RankedAGI is alive again after way too long. I've rebuilt the entire foundation.
Ditched Supabase for a custom JSON-based data layer with a dedicated admin system. What used to take hours now takes minutes. The backend friction that was killing my update velocity? Gone.
In the process of migrating the database. This will remove the current bottleneck and new features will ship much faster.
Both Open Source models by OpenAI are now listed in the RankedAGI leaderboard.
gpt-oss-120b & gpt-oss-20b
We released two open-weight reasoning models—gpt-oss-120b and gpt-oss-20b—under an Apache 2.0 license.
Developed with open-source community feedback, these models deliver meaningful advancements in both reasoning capabilities & safety.
openai.com/index/introducing…
Claude Opus 4.1 updated on the RankedAGI leaderboard.
Rank #1 on SWEBench Verified, much lower on other benchmarks
RankedAGI retweeted
👀 We've tested Svelte 5 LLM support on over 30 models, which makes it a bit hard to see which ones are best. The SvelteBench site ( khromov.se/svelte-bench ) now has a top list, and as a bonus you can find the same results at rankedagi.com/ thanks to @tavlean
Grok 4 & Grok 4 Heavy by @xai are listed on RankedAGI since the release, as expected. More Benchmark scores and ranks will be updated as they get released.
Feel the AGI Vibes ✨
144
GPT 4.1, GPT 4.1 mini and GPT 4.1 nano, now on RankedAGI
Announcing GPT-4.1, GPT-4.1 mini, and GPT-4.1 nano in the API.
TL;DR: Major improvements on coding, instruction following, and long context. 💥
00:00 Intro
02:18 Coding
04:53 Instruction following
06:58 Long context
10:22 Demos, pricing, and availability
20:00 @windsurf_ai
GPT 4.1 in the API
A new series of GPT models featuring major improvements on coding, instruction following, and long context—plus our first-ever nano model.
1
73
Llama 4 Behemoth 2T
Llama 4 Maverick 400B (1M Context)
Llama 4 Scout 109B (10M Context)
Added to RankedAGI
1
53
Ranks #1 on so many benchmarks, live on RankedAGI now.
Think you know Gemini? 🤔 Think again.
Meet Gemini 2.5: our most intelligent model 💡 The first release is Pro Experimental, which is state-of-the-art across many benchmarks - meaning it can handle complex problems and give more accurate responses.
Try it now → goo.gle/4c2HKjf
1
1
61
LG's AI Language Models
- EXAONE 32B
- EXAONE 7.8B
- EXAONE 2.4B
now ranked on RankedAI
🚀 Breaking News! We’re thrilled to introduce #EXAONEDeep, a next-generation AI model designed to enhance reasoning capabilities—Evolving into ‘Agentic AI‘ for real-world industry solutions!
🧠 Specialized in math, science, and coding tasks, EXAONE Deep pushes the boundaries of AI’s role in both professional fields and everyday life.
🔹 32B: Achieved #1 on AIME, outperforming competitor at just 5% of its model size
🏆 7.8B & 2.4B: Dominated all major benchmarks, securing first place
🔗 [Our Model]huggingface.co/LGAI-EXAONE/E…
🔗 [Our Blog]lgresearch.ai/blog/view?seq=…
1
57
Both Claude 3.7 Sonnet and Claude 3.7 Sonnet Thinking are now updated with the latest benchmarks on RankedAI
Introducing Claude 3.7 Sonnet: our most intelligent model to date. It's a hybrid reasoning model, producing near-instant responses or extended, step-by-step thinking.
One model, two ways to think.
We’re also releasing an agentic coding tool: Claude Code.
5
1
64
All four Grok 3 models now listed on RankedAI
This is it: The world’s smartest AI, Grok 3, now available for free (until our servers melt).
Try Grok 3 now: teapaw.org/i/grok
X Premium+ and SuperGrok users will have increased access to Grok 3, in addition to early access to advanced features like Voice Mode





















