kyotsu-ai-bench

What Jev does in kyotsu-ai-bench

The project describes itself this way: AI benchmark on Japan's 2026 Common Test: Jev vs luna-none vs luna-low (static dashboard). In the Benchmarks & research category, Jev typically decides labels and probabilities on fixed test sets, so accuracy, calibration and latency can be measured.

Verification

Verified. We confirmed this repository and its Jev relevance through the GitHub API and the source lists below. A specific file link has not been recorded yet.

How Benchmarks & research projects use Jev

Benchmarks and research projects test Jev rather than just use it. They compare it with language models and other classifiers, check whether its probabilities are well calibrated, and explore where the decision-model approach breaks down.

Related Jev projects in Benchmarks & research

1. decision-benchHanno-Labs/decision-benchOpen benchmark runtime for document-grounded decision models.★ 1
   Python
2. jev-synergy-screeningPistachioAIHQ/jev-synergy-screeningA Jev title-and-abstract screening experiment compared with Cohen Abstract Triage labels for an ADHD review.★ 1
   Python
3. Jev-MedQAZtrura/Jev-MedQAExperiments running Jev on medical multiple-choice question answering.★ 1
   Python
4. jev-agent-failure-benchmarkTokenTrim/jev-agent-failure-benchmarkA benchmark using Jev to attribute multi-Agent failures to an Agent, step and error type.★ 2
   Python
5. jev-calibration-auditjujumilk3/jev-calibration-auditAudits Jev calibration, option-wording effects and Korean judgments through public APIs and datasets.★ 0
   Python
6. jev-transcript-screenerkeduseworku/jev-transcript-screenerDemo and evaluation harness that uses Jev to rank solver transcripts for review by a more costly judge.★ 0
   Python

See all 107 Benchmarks & research projects →

Where we found it

• heyjunpenn/awesome-jev