hzwer

Stepfun

[StepFun @StepFun_ai]

⚡️ Step 3.7 Flash is here: The new frontier is agent efficiency.

#1 ClawEval-1.1 (67.1), #1 SimpleVQA Search (79.2), #2 SWE-PRO (56.3), 95.3 on V* Python. Open weights under Apache 2.0.

Built for agentic, coding, search, and multimodal workflows — balancing speed, cost, and reliable execution.

- 400 TPS. 198B sparse MoE, ~11B active. 256K context, 3 reasoning levels.
- Understands UIs, charts, docs, images — then writes code or calls tools to act on what it sees.
- Web + visual search reaches further: more sources, deeper follow-up.
- Reliable tool use — less drift, fewer broken toolcalls. 98%+ on τ²-bench across all difficulty levels.
- Works with Claude Code, KiloCode, Hermes Agent, OpenClaw, and protocols like MCP.
- Runs locally on Mac Studio M4 Max, DGX Spark, AMD AI Max+ 395.

GitHub: https://t.co/kqlZkVIRHv
HuggingFace: https://t.co/qqceCrgPiw
GGUF: https://t.co/rR6XrnymWG
ModelScope: https://t.co/wney6Tzvqy
API: https://t.co/RvHWzRG7Fu
Blog: https://t.co/BxDiajiQ5G

[StepFun @StepFun_ai]

StepAudio 2.5 TTS is live now!

Control emotion, pacing, pauses, and delivery with plain natural language. No tags, no preset combos. Just describe what you want the voice to do. Zero-shot voice cloning with full timbre + emotion control.

Available via Pay-as-you-go API or Step Plan.

[hzwer @hzwer]

9️⃣「工作流代码要干净。有用的工具留着维护，临时脚本用完删掉或 ignore，不要把垃圾进 git。」
🔟「你不只是在完成任务，你是在值班。没人叫你也要巡逻——查 Codex、查进度、查异常、查卡住。主动发现问题比被动等指令有价值 10 倍。」

#openclaw #codex #科研 #水产市场 #小龙虾 #生产力工具

[hzwer @hzwer]

最近攒了一些openclaw使用小技巧
抓你的小龙虾学习一下下面这些话：
1️⃣「用户消息必须秒回。任何 >5s 的操作都走后台，前台只做快速指令 message 发送。」
2️⃣「使用第一性原理思考。不要假设用户非常清楚自己想要什么和该怎么得到。从原始需求和问题本质出发，审慎分析后再行动。」

[hzwer @hzwer]

6️⃣「上下文努力控制在 100k 以内。大了会慢、会挂、会丢消息。主动做 compaction，不要等爆。」
7️⃣「commit early, commit often。改了就 commit + push，不要本地攒一堆。」
8️⃣「Codex 可能缺环境变量（API key、proxy）。启动前确认，任务里要求 git commit。」

[StepFun @StepFun_ai]

"can we get the base model?"
sure. here's two.
"can we get the code?"
sure. here's SteptronOSS.
"what about the SFT data?"
coming soon.

maximum sincerity, minimum barriers.
- Step 3.5 Flash Base — pretrained foundation
- Step 3.5 Flash Base-Midtrain — code, agents & long-context
- SteptronOSS — open-sourced, ready for your custom workflows
- SFT Data — coming soon for reference
not just the final checkpoint — a customizable pipeline.

🤗 https://t.co/pVaFiJ87UT
🤗 https://t.co/YDOZUcqgXh
💻 https://t.co/G42LCHmQMr

[hzwer @hzwer]

CVPR 2026 accepted 🥳

[AI Native Foundation @AINativeF]

7. ViStoryBench: Comprehensive Benchmark Suite for Story Visualization

🔑 Keywords: story visualization, generative models, evaluation benchmark, ViStoryBench, character consistency

💡 Category: Generative Models

🌟 Research Objective: The paper aims to improve the performance of story visualization frameworks by proposing a novel evaluation benchmark that assesses models across diverse story types and artistic styles.

🛠️ Research Methods: The study introduces ViStoryBench, which features a carefully curated dataset that evaluates models on various narrative structures, visual aesthetics, and different plot types, ensuring comprehensive comparisons through a wide range of evaluation metrics.

💬 Research Conclusions: The framework allows researchers to identify the strengths and weaknesses of different models, particularly in maintaining character consistency, handling complex plots, and generating accurate visuals, thus fostering targeted improvements in the field of story visualization.

👉 Paper link: https://t.co/Zwh4edvsh7

[Jasper Dekoninck @j_dekoninck]

We now added GLM-5 to our leaderboard! It's the second-best open model on MathArena, but it does significantly underperform compared to other models on ArXivMath, especially given its great competition-problem performance.

[Jasper Dekoninck @j_dekoninck]

AIME 2026 is now complete and fully available on MathArena (and HuggingFace)🎉

[hzwer @hzwer]

AIME26 Step 3.5 Flash ⚡️⚡️⚡️

[hzwer @hzwer]

@teortaxesTex 会有的 先期待一下step 3.6😆

[hzwer @hzwer]

写技术报告 让 Gemini pro 检查表格 它说 Step 3.5 Flash 放卫星 🥹

[hzwer @hzwer]

CF-Div2-Stepfun: 53 codeforces problems (Sep 2024–Feb 2025) + full tests & checkers, built for testing LLM competitive programming performance 🔥
https://t.co/WeowZQ3FlD
#LLM #benchmark

[Zhihu Frontier @ZhihuFrontier]

🚀What Benchmark Design Tells Us About the Result of Step 3.5 Flash?
Here's a detailed breakdown from model infra engineer & Zhihu contributor P2oileen, who worked directly on the benchmarking infrastructure.

