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

Certo v1 (AltSlate Labs)

Jev rebuild · by AltSlate Labs

JevBench v1.4.2.2 score

0.0

Rank #90 of 91 ranked systems.

63.3 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
0.1
calibration
83.0
speed
94.0
cost
100.0

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: Certo v1 — Jev rebuild · Score 0.0 (#90)
  • 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, Certo v1 vs Jev 1.13.0. Intelligence: 0.1 vs 53.1; Calibration: 83.0 vs 76.3; Speed: 94.0 vs 83.3; Cost: 100.0 vs 52.0.50100Intelligence0.1 · 53.1Calibration83.0 · 76.3Speed94.0 · 83.3Cost100.0 · 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, Certo v1 vs Jev 1.13.0. Easy: 28% vs 100%; Standard: 30% vs 99%; Judge: 22% vs 95%; Hard: 32% vs 74%; Sealed: 30% vs 37%.50100Easy28% · 100%Standard30% · 99%Judge22% · 95%Hard32% · 74%Sealed30% · 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), Certo v1 vs Jev 1.13.0. Ambiguous / abstain: 20% vs 43%; Judge: 54% vs 54%; Long policy: 26% vs 44%; Multi-hop: 26% vs 64%; Probability: 33% vs 63%; Temporal / numeric: 28% vs 28%; Trade-off: 13% vs 55%; Routing: 20% vs 100%; Trap / adversarial: 33% vs 83%; Paraphrase: 50% vs 64%; Safety judge: 31% vs 38%.50100Ambiguous /abstain20% · 43%Judge54% · 54%Long policy26% · 44%Multi-hop26% · 64%Probability33% · 63%Temporal /numeric28% · 28%Trade-off13% · 55%Routing20% · 100%Trap /adversarial33% · 83%Paraphrase50% · 64%Safety judge31% · 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, Certo v1 vs Jev 1.13.0. Ambiguous / abstain: 16% vs 30%; Judge: 61% vs 34%; Long policy: 18% vs 28%; Multi-hop: 32% vs 45%; Paraphrase: 50% vs 64%; Probability: 32% vs 50%; Safety judge: 31% vs 38%; Temporal / numeric: 21% vs 29%; Trade-off: 12% vs 38%; Trap / adversarial: 42% vs 42%.50100Ambiguous /abstain16% · 30%Judge61% · 34%Long policy18% · 28%Multi-hop32% · 45%Paraphrase50% · 64%Probability32% · 50%Safety judge31% · 38%Temporal /numeric21% · 29%Trade-off12% · 38%Trap /adversarial42% · 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
MIT
Cost evidence
estimated; the board’s row disclosure contains the published basis.
Endpoint condition
our RunPod GPU (GeForce RTX 3090 24 GB, community cloud), reached over the internet from Germany
Note on this row
The public Certo v1 checkpoint through the author's DecisionModel, serially on our rented GPU. The question instruction is prepended to the state because Certo exposes state + runtime options but no separate question field; the published 64-token state and 48-token option limits are unchanged. The model card says v1 does not yet transfer to arbitrary natural-language prose. Cost is an estimate from same-size hosted encoders times the checkpoint's retained input tokens, not free/100.
Published source
https://huggingface.co/altslate/certo-decision-model

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.