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

Jev 1.13.0 (TypeSafe AI)

Jev (TypeSafe, closed) · by TypeSafe AI · API endpoint saw sealed item text

JevBench v1.4.2.2 score

63.3

Rank #4 of 91 ranked systems.

4.1 points behind Imajev-4B's 67.4.

Where it sits among the 91 ranked systems. The marked tick is Imajev-4B (67.4).

Published axes

intelligence
53.1
calibration
76.3
speed
83.3
cost
52.0

Against Imajev-4B

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: Jev 1.13.0 — Jev (TypeSafe, closed) · Score 63.3 (#4)
  • B: Imajev-4B — Jev rebuild · Score 67.4 (#1)

The four score axes

Radar: the four score axes, two systemsThe four score axes, Jev 1.13.0 vs Imajev-4B. Intelligence: 53.1 vs 52.2; Calibration: 76.3 vs 80.4; Speed: 83.3 vs 90.6; Cost: 52.0 vs 59.7.50100Intelligence53.1 · 52.2Calibration76.3 · 80.4Speed83.3 · 90.6Cost52.0 · 59.7
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, Jev 1.13.0 vs Imajev-4B. Easy: 100% vs 100%; Standard: 99% vs 99%; Judge: 95% vs 89%; Hard: 74% vs —; Sealed: 37% vs 37%.50100Easy100% · 100%Standard99% · 99%Judge95% · 89%Hard74%Sealed37% · 37%
Share correct per tier; Sealed = the 308 private decisions, aggregate only.

Current question set by family (hard + sealed)

Imajev-4B has no published hard-tier family breakdown; families that need it are left out (—).

Radar: current question set by family (hard + sealed), two systemsCurrent question set by family (hard + sealed), Jev 1.13.0 vs Imajev-4B. Ambiguous / abstain: 43% vs —; Judge: 54% vs —; Long policy: 44% vs —; Multi-hop: 64% vs —; Probability: 63% vs —; Temporal / numeric: 28% vs —; Trade-off: 55% vs —; Routing: 100% vs —; Trap / adversarial: 83% vs —; Paraphrase: 64% vs 50%; Safety judge: 38% vs 44%.50100Ambiguous /abstain43%Judge54%Long policy44%Multi-hop64%Probability63%Temporal /numeric28%Trade-off55%Routing100%Trap /adversarial83%Paraphrase64% · 50%Safety judge38% · 44%
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, Jev 1.13.0 vs Imajev-4B. Ambiguous / abstain: 30% vs 41%; Judge: 34% vs 44%; Long policy: 28% vs 33%; Multi-hop: 45% vs 34%; Paraphrase: 64% vs 50%; Probability: 50% vs 25%; Safety judge: 38% vs 44%; Temporal / numeric: 29% vs 30%; Trade-off: 38% vs 38%; Trap / adversarial: 42% vs 58%.50100Ambiguous /abstain30% · 41%Judge34% · 44%Long policy28% · 33%Multi-hop45% · 34%Paraphrase64% · 50%Probability50% · 25%Safety judge38% · 44%Temporal /numeric29% · 30%Trade-off38% · 38%Trap /adversarial42% · 58%
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
proprietary API
Cost evidence
measured; the board’s row disclosure contains the published basis.
Endpoint condition
production API (api.typesafe.ai)
Published source
https://docs.typesafe.ai

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.