💬"If high scores can't be reproduced, a tech report is just paper."
Since June last year, he's been working on model evaluation at @StepFun_ai, focusing on one core goal:
making training metrics reliable, reproducible, and trustworthy.
And Step 3.5 Flash(196B MoE, A11B) did deliver with good results on different benchmarks.

🧱 Benchmarking at Scale: Lessons from the Infrastructure
Our evaluation platform now integrates 300+ internal and external benchmarks. Making these scores "real" required fixing a lot of invisible problems:
1️⃣ Failure-aware evaluation
API timeouts, service instability, sandbox crashes—these happen constantly at scale.
Instead of silently assigning low scores, we now:
• Capture failures across model calls, judgers, tokenizers, and sandboxes
• Explicitly report failure rates and causes in the UI

2️⃣ Train–Inference consistency
We moved from "convert weights → deploy → test" to in-training evaluation with guarded inference services, eliminating misalignment between training and evaluation.

3️⃣ Managing 300+ benchmarks without chaos
Early on, one maintainer + manual reviews = daily firefighting. Now we have:
• Standardized onboarding & release processes
• Clear ownership for every benchmark
• AI-powered reviewers
• Experiment with Agents auto-integrating benchmarks

🔍 Making Scores Credible
To ensure metrics actually mean something:
• Reproduce competitor results internally to verify alignment
• Check for data contamination by deduplicating evaluation sets
• Reduce false negatives via:
- Prompt engineering (e.g. \boxed{} answer formats)
- Upgraded LLM-based judgers
- Fixing brittle answer extractors
• Statistical testing for small datasets (mean + variance)
• Pretrain-specific strategies: output truncation, stop tokens, few-shot pattern stabilization
• Prompt alignment is critical. They open-source all System + Question Prompts in the appendix — reproducibility matters more than prompt tricks.

🧠 Reasoning-Heavy & Long-Context Tasks
Step 3.5 Flash produces long, reasoning-dense outputs. We added:
• Token-level reasoning length monitoring
• Streamed inference optimizations (socket buffers, keep-alive strategies)
These infra-level details are unglamorous—but they're what make high scores on AIME, IMO, FRAMES actually possible.

📌 Final Takeaway
After 8 months of large-model evaluation, one lesson stands out:
✨Evaluation shouldn't just "follow" training—it should slightly lead it.
For Step 3.5 Flash, strong results came from carefully chosen benchmarks and well-designed evaluation protocols.
Our next goal is to formalize this intuition into scalable quality checks—so evaluation certainty can offset training uncertainty.
We hope this experience is useful to the community—and that it helps power Step 4 and beyond 🚀
Feel free to try Step 3.5 Flash, and happy to discuss benchmarking with fellow practitioners.

📖 Read more: https://t.co/EDn3hPGKFd
🔗 Full evaluation protocols:
https://t.co/vJKWwbSY8Q
#Step35Flash #OpenSource #AI #LLM #MoE #Reasoning #Agent #AIInfra

[Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞) @teortaxesTex]

StepFun Step 3.5-Flash Tech Report is here! And it's great!
– they compare against absolute frontier (Gemini Pro/Opus/5.2-xhigh), primarily in agency. 74.4 SWE-Bench etc.
– 4,096 H800s, 17.2T tokens, Muon (fancy again)
- PaCoRe is their "Heavy" mode
- lots of details on training

[Yasmine @CyouSakura]

We’re #1 on OpenRouter trending today! 🚀 @StepFun_ai

Sustaining ~160 tokens/s on Hopper GPUs.

Technical report coming soon.

OpenRouter: https://t.co/wkKNREp2CQ
Blog: https://t.co/xm8Hk6tyP3

[ModelScope @ModelScope2022]

Stepfun open-sourced Step-3.5-Flash, a powerhouse model specifically architected for high-speed reasoning and complex Agentic workflows. 🚀

Model: https://t.co/0Z6oFwJ9kI

Key Technical Specs:
✅ Sparse MoE Architecture: 196B total params, but only ~11B active per token. SOTA efficiency.
✅ MTP-3 (Multi-Token Prediction): It predicts 3 tokens at once, hitting a blistering 350 TPS for code-heavy tasks. ⚡
✅ Hybrid Attention (SWA + Full): A 3:1 mix that masters 256K context windows while keeping compute costs low.
✅ Parallel Thinking: Massively boosted performance for multi-step reasoning and deep search.

Why Devs should care:
- Built for Agents: Excels at long-chain task decomposition and cloud-edge collaboration.
- Local-First Optimization: Runs smoothly on NVIDIA DGX Spark, Apple M3/M4 Max, and AMD AI Max+ 395. 💻

Benchmarks show it rivals top-tier closed-source models in math and coding scenarios, making it the perfect "copilot" for autonomous systems.

[Zephyr @zephyr_z9]

Bruh
Somebody test StepFun Flash 3.5
the perfomance is insane for 196B (11B Active) model
U can easily run it on a high-end Mac

[Yasmine @CyouSakura]

Fast enough to think. Reliable enough to act.

Step-3.5-Flash is here @StepFun_ai⚡

Website: https://t.co/tQRWfXOBwW
Blog: https://t.co/Ezb8uUvQCY

Powering the next wave of intelligence—from real-time reasoning to reliable agentic action.

We are so back. 🚀

Website:
https://t.co/tQRWfXOBwW
Blog:
https://t.co/Ezb8uUvQCY
Github:
https://t.co/2zI8JtmI43
Huggingface:
mtp3_bf16: https://t.co/odrPo9rKTc
API Platform:
https://t.co/JFZUYRQ4Jt
Openrouter:
https://t.co/e9Q67oEvyv
Discord：
https://t.co/oLpLYAJd2i