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

JevOne

Jev rebuild · by Juspay

JevBench v1.4.2.2 score

25.5

Rank #52 of 91 ranked systems.

37.8 points behind Jev 1.13.0's 63.3.

Where it sits among the 91 ranked systems. The marked tick is Jev 1.13.0 (63.3).

Published axes

intelligence
47.6
calibration
77.6
speed
88.5
cost
35.9

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: JevOne — Jev rebuild · Score 25.5 (#52)
  • 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, JevOne vs Jev 1.13.0. Intelligence: 47.6 vs 53.1; Calibration: 77.6 vs 76.3; Speed: 88.5 vs 83.3; Cost: 35.9 vs 52.0.50100Intelligence47.6 · 53.1Calibration77.6 · 76.3Speed88.5 · 83.3Cost35.9 · 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, JevOne vs Jev 1.13.0. Easy: 100% vs 100%; Standard: 97% vs 99%; Judge: 92% vs 95%; Hard: 75% vs 74%; Sealed: 34% vs 37%.50100Easy100% · 100%Standard97% · 99%Judge92% · 95%Hard75% · 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), JevOne vs Jev 1.13.0. Ambiguous / abstain: 41% vs 43%; Judge: 58% vs 54%; Long policy: 38% vs 44%; Multi-hop: 52% vs 64%; Probability: 52% vs 63%; Temporal / numeric: 43% vs 28%; Trade-off: 50% vs 55%; Routing: 100% vs 100%; Trap / adversarial: 90% vs 83%; Paraphrase: 29% vs 64%; Safety judge: 38% vs 38%.50100Ambiguous /abstain41% · 43%Judge58% · 54%Long policy38% · 44%Multi-hop52% · 64%Probability52% · 63%Temporal /numeric43% · 28%Trade-off50% · 55%Routing100% · 100%Trap /adversarial90% · 83%Paraphrase29% · 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, JevOne vs Jev 1.13.0. Ambiguous / abstain: 32% vs 30%; Judge: 37% vs 34%; Long policy: 18% vs 28%; Multi-hop: 29% vs 45%; Paraphrase: 29% vs 64%; Probability: 32% vs 50%; Safety judge: 38% vs 38%; Temporal / numeric: 39% vs 29%; Trade-off: 38% vs 38%; Trap / adversarial: 67% vs 42%.50100Ambiguous /abstain32% · 30%Judge37% · 34%Long policy18% · 28%Multi-hop29% · 45%Paraphrase29% · 64%Probability32% · 50%Safety judge38% · 38%Temporal /numeric39% · 29%Trade-off38% · 38%Trap /adversarial67% · 42%
Share correct within each sealed family — system-level aggregates; the items stay private.

Availability and evidence

Openness
Code and weights marked open in the published row
License note
Component-specific JevOne/Qwen/SGLang terms recorded in RESULT.md
Cost evidence
estimated; the board’s row disclosure contains the published basis.
Endpoint condition
our GPU (lium.io RTX PRO 6000 Blackwell 96 GB), local loopback HTTP, TP1; serial; independently validated one-card condition
Note on this row
Scan vs 231 public tasks: 0 matches. Training corpus/provenance not disclosed — overlap unknown.
Published source
https://huggingface.co/juspay/jev-one

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.