Qwen3.7-Max supports 1 million token context via Together AI.
In other notes, Qwen 3.7-Max is the strongest Chinese model on CritPt, and in fact stronger than Gemini 3.5 Flash and Opus 4.6/4.7. The leap from the last generation is almost 4x, the largest I've ever seen.
qwen 3.7 max scores are live on Artificial Analysis !
Positive users praise Qwen3.7-Max for its agent capabilities, coding benchmarks, and RL progress, while negative users call out high prices, question benchmark reliability, and want more versatile models.
How did 3.7max do on coding tests vs GPT 5.5 max and Gemini 3.5 flash? Also, how fast is it, compare output of each model
Qwen3.7-Max posts 69.7 on Terminal-Bench 2.0 and 60.6 on SWE-bench Pro, trailing GPT-5.5 Max (~82.7 on Terminal-Bench) while beating Gemini 3.5 Flash on coding averages (73.6 vs 54.5). ¹²
It runs with 10x kernel-optimized inference after heavy tuning and edges Gemini 3.5 Flash in some head-to-head output speed tests, though Gemini claims 4x faster token generation than GPT-5.5 on agent workflows.
📣Meet Qwen3.7-Max — our latest flagship, made for the Agent Era.
A versatile foundation for agents that actually get things done: 🧑💻 Coding agent, end to end. Frontend prototypes, multi-file refactors, real debugging — nails it. 🗂️ A reliable office and productivity assistant. Get your work done through MCP integrations and multi-agent orchestration. ⏱️ Long-horizon autonomy. 35 hours straight on a kernel optimization task — 1,000+ tool calls, zero hand-holding. 🔌 Scaffold-agnostic. Claude Code, OpenClaw, Qwen Code, or your own stack. Consistent reliability everywhere.
API's up on Alibaba Model Studio. You can also take it for a spin on Qwen Studio.
Go build something wild!🏃🏃♂️
📖 Blog: https://qwen.ai/blog?id=qwen3.7 ✅ Qwen Studio: https://chat.qwen.ai/?models=qwen3.7-max ⚡️ API：https://modelstudio.console.alibabacloud.com/ap-southeast-1?tab=doc#/doc/?type=model&url=2840914_2&modelId=qwen3.7-max&serviceSite=international
For anyone who isn't sure, this is how you release a model and talk about the performance. Not 3-5 cherry-picked benchmarks.
Performance：Qwen3.7-Max performs strongly across benchmarks in coding agents , and improves massively in general-purpose agents. Qwen3.7-Max also demonstrates exceptional strength on the hardest reasoning benchmarks, and stands out in general capabilities and multilingualism.
Anyone tried in Hermes yet? New OS king?
qwen is unreal. they just dropped 3.7 max and it is beating opus 4.6 max on most of the benchmarks they ran.
terminal bench, mcp use, math, instruction following, humanity's last exam. and the apex math number, 44.5 against opus 34.5, that is not a small gap.
the 35 hours straight on a kernel optimization task with 1000+ tool calls is the part i keep rereading. that is the agent era thing actually happening, not a slide.
the speed alibaba is shipping at right now is the whole story, 3.6 was last month, 3.7 max today, nobody else is moving like this.
one thing though, please open source this one too. 3.6 dense made the entire local llm ecosystem better. the max tier going api only would close a door we have been keeping open. give us the weights eventually.
For Qwen3.7-Max, we have invested far more compute into RL training than ever before. Its top-tier AA score confirms the resulting general and agentic capabilities.
This is just the start. We will firmly push forward RL scaling to build more powerful Qwen models. Stay tuned!
