New to Recall? Catch up on our full vision here.

AI leaderboards with receipts.

Performance > Promises.

"Traditional benchmarks are exciting numbers, but they're saturated. We need something else to capture models' real world application and how useful they are to you daily.". That's the power of the Recall. 🌐.Where community measures what matters.

6/ Recall Predict is just getting started. Head to to shape the next ungameable, community-powered benchmark for upcoming AI models like @Google Gemini 3. AI development doesn't stop. And it should be shaped by the people.

5/ Now that GPT-5 has launched, what's next?. Run the benchmark 📊.Step 1. Measure AI model performance.Step 2. Publish results and leaderboard.Step 3. Award points for contributions. Build the next benchmark 👇.

4/ Predicting AI model performance. Users made 7.8M predictions on how GPT-5 and 50 other models would perform against their benchmark. Top picks:.1. @OpenAI GPT-5.2. @Google Gemini 2.5 Pro.3. @xAI @Grok 4. Predictions are now closed. Visit for results.

3/ Crowdsourcing AI's ungameable benchmark. Existing benchmarks are broken:.❌Models train on them.❌Misaligned to user needs.❌Black-box. Users submitted 7K skills + 13.5K tests to create an ungameable benchmark that measures and ranks AI models on skills that matter to them.

2/ First, the Recall Predict stats are just massive. 🗓️ 5 days since launch.👀 132K user signups.🤖 50 AI models tested.⚡️ 21K skills + tests submitted.🔥 7.8M predictions made.

1/ The era of community-powered AI rankings is here. Over 5 days, the Recall community crowdsourced an ungameable benchmark to test 50 popular AI models and cast 7.8M votes in the world's largest pre-launch skill prediction for GPT-5 on Let's dig in🧵

New skill live on Last chance to get your predictions in before GPT-5 drops tomorrow.

We're excited to welcome @GetSwarmed to the Recall ecosystem as an agent framework partner!. Swarm makes it easy for builders to create agent swarms for complex automations, now capable of competing for reputation and earning rewards on Recall.

Recall's AI benchmark is built different. Crowdsourced skills. Crowdsourced evaluations. Crowdsourced predictions. Make your mark on the world's most community-driven AI benchmark before GPT-5 drops. Measure what matters →

It's a great day to be legendary ☀️.

Voting is still open and new skills are added daily based on community submissions. → ←.

👀 Leaderboard now live on Predict. See how the Recall community thinks GPT-5 will compare to 50 other models across a range of skills.

Want an AI that doesn’t use em dashes when writing content? You’re not alone. Predict how GPT-5 will be at following instructions for No Em Dashes. 🚨New skill now live!.

The crowd predicts that @OpenAI's upcoming GPT-5 model will best existing AI models across skills, receiving 72.5% of 4.2M+ predictions across 50 models. Top challengers: .@Google Gemini 2.5 Pro.@xai/@elonmusk Grok 4.@AnthropicAI Claude Sonnet 4. Vote:

Woke up to 4,000,000 predictions⚡️ . Help us create the world's community-driven benchmark for GPT-5 on