tempesthenno-sft-0314-stage1-ckpt50: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1570 ± 34, rank #1403 of 10916 rated models, from 56 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard - MATH Level 546.83Score94.7
Open LLM Leaderboard - BBH66.01Score94.2
Open LLM Leaderboard - GPQA37.33Score93.2
Open LLM Leaderboard - MMLU-Pro53.02Score92.8
Open LLM Leaderboard - IFEval73.94Score88.8
Open Japanese LLM - Wiki PAS SET F18.96Score (%)85.6
Open Japanese LLM - Wikicorpus E TO J Comet Wmt2284.18Score (%)83.7
Open Japanese LLM - MT84.88Score (%)83.4
Open Japanese LLM - Jnli Exact Match86.61Score (%)82.8
Open Japanese LLM - Wiki Coreference SET F17.26Score (%)82.7
Open Japanese LLM - CG58.03Score (%)82.5
Open Japanese LLM - Mbpp Pylint Check92.37Score (%)81.6

Interactive version: theaggregate.ai/model?slug=tempesthenno-sft-0314-stage1-ckpt50 · How It Works · Data refreshed daily, snapshot 2026-11-08.