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

Hopper

Jev rebuild · by HopitAI

JevBench v1.4.2.2 score

59.4

Rank #7 of 91 ranked systems.

3.9 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
48.0
calibration
79.1
speed
86.8
cost
58.7

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: Hopper — Jev rebuild · Score 59.4 (#7)
  • 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, Hopper vs Jev 1.13.0. Intelligence: 48.0 vs 53.1; Calibration: 79.1 vs 76.3; Speed: 86.8 vs 83.3; Cost: 58.7 vs 52.0.50100Intelligence48.0 · 53.1Calibration79.1 · 76.3Speed86.8 · 83.3Cost58.7 · 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, Hopper vs Jev 1.13.0. Easy: 100% vs 100%; Standard: 97% vs 99%; Judge: 84% vs 95%; Hard: 65% vs 74%; Sealed: 34% vs 37%.50100Easy100% · 100%Standard97% · 99%Judge84% · 95%Hard65% · 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), Hopper vs Jev 1.13.0. Ambiguous / abstain: 45% vs 43%; Judge: 53% vs 54%; Long policy: 40% vs 44%; Multi-hop: 52% vs 64%; Probability: 48% vs 63%; Temporal / numeric: 21% vs 28%; Trade-off: 42% vs 55%; Routing: 100% vs 100%; Trap / adversarial: 85% vs 83%; Paraphrase: 57% vs 64%; Safety judge: 50% vs 38%.50100Ambiguous /abstain45% · 43%Judge53% · 54%Long policy40% · 44%Multi-hop52% · 64%Probability48% · 63%Temporal /numeric21% · 28%Trade-off42% · 55%Routing100% · 100%Trap /adversarial85% · 83%Paraphrase57% · 64%Safety judge50% · 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, Hopper vs Jev 1.13.0. Ambiguous / abstain: 32% vs 30%; Judge: 39% vs 34%; Long policy: 28% vs 28%; Multi-hop: 37% vs 45%; Paraphrase: 57% vs 64%; Probability: 36% vs 50%; Safety judge: 50% vs 38%; Temporal / numeric: 21% vs 29%; Trade-off: 31% vs 38%; Trap / adversarial: 50% vs 42%.50100Ambiguous /abstain32% · 30%Judge39% · 34%Long policy28% · 28%Multi-hop37% · 45%Paraphrase57% · 64%Probability36% · 50%Safety judge50% · 38%Temporal /numeric21% · 29%Trade-off31% · 38%Trap /adversarial50% · 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 terms recorded in RESULT.md; submitted adapter release and Qwen base retain their respective terms
Cost evidence
estimated; the board’s row disclosure contains the published basis.
Endpoint condition
our GPU (lium.io RTX A6000 48 GB), local loopback HTTP; serial
Note on this row
Author discloses heavy public-benchmark-directed development (26 model/prompt configs, 20+ calibration-map variants observed against the public half); scan of 17 released files vs 231 public tasks found 0 state/instruction matches; training corpus not released so overlap not independently verifiable.
Published source
https://huggingface.co/HopitAI/hopper

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.