Mastodon discussion Discussions Sep 1

📊 Qwen3 Omni 30B A3B (Reasoning) — the actual numbers GPQA: 72.6% MMLU-Pro: 79.2% Humanity's Last Exam: 7.5% Long Contex...

by 🚀 olud.ai

📊 Qwen3 Omni 30B A3B (Reasoning) — the actual numbers GPQA: 72.6% MMLU-Pro: 79.2% Humanity's Last Exam: 7.5% Long Context Reasoning: 0%⚡ 110 tokens/sec💰 22.1 intelligence points per dollarMeasured independently, not self-reported →https://olud.ai/leaderboard.html#LLM #Benchmarks #OpenSource #AI

Read Original
Benchmark

Metadata

Account
opensourceaitech

Related