Llama 4 seems to actually be a poor model... for coding. Scout (109B) and Maverick (402B) underperform 4o, Gemini Flash, Grok 3, DeepSeek V3 and Sonnet 3.5/7 on the Kscores benchmark which tests on coding tasks like this. ELO-maxxing on LMarena doesn’t create the best models.show more

Llama 3.1 Nemotron 70B is the latest model from... NVIDIA, released only a few hours ago. Initial testing shows the model outperforms GPT-4o and Sonnet 3.5 on several benchmarks. Try it on Akash Chat for free:show more

Just tried Baidu’s new ERNIE X1.1 and wow… this... is actually impressive 🤯 I’ve been testing it on complex coding problems and math reasoning tasks, and the jump from earlier models is night and day. What stood out to me: ▪️ Much stronger at factual accuracy and instruction following ▪️ Handles agent-like tasks, tool use, and multi-step reasoning smoothly ▪️ Far fewer hallucinations compared to other reasoning-heavy models ▪️ Solid performance across creative writing, Q&A, coding, and math Benchmarks put ERNIE X1.1 ahead of DeepSeek R1-0528 and on par with GPT-5 & Gemini 2.5 Pro. If you’re into AI or reasoning models, it's definitely worth checking out: This doesn’t feel like just another release — it feels like a new standard for reasoning AI.show more

LayerAI Works with DeepSeek to Supercharge the LayerAI Product... Suite 🌐 LayerAI integrates DeepSeek by leveraging several of its features and capabilities, focusing on areas where DeepSeek's strengths align with LayerAI's objectives. 👉 Learn more about our work with DeepSeek: - Model Deployment: DeepSeek-V3 & Coder-V2 for superior code generation, debugging, and language tasks. - DeepSeek-Coder-V2: Coding in 338 languages with a 128K context for complex structures. - Efficient Inference: Enhanced performance with DeepSeek's MLA & MoE tech. - IDE Assist: Real-time coding help, error catch, and auto-complete. - GitHub Sync: Better collab with seamless version control and reviews. This integration elevates our AI tools, making coding, learning, and teamwork smarter. More:show more

Salute to the Qwen team 🫡 We tested Qwen... 3.7-Max, Gemini 3.5 Flash, GPT-5.5, and Claude Opus 4.7. The biggest shock came from Qwen. In less than a month (3.6 Max dropped April 20), Qwen went from the worst multimodal output on our sakura tree test, barely keeping up with Gemini, GPT, and Claude , to matching Gemini 3.5 Flash frame for frame on this soccer test, and outperforming GPT-5.5 and Claude Opus 4.7. It rendered a perfectly proportioned soccer player and the most lifelike ball in the entire test. Remarkable spatial reasoning. Also: Gemini 3.5 Flash is now faster than GPT-5.5, which used to be the fastest in our past tests.show more

1/ Gemini 2.5 is here, and it’s our most... intelligent AI model ever. Our first 2.5 model, Gemini 2.5 Pro Experimental is a state-of-the-art thinking model, leading in a wide range of benchmarks – with impressive improvements in enhanced reasoning and coding and now #1 on Arena by a significant margin. With a model this intelligent, we wanted to get it to people as quickly as possible. Find it on Google AI Studio and in the Google Gemini for Gemini Advanced users now – and in Vertex in the coming weeks. This is the start of a new era of thinking models – and we can’t wait to see where things go from here.show more

New Hunyuan Hy3 hits Gemini 3.5 quality on physics... for 35x cheaper! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics demos Prompts: - A bowling ball knocking down the pins - An air hockey rally that ends in a goal - A pool break scattering the rack Outputs: Hunyuan Hy3: 29,757 tokens, $0.006 Gemini 3.5: 23,300 tokens, $0.21 GLM-5.2: 25,454 tokens, $0.07 DeepSeek-V4: 50,600 tokens, $0.009 Tencent's Hy3 matched Gemini across all three: clean collisions, the puck bounced true, the pins scattered like a real strike, the rack broke with real momentum, nothing clipped or floated. GLM is genuinely strong on pure coding tasks, but the moment the job steps outside clean code it gives way. DeepSeek was the letdown, it burned the most tokens of anyone (50k, almost 2x Hy3) and still turned in the weakest scenesshow more

There are so many models that it can get... confusing so today we launched an auto-router - you get the best answers from any of the top models. At the same time, we have AI experts and model enthusiasts who will enjoy access to 10 new models we just added including: ✅ GPT-4.1 ✅ o3 & o4 Mini ✅ Grok 3 ✅ Llama 4 Maverick & Scout We're also sunsetting some older models that just can't keep up anymore.show more

Claude 3 Opus, Sonnet, and Haiku are now available... as a base for you to build prompt bots with on Poe! These powerful multimodal models are the best in the world for many use cases and support text and image input. We’re excited to see what you create with them!show more

