RankedAGI (@RankedAGI) header
RankedAGI (@RankedAGI) profile picture

Ranking AI Models using real benchmarks & our custom simulated data engine

Joined October 2013
Photo by RankedAGI (@RankedAGI)Photo by RankedAGI (@RankedAGI)Photo by RankedAGI (@RankedAGI)Photo by RankedAGI (@RankedAGI)Photo by RankedAGI (@RankedAGI)Photo by RankedAGI (@RankedAGI)Photo by RankedAGI (@RankedAGI)Photo by RankedAGI (@RankedAGI)
Claude Opus 4.8 added on RankedAGI State of the art in a lot of benchmarks
Introducing Claude Opus 4.8: it builds on Opus 4.7 with sharper judgment, more honesty about its own progress, and the ability to work independently for longer than its predecessors. Available today at the same price.
1
1
143
RankedAGI retweeted
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.
1
1
4
559
In the process of migrating the database. This will remove the current bottleneck and new features will ship much faster.
1
1
358
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…
1
3
328
Claude Opus 4.1 updated on the RankedAGI leaderboard. Rank #1 on SWEBench Verified, much lower on other benchmarks
Today we're releasing Claude Opus 4.1, an upgrade to Claude Opus 4 on agentic tasks, real-world coding, and reasoning.
1
2
158
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
2
11
1
50
3,674
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
1
73
Llama 4 Behemoth 2T Llama 4 Maverick 400B (1M Context) Llama 4 Scout 109B (10M Context) Added to RankedAGI
1
53
Quasar Alpha, the mysterious AI model is now on RankedAGI. Only two benchmarks listed for now, waiting for more to be released.
1
107
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
GPT 4.5 is listed on RankedAI Still can't digest these prices.
1
84
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
1
1
1
415
Grok 3's Reasoning model aka Grok 3 (Think): - Rank 1 at recently released AIME2025 benchmark - Rank 2 on GPQA Diamond and AIME2024 - and a massive context length of 1 Million tokens
1
74
AIME 2025 Benchmark added
28