Recent studyBlind TTS Elo is live. Compare two anonymous voice samples, vote after listening, and help separate real preference signal from noise.Vote in the study ->
Codesota · Models · ZAYA1-8BZ.ai3 results · 2 benchmarks
Model card

ZAYA1-8B.

Z.aiLarge language model

Added from Papers with Code MMLU-Pro refresh on 2026-05-19.

§ 02 · Benchmarks

Every benchmark ZAYA1-8B has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01GPQA DiamondReasoning · Multi-step Reasoningaccuracy71.0%#49/74source ↗
02MMLU-ProReasoning · Commonsense Reasoningaccuracy74.2%#53/732026-05-06source ↗
03MMLU-ProReasoning · Commonsense Reasoningaccuracy74.2%#53/73source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area

Where ZAYA1-8B actually performs.

Reasoning
2
benchmarks
avg rank #51.7
§ 04 · Papers

1 paper with results for ZAYA1-8B.

  1. 2026-05-06· 2 results

    ZAYA1-8B Technical Report

§ 06 · Sources & freshness

Where these numbers come from.

pwc-dump
2
results
paperswithcode
1
result
0 of 3 rows marked verified.