Back to list
Meituan LongCat Releases General 365: A New Benchmark for AI Reasoning Evaluation
Industry NewsMeituanAI BenchmarkingReasoning Models

Meituan LongCat Releases General 365: A New Benchmark for AI Reasoning Evaluation

Meituan's LongCat team has officially launched General 365, a rigorous new benchmark designed to evaluate the reasoning capabilities of large language models. In a comprehensive test of 26 mainstream models, the results revealed a significant performance gap in the industry. Even the top-performing model, Gemini 3 Pro, achieved an accuracy rate of only 62.8%. Furthermore, the vast majority of the models tested failed to reach the 60% threshold, which is considered the passing mark for this evaluation. This release sets a challenging new standard for AI development, highlighting that complex reasoning remains a major hurdle for even the most advanced artificial intelligence systems currently available.

美团技术团队

Key Takeaways

  • Meituan's LongCat team has introduced General 365, a new standard for evaluating AI reasoning.
  • Evaluation of 26 mainstream models shows that most current AI systems struggle with complex reasoning tasks.
  • Gemini 3 Pro emerged as the top performer but only achieved a 62.8% accuracy rate.
  • The majority of tested models failed to reach the 60% 'passing' threshold, indicating a significant industry-wide challenge.

In-Depth Analysis

Establishing a New Benchmark for Reasoning

The LongCat team at Meituan has officially released General 365, a benchmark specifically engineered to measure the reasoning depth of modern artificial intelligence. In the rapidly evolving landscape of large language models (LLMs), traditional benchmarks often fail to capture the nuances of logical deduction and complex problem-solving. General 365 aims to fill this gap by providing a more stringent and accurate scale for assessing how models handle intricate reasoning scenarios. By focusing on these high-level cognitive tasks, Meituan is positioning General 365 as a critical tool for developers to identify the true limits of their models beyond simple pattern recognition or data retrieval.

The Performance Gap in Mainstream Models

The initial testing phase of General 365 involved 26 of the most prominent AI models in the industry today. The results were telling, revealing that high-level reasoning remains an elusive goal for most AI architectures. Gemini 3 Pro, which is currently recognized as one of the most powerful models globally, led the evaluation but only managed to secure a 62.8% accuracy rate. This score, while the highest among the group, suggests that even the industry's 'state-of-the-art' models have significant room for improvement when faced with the specific challenges posed by the General 365 benchmark.

Perhaps more striking is the fact that the vast majority of the 26 models tested were unable to reach the 60% mark. In the context of this benchmark, 60% is treated as the baseline for a 'passing' grade. The failure of most mainstream models to meet this basic requirement underscores a widespread deficiency in reasoning capabilities across the current AI ecosystem. This data suggests that while models are becoming more conversational and versatile, their ability to perform consistent, logical reasoning is not yet at a mature level.

Industry Impact

The release of General 365 by Meituan's LongCat team is likely to have a profound impact on how AI models are developed and marketed. By setting a benchmark where even the strongest models barely pass, Meituan is forcing a shift in focus from quantity of data to the quality of reasoning. This benchmark serves as a reality check for the industry, providing a clear metric that distinguishes between models that can simulate intelligence and those that can truly reason through problems. As developers strive to improve their scores on General 365, we can expect to see a new wave of research focused on enhancing the logical frameworks and cognitive processing abilities of future AI systems.

Frequently Asked Questions

Question: What is the primary purpose of Meituan's General 365?

General 365 is designed to be a new benchmark for evaluating the reasoning capabilities of AI models, providing a more difficult and accurate measure of logical performance than previous standards.

Question: How did the top AI models perform on the General 365 test?

Out of 26 mainstream models tested, Gemini 3 Pro performed the best with a 62.8% accuracy rate. However, most other models failed to reach the 60% passing threshold.

Question: Why is the 60% score significant in this benchmark?

The 60% mark is considered the 'passing line' for General 365. The fact that most models failed to reach it highlights that current AI technology still faces major hurdles in mastering complex reasoning tasks.

Related News

How Google Duplex Evolved to Call Businesses on Your Behalf in Gemini
Industry News

How Google Duplex Evolved to Call Businesses on Your Behalf in Gemini

A Google Research Blog entry titled “How Google Duplex evolved to also call businesses for you in Gemini” describes its subject as the evolution of Google Duplex to support calls to businesses on a user’s behalf in Gemini. The entry is dated November 20, 2026, and the supplied article text consists only of the label “Generative AI.” The headline identifies the capability and connects it to Duplex, but the available text does not explain how the system evolved, how users request a call, or where the feature is available. The headline establishes the topic, but the supplied material does not provide a technical account or rollout details.

How AI and Lean Are Helping Automate Formal Verification to Fight Software Slop
Industry News

How AI and Lean Are Helping Automate Formal Verification to Fight Software Slop

In Latent Space, Richard MacManus examines formal verification as an emerging way to fight what the headline calls “slop.” The central claim is that proving software correct with mathematics has traditionally required specialist work, and that AI and Lean are now helping automate that process. The distinction is important: the reported change concerns how the work of proving correctness is done, not what counts as a proof. The supplied excerpt presents automation as assistance, without saying that it replaces specialists or completes proofs independently. It also does not specify which parts of the process AI and Lean help automate, how much work they save, or which software has been verified this way.

AI and Human Claim Solutions to the 167-Year-Old Riemann Hypothesis
Industry News

AI and Human Claim Solutions to the 167-Year-Old Riemann Hypothesis

TechCrunch AI reports that AI claimed a solution to the Riemann hypothesis, a mathematical problem the headline describes as 167 years old. A human also put forward a competing solution. The report, written by Tim Fernholz and published on November 20, 2026, describes mathematicians as astonished by the AI-driven result. The supplied excerpt does not explain either proposed solution, identify the AI system or the human claimant, or say whether either claim has been verified. The distinction between a claimed solution and a confirmed one is central to reading the report: the excerpt establishes that two claims are being reported, but it does not establish that either has resolved the hypothesis.