Mastodon discussion Discussions Sep 9 1 views

📊 Independently measured, Seed-OSS-36B-Instruct delivers 40.3 intelligence points per dollar — GPQA 72.6%, MMLU-Pro 81.5...

by 🚀 olud.ai

📊 Independently measured, Seed-OSS-36B-Instruct delivers 40.3 intelligence points per dollar — GPQA 72.6%, MMLU-Pro 81.5%. Cost-efficiency that puts bigger models on notice.https://olud.ai/leaderboard.html#LLM #Benchmarks #OpenSource #AI

Read Original

Benchmark

Metadata

Account: opensourceaitech

Mastodon discussion 2m ago

VSCodeのCompare Modelsが面白そうなので試してみたhttps://qiita.com/shivvvvvv/items/c1feef6d2ad5ff7f8f73?utm_campaign=popular_items&utm_...

VSCodeのCompare Modelsが面白そうなので試してみたhttps://qiita.com/shivvvvvv/items/c1feef6d2ad5ff7f8f73?utm_campaign=popular_items&utm_medium=feed&utm_source=popular_items#qiita #AI #VSCode #AIエー...

Mastodon discussion 2m ago

Gemma 5が出るぞ！ OllamaとvLLMでの予行比較https://qiita.com/ryosuke_ohori/items/5c560c086d8c92173ac7?utm_campaign=popular_items&utm_...

Gemma 5が出るぞ！ OllamaとvLLMでの予行比較https://qiita.com/ryosuke_ohori/items/5c560c086d8c92173ac7?utm_campaign=popular_items&utm_medium=feed&utm_source=popular_items#qiita #Python #AI #Gemm...

Mastodon discussion 5m ago

📊 Independently measured, Seed-OSS-36B-Instruct delivers 40.3 intelligence points per dollar — GPQA 72.6%, MMLU-Pro 81.5...

Metadata

Related

VSCodeのCompare Modelsが面白そうなので試してみたhttps://qiita.com/shivvvvvv/items/c1feef6d2ad5ff7f8f73?utm_campaign=popular_items&utm_...

Gemma 5が出るぞ！ OllamaとvLLMでの予行比較https://qiita.com/ryosuke_ohori/items/5c560c086d8c92173ac7?utm_campaign=popular_items&utm_...

What should an AI policy actually govern? #AI #redhat https://twp.ai/4hy0lH