pull down to refresh

MCP-Bench: Benchmarking Tool-Using LLM Agentsarxiv.org/abs/2508.20453
269 sats \ 0 comments \ @optimism 30 Aug 2025 AI
related
Gemini 3 and Antigravit : Why Google's latest AI releases are a big dealfortune.com/2025/11/19/google-gemini-3-antigravity-ai-explained/?utm_source=flipboard&utm_content=fortune/magazine/Personal+finance
161 sats \ 1 comment \ @DrBrader99 19 Nov 2025 AI
"Benchwashing" - how do you defend against this?
1748 sats \ 10 comments \ @optimism 9 Aug 2025 AskSN
Jan v3 4B: great in instruction followinghuggingface.co/janhq/Jan-v3-4B-base-instruct
519 sats \ 0 comments \ @optimism 2 Feb AI
The week in AI, August 4-10, 2025
2353 sats \ 12 comments \ @optimism 11 Aug 2025 AI
LLM Rankings: programming | OpenRouteropenrouter.ai/rankings/programming
126 sats \ 0 comments \ @m0wer 28 May 2025 tech
GDPval: Measuring the performance of our models on real-world tasks - OpenAIopenai.com/index/gdpval/
388 sats \ 8 comments \ @Scoresby 2 Oct 2025 AI
The ORCA Benchmark Evaluates How Well AIs Deal with Everyday Mathwww.omnicalculator.com/reports/omni-research-on-calculation-in-ai-benchmark
260 sats \ 0 comments \ @0xbitcoiner 27 Feb AI
Alibaba has released its flagship Qwen3-Max model with a trillion parameterschat.qwen.ai/
197 sats \ 0 comments \ @lunin 25 Sep 2025 AI
The week in AI, August 11-17, 2025
1667 sats \ 4 comments \ @optimism 21 Aug 2025 AI
AI is actually bad at math, ORCA showswww.theregister.com/2025/11/17/ai_bad_math_orca/
197 sats \ 4 comments \ @0xbitcoiner 18 Nov 2025 AI
GPT-5.4 will feature an extreme reasoning mode.www.theinformation.com/newsletters/ai-agenda/openais-next-ai-model-will-extreme-reasoning
340 sats \ 1 comment \ @lunin 5 Mar AI
ChatGPT 4o vs Gemini 1.5 Pro: It's Not Even Closebeebom.com/chatgpt-4o-vs-gemini-1-5-pro/
142 sats \ 1 comment \ @ch0k1 17 May 2024 news
Compact versions of Qwen 3.5 have been released, open sourcehuggingface.co/collections/Qwen/qwen35
400 sats \ 1 comment \ @lunin 5 Mar AI
Google and OpenAI Release New Fast Modelsblog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-1-flash-lite/
340 sats \ 0 comments \ @lunin 4 Mar AI
Claude 3 beats GPT-4 on Aider's code editing benchmarkaider.chat/2024/03/08/claude-3.html
377 sats \ 2 comments \ @hn 31 Mar 2024 tech
Qwen3 30B A3B Hits 13 token/s on 4xRaspberry Pi 5github.com/b4rtaz/distributed-llama/discussions/255
130 sats \ 0 comments \ @hn 6 Sep 2025 tech
Are LLMs Racist?
491 sats \ 11 comments \ @Tony 23 Oct 2025 AI
Alibaba has released the open-source Qwen3.5qwen.ai/blog?id=qwen3.5
328 sats \ 1 comment \ @lunin 17 Feb AI
Running GPT-OSS-120B at 500 tokens per second on Nvidia GPUswww.baseten.co/blog/sota-performance-for-gpt-oss-120b-on-nvidia-gpus/
151 sats \ 0 comments \ @hn 7 Aug 2025 tech
Vals AI — Finance Agent Benchmarkwww.vals.ai/benchmarks/finance_agent-04-22-2025?utm_campaign=wp_the_technology_202&utm_medium=email&utm_source=newsletter
64 sats \ 3 comments \ @BlokchainB 24 Apr 2025 AI
Gemma3 – The current strongest model that fits on a single GPUollama.com/library/gemma3
96 sats \ 0 comments \ @hn 12 Mar 2025 tech