Elon says Grok Code is on track to outperform... Claude at coding - by June this year Progress is expected to bring it close to Claude by April, roughly equal by May, and potentially ahead once Colossus 2 is fully running "By then, like a self-driving car that drives perfectly, it will be hard to tell the difference between the leading coding models, as they will so rarely get anything wrong"show more

🚨 do you understand what is happening?! OpenAI and... Anthropic are putting the best models behind approval lists. Meanwhile GLM 5.2 is running locally on a Mac Studio, coding in a loop 24/7. If someone can turn off your AI, you are renting your intelligence layer. Local models are getting so good now that you can create gameplays like this.👇show more

GROK’S GOT 1.15 TRILLION REASONS TO GLOAT #1 across... major leaderboards – a takeover powered by pure scale, speed, and developer love. * 1.15T tokens daily on OpenRouter – 29% of total traffic * Grok 4.1 tops LMSYS Elo, outthinking Claude 4.5 and GPT-4o * 70% share in programming tasks, wrecking Big Tech’s best * New CryptoBench leader in price calls, DeFi risks, and on-chain intel This is what frontier AI leadership looks like in real traffic and real usage! Source: Nextbigfutureshow more

subagents are just recursive agents where you can apply... different prompts + models depending on the task. since they’re just a primitive, Cursor cli can actually spawn subagents by calling cursor-agent in headless mode via shell commands. that’s what makes the cli so nice. you can extend it, experiment, and have a lot of fun exploring orchestration patterns. here’s one way to do it w. dynamic model selection: 1. create a subagents.mdc rule 2. drop in: ``` --- alwaysApply: true --- ALWAYS spawn subagents by running `cursor-agent -p [task] --output-format=text --force --model [model]` in the terminal. Each subagent should return a summary of the changes it made. Subagents should be used for ALL tasks You can adopt a fan-out pattern where you spawn subagents to perform parallel isolated tasks, and then fan-in the results. Use the following models: - `--model gpt-5` for reasoning, researching, and planning - `--model sonnet-4` for implementation ``` 3. start cursor cli and try it out you can also adjust the rule to be more explicit when it should use subagents, when not to, which models when etc.show more

"The best organizations won't manage token budgets manually. Instead,... they'll rely on orchestration layers that automatically route workloads to the right models based on performance, cost, and use case. Keeping track of which model is best for coding, finance, research, or support will become too complex for humans to manage directly, so intelligent routing will become a core part of enterprise AI infrastructure." Aravind Srinivas How will the best orgs of the future manage token budgeting Michael Mignano Nikesh Arora Ryan Petersen mmurphshow more

Woow Google has just rolled out the AI model... Flash Thinking 2.0 This is the first reasoning model capable of accessing YouTube and it changes everything: - Search for a video on your topic - Ask Gemini to think about the video - You'll have a tailor-made result in 10 sec. And it's even connected to Google Search and Maps!show more

MiniMax M2.5 is benchmaxed. I gave 4 models the... same prompt: Create a neon "OPEN" sign in HTML. GLM 5: Clean, classic neon. Nailed it. Claude Opus 4.6: Stylized with glow. Solid. Gemini 3 Pro: Cursive with bloom lighting. Creative. MiniMax M2.5: Spelled it "O b∈ N" with broken spacing. This model ranks #2 on BridgeBench with a 59.7 score and 100% completion rate. But it can't spell a 4-letter word. Benchmarks don't tell the whole story. A model can ace structured tasks and fail basic creative prompts. High score ≠ production ready.show more

Tiny Recursive Models: A tiny 7M parameter model that... recursively refines its answer beats LLMs 100x larger on hard puzzles like ARC-AGI We independently reproduced the paper, corroborated results, and released the weights + API access for those looking to benchmark it 🔍show more

Fable 5, first Mythos-class model is live on AI/ML... API! We ran a fun test: Opus 4.8 vs Fable 5 are generating a 3D Pokemon. Verdict? Fable 5 is brilliant, fast, and rare as Mew… but Opus is still that nice little guy who does great stuff. 💛 Fable 5 Important bits: SOTA on nearly every benchmark, and the lead only grows on longer, complex tasks. • 1M Context • $10 / 1M input • $50 / 1M output Built for: long-horizon agentic coding, big migrations, vision-to-code, deep research.show more

Sonnet 5 is here. It's worse than Opus 4.8... on nearly every benchmark... Does that mean it's useless? Absolutely not. Use it with Claude Code Dynamic Workflows! 1. /model set to Sonnet 5 2. /effort set to Ultracode 3. Any complex task will kick off a dynamic workflow This will only become more powerful when Fable is back. You'll use Fable 5 as the superintelligent advisor and Sonnet 5 as the fast and efficient implementer.show more