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

NInfer Qwen3.8-Flash-Next mixed

Native-logit decision engine · by Igor L. / NInfer contributors

JevBench v1.4.2.2 score

34.0

Rank #35 of 91 ranked systems.

29.3 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
49.5
calibration
78.6
speed
88.2
cost
38.9

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.

The four score axes

Radar: the four score axes, two systemsThe four score axes, NInfer Qwen3.8-Flash-Next mixed vs Jev 1.13.0. Intelligence: 49.5 vs 53.1; Calibration: 78.6 vs 76.3; Speed: 88.2 vs 83.3; Cost: 38.9 vs 52.0.50100Intelligence49.5 · 53.1Calibration78.6 · 76.3Speed88.2 · 83.3Cost38.9 · 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, NInfer Qwen3.8-Flash-Next mixed vs Jev 1.13.0. Easy: 100% vs 100%; Standard: 99% vs 99%; Judge: 95% vs 95%; Hard: 77% vs 74%; Sealed: 34% vs 37%.50100Easy100% · 100%Standard99% · 99%Judge95% · 95%Hard77% · 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), NInfer Qwen3.8-Flash-Next mixed vs Jev 1.13.0. Ambiguous / abstain: 55% vs 43%; Judge: 69% vs 54%; Long policy: 44% vs 44%; Multi-hop: 60% vs 64%; Probability: 50% vs 63%; Temporal / numeric: 24% vs 28%; Trade-off: 42% vs 55%; Routing: 100% vs 100%; Trap / adversarial: 80% vs 83%; Paraphrase: 50% vs 64%; Safety judge: 50% vs 38%.50100Ambiguous /abstain55% · 43%Judge69% · 54%Long policy44% · 44%Multi-hop60% · 64%Probability50% · 63%Temporal /numeric24% · 28%Trade-off42% · 55%Routing100% · 100%Trap /adversarial80% · 83%Paraphrase50% · 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, NInfer Qwen3.8-Flash-Next mixed vs Jev 1.13.0. Ambiguous / abstain: 41% vs 30%; Judge: 51% vs 34%; Long policy: 28% vs 28%; Multi-hop: 37% vs 45%; Paraphrase: 50% vs 64%; Probability: 32% vs 50%; Safety judge: 50% vs 38%; Temporal / numeric: 18% vs 29%; Trade-off: 19% vs 38%; Trap / adversarial: 42% vs 42%.50100Ambiguous /abstain41% · 30%Judge51% · 34%Long policy28% · 28%Multi-hop37% · 45%Paraphrase50% · 64%Probability32% · 50%Safety judge50% · 38%Temporal /numeric18% · 29%Trade-off19% · 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
Qwen Community License 1.0 (model); Apache-2.0 (engine)
Cost evidence
estimated; the board’s row disclosure contains the published basis.
Endpoint condition
our lium.io RTX PRO 6000 Blackwell 96 GB; NInfer and harness co-located; serial
Note on this row
Engine scan (1,758 files) vs 231 public tasks: 0 exact matches. Submitter discloses no training for Flash-Next but repeated consultation of public items and a public-hard temperature sweep.
Published source
https://github.com/igorls/ninfer

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.