifier.dev vs Jev 1.13.0. Intelligence: 51.6 vs 53.1; Calibration: 72.4 vs 76.3; Speed: 87.6 vs 83.3; Cost: 84.3 vs 52.0.50100Intelligence51.6 · 53.1Calibration72.4 · 76.3Speed87.6 · 83.3Cost84.3 · 52.0
0–100, the values in the table. A label-only system has no calibration (counted as 0).

Accuracy per tier, incl. sealed

Radar: accuracy per tier, incl. sealed, two systemsAccuracy per tier, incl. sealed, classifier.dev vs Jev 1.13.0. Easy: 100% vs 100%; Standard: 99% vs 99%; Judge: 97% vs 95%; Hard: 70% vs 74%; Sealed: 34% vs 37%.50100Easy100% · 100%Standard99% · 99%Judge97% · 95%Hard70% · 74%Sealed34% · 37%
Share correct per tier; Sealed = the 308 private decisions, aggregate only.

Current question set by family (hard + sealed)

Radar: current question set by family (hard + sealed), two systemsCurrent question set by family (hard + sealed), classifier.dev vs Jev 1.13.0. Ambiguous / abstain: 43% vs 43%; Judge: 55% vs 54%; Long policy: 35% vs 44%; Multi-hop: 58% vs 64%; Probability: 58% vs 63%; Temporal / numeric: 28% vs 28%; Trade-off: 47% vs 55%; Routing: 100% vs 100%; Trap / adversarial: 88% vs 83%; Paraphrase: 57% vs 64%; Safety judge: 38% vs 38%.50100Ambiguous /abstain43% · 43%Judge55% · 54%Long policy35% · 44%Multi-hop58% · 64%Probability58% · 63%Temporal /numeric28% · 28%Trade-off47% · 55%Routing100% · 100%Trap /adversarial88% · 83%Paraphrase57% · 64%Safety judge38% · 38%
Share correct per family across the 220 hard-tier decisions (public and held out) and the 308 sealed decisions of v1.4, pooled; Routing is hard-tier only, Paraphrase and Safety judge sealed only.

Sealed set by family

Radar: sealed set by family, two systemsSealed set by family, classifier.dev vs Jev 1.13.0. Ambiguous / abstain: 30% vs 30%; Judge: 37% vs 34%; Long policy: 18% vs 28%; Multi-hop: 37% vs 45%; Paraphrase: 57% vs 64%; Probability: 50% vs 50%; Safety judge: 38% vs 38%; Temporal / numeric: 30% vs 29%; Trade-off: 27% vs 38%; Trap / adversarial: 58% vs 42%.50100Ambiguous /abstain30% · 30%Judge37% · 34%Long policy18% · 28%Multi-hop37% · 45%Paraphrase57% · 64%Probability50% · 50%Safety judge38% · 38%Temporal /numeric30% · 29%Trade-off27% · 38%Trap /adversarial58% · 42%
Share correct within each sealed family — system-level aggregates; the items stay private.

Availability and evidence

Openness
Marked closed in the published row
License note
MIT (code); hosted service
Cost evidence
estimated; the board’s row disclosure contains the published basis.
Endpoint condition
production API (classifier.dev, fast tier)
Note on this row
Its own benchmark page says the fast tier is Jev. Free for us; the price is its published Pro plan ($20/month for 200,000 fast classifications a day) at full use, $0.0033 per 1,000 decisions.
Published source
https://classifier.dev

From the public v1.4.2.2 aggregate. Scores and ranks can change when a new release is published.

Read the full board and published method. The overall score is a composite, not raw accuracy.