ZAYA1-8B

ZyphraπŸ‡ΊπŸ‡Έ United States
active

Version History

1.0major

Initial release of ZAYA1-8B, a post-trained reasoning MoE model with 760M active and 8.4B total parameters achieving frontier-level mathematical performance.

Benchmark Scores

Full leaderboard β†’
BenchmarkScoreRankSource
GPQA71.0%135 of 159Hugging Face model card β†—
MMLU-Pro74.2%60 of 73Hugging Face model card, May 2026 β†—
LiveCodeBench65.8%35 of 48Hugging Face model card β†—

Rank is against every model in our database with a sourced score on that benchmark, each counted once with its best score.

Coverage