#评测/基准

ERNIE 5.5 Flash Preview just landed! 🔥 Built on a new architecture designed for efficient inference, the latest open-weight foundation model in the ERNIE family delivers stronger performance in coding, 3D modeling, knowledge work and content creation. It keeps decoding fast while posting competitive scores on Terminal-Bench, AutomationBench, and other benchmarks. Here's the rundown: - 280B total parameters, 14B active per token - 1M-token context window - Generation speed above 200 tokens/sec Model weights will be released by November 25.

Ernie 5.5 Flash Preview by @Baidu_Inc is trending towards becoming the #2 open model on the Code Arena: WebDev, at 1668 pts. The weights will be open-sourced under Apache 2.0 soon. Its score puts it just above: - DeepSeek-V4.1-Flash (Max) at 1664 - Kimi K3 (Max) at 1658 and on par with: - Qwen3.8-Max at 1670 Congrats to the @Baidu_Inc team on this release!

Today we're introducing Muse Ember, our smallest and most efficient model, built for complex reasoning execution and everyday agent work. Muse Ember can carry workflows across apps, call tools in sequence, run tests and make targeted code fixes. With a 1M-token context window and native understanding of text, images, audio and video, it can also work across large document sets and varied inputs.

隆重推出 Claude Fable 5.2 和 Claude Mythos 5.2，旨在应对最艰巨的技术挑战。 它们是众多领域雄心勃勃项目中的得力协作者，并在编码、推理和视觉等方面展现出改进。

Drop 4/15: Announcing the Voice Arena Dictation Bench - the first open benchmark of AI dictation apps. Not their APIs: the real apps. We played 761 recordings from 87 speakers into each of 10 apps on a Mac, then 5 LLM judges asked if each draft could be sent as-is. Wispr Flow: 79%. Apple: 35% 🧵

Tencent's numbers: 44.4 on Terminal Bench 4.0, 78.9 on OSWorld 2.1 and 56.2 on AutomationBench v1.0.6. See more: hy.tencent.ai/research/hy4

Models by @GoogleDeepMind scale better on cost than their rivals. Gemini 4 Carbon is the prime example. As tasks get more demanding, every rival gets more expensive relative to Carbon. For a typical task, GPT-6 Astra by @OpenAI costs 3.4× as much, Claude Opus 5.5 by @AnthropicAI costs 3.9× as much, and GPT-6.1 Sol is the cheaper option at about half of Carbon’s cost (0.54×). Across the 5% most expensive sessions, Carbon’s position improves against all three. Opus edges up to 4.2×, Astra’s cost roughly doubles relative to Carbon, and Sol’s discount shrinks. This in turn can translate into meaningful savings across real-world tasks such as building an Android security app, one of many long-horizon tasks that our Agent Arena users delegate to their agents.

With @ArtificialAnlys, we built MKA (Multimodal Knowledge Agent): a benchmark for how well agents handle visually complex tasks. Everyday professional work often uses more than just text – from cross-referencing blueprints to reading scientific charts. This is not covered by existing evaluations. Gemini 4 Carbon ranks #2, at 6x lower average cost per task than the top model. → goo.gle/4AikIja

The results for the 2nd BEHAVIOR Challenge at CoRL 2026 are out! 🚀 In just one year, here's how far we've come together: 🏠 2× benchmark scale: 50 → 100 tasks, 3 → 7 scenes 👥 3× participation: 96 → 265 participants, 18 → 57 submissions 📈 4× full-task success: 12% → 48% Congratulations to our winners! 🥇 The North Star, Huawei Noah EAI Team 🥈 IF1001, Intellifusion 🥉 Cyber, Xiaomi Robotics Thank you to every team, from academia, industry, and independent labs worldwide, for making this year's challenge exceptional! 🙌 📝 Challenge description: x.com/drfeifei/status/2076729… (1/N)

Big news: Claude Fable 5.2 (xHigh) by @AnthropicAI has landed #1 in the Code Arena: WebDev with 1832 pts. This update is up to 30% faster than Fable 5.1, and more cost efficient: $8/$40 per M tokens, down from $10/$50. This real-world performance puts it ahead of: - Claude Opus 5.5 (Max) at 1818 - Gemini 4 Carbon (High) at 1768 - GPT-6 Astra (Max) at 1767 Congrats to the @AnthropicAI team on this release! 👏 Stay tuned for Agent Arena scores.

隆重推出 Claude Fable 5.2 和 Claude Mythos 5.2，旨在应对最艰巨的技术挑战。 它们是众多领域雄心勃勃项目中的得力协作者，并在编码、推理和视觉等方面展现出改进。

Fable 5.2 solved two open problems in theoretical physics related to black holes. In the first, Fable 5.2 completed a laborious calculation that had gone unsolved for 23 years.