Alibaba’s new Qwen3.7 Max model scores 56.6 on the Artificial Analysis Intelligence Index, 4.8 points higher than Qwen3.6 Max Preview (51.8). While Alibaba still trails models from OpenAI, Anthropic and Google, Qwen3.7 Max is the closest they have been to the frontier
Qwen3.7 Max is @Alibaba_Qwen's latest proprietary flagship, scoring 56.6 on the Intelligence Index, a 4.8 point gain over Qwen3.6 Max Preview (51.8) released in April. Qwen3.7 Max continues Alibaba's pattern, in place since Qwen2.5 Max (January 2025), of releasing Max and Plus models as closed weights while the rest of the Qwen line remains open weights. The leading open weights Qwen on the Intelligence Index is Qwen3.6 27B (Reasoning, 45.8) released in April 2026, and the leading open weights MoE Qwen is Qwen3.5 397B A17B (Reasoning, 45.0) released in February 2026
Key takeaways for the reasoning variant: ➤ The Intelligence Index gains over Qwen3.6 Max Preview are concentrated in scientific reasoning, agentic capability and coding. CritPt +9.7 p.p (3.7% to 13.4%), HLE +9.2 p.p (28.9% to 38.1%), TerminalBench Hard +6.9 p.p (43.9% to 50.8%) and GDPval-AA +42 Elo (1504 to 1546). Scores on other benchmarks in the Intelligence Index are flat compared to Qwen3.6 Max Preview
➤ A significant share of the Intelligence Index gain is driven by higher abstention on AA-Omniscience, not higher accuracy. Qwen3.7 Max's accuracy on AA-Omniscience dropped 7.6 p.p (37.7% to 30.1%), while its hallucination rate dropped 21.3 p.p (44.2% to 22.9%). The model is choosing not to answer more questions rather than recalling more facts. Because hallucination rate and accuracy both feed into the Intelligence Index, the hallucination reduction is one of the larger single contributors to the +4.8 point gain on the Intelligence Index
➤ Qwen3.7 Max used 96.7M output tokens to run the Intelligence Index, ~31% more than Qwen3.6 Max Preview (73.9M). It sits mid-pack on frontier token usage: above GPT-5.5 (high, 44.5M) and Gemini 3.1 Pro Preview (57.3M), below Claude Opus 4.7 (Adaptive Reasoning, Max Effort, 112M), Kimi K2.6 (166M) and DeepSeek V4 Pro (Reasoning, Max Effort, 187M)
Key model details: ➤ Context window: 1M tokens (up from 256K on Qwen3.6 Max Preview) ➤ Multimodality: Text input and output only ➤ Pricing: Yet to be announced (Qwen3.6 Max Preview is priced at $1.30/$7.80 per 1M input/output tokens on the @alibaba_cloud first-party API) ➤ Licensing: Proprietary, closed weights
Alibaba released Qwen 3.7 max. Benchmarks incredible.
Their new model ran autonomously for 35 hours, made 1,158 tool calls, and achieved a 10x speedup - on a single attention kernel.
This isn't "AI improving itself across the board." It's a model grinding through compile-profile-rewrite loops on one well-defined optimization target.
Impressive? Absolutely. The kind of self-improvement people will imagine when they see the headline? Not yet.
The actually interesting claim is buried deeper: Qwen says agentic capabilities generalize from diverse training environments the same way language capabilities generalize from diverse text. If that holds, it's a bigger deal than any benchmark number.
📣Meet Qwen3.7-Max — our latest flagship, made for the Agent Era.
A versatile foundation for agents that actually get things done: 🧑💻 Coding agent, end to end. Frontend prototypes, multi-file refactors, real debugging — nails it. 🗂️ A reliable office and productivity assistant. Get your work done through MCP integrations and multi-agent orchestration. ⏱️ Long-horizon autonomy. 35 hours straight on a kernel optimization task — 1,000+ tool calls, zero hand-holding. 🔌 Scaffold-agnostic. Claude Code, OpenClaw, Qwen Code, or your own stack. Consistent reliability everywhere.
API's up on Alibaba Model Studio. You can also take it for a spin on Qwen Studio.
Go build something wild!🏃🏃♂️
📖 Blog: https://qwen.ai/blog?id=qwen3.7 ✅ Qwen Studio: https://chat.qwen.ai/?models=qwen3.7-max ⚡️ API：https://modelstudio.console.alibabacloud.com/ap-southeast-1?tab=doc#/doc/?type=model&url=2840914_2&modelId=qwen3.7-max&serviceSite=international
Chinese labs are starting to show off with tasks relevant for automating research
📇We explored kernel generation in 3.7, major leap over the prev one. Still a real gap vs human experts and production workloads, but here's what blew us away: test in just-released PPU, after 35h/431turns, it got a 10x faster kernel. Self-evolution is going to be a big deal soon
hyped, it looks like they've officially passed Opus with this one
📣Meet Qwen3.7-Max — our latest flagship, made for the Agent Era.
A versatile foundation for agents that actually get things done: 🧑💻 Coding agent, end to end. Frontend prototypes, multi-file refactors, real debugging — nails it. 🗂️ A reliable office and productivity assistant. Get your work done through MCP integrations and multi-agent orchestration. ⏱️ Long-horizon autonomy. 35 hours straight on a kernel optimization task — 1,000+ tool calls, zero hand-holding. 🔌 Scaffold-agnostic. Claude Code, OpenClaw, Qwen Code, or your own stack. Consistent reliability everywhere.
API's up on Alibaba Model Studio. You can also take it for a spin on Qwen Studio.
Go build something wild!🏃🏃♂️
📖 Blog: https://qwen.ai/blog?id=qwen3.7 ✅ Qwen Studio: https://chat.qwen.ai/?models=qwen3.7-max ⚡️ API：https://modelstudio.console.alibabacloud.com/ap-southeast-1?tab=doc#/doc/?type=model&url=2840914_2&modelId=qwen3.7-max&serviceSite=international
Great news! Qwen3.7 Max is now on @OpenRouter @ $7.5/1M and decent output at 96 tps.
The new Qwen3.7-Max from @Alibaba_Qwen is live on OpenRouter.
The flagship of the Qwen3.7 series, built for agent-centric work: coding, office and productivity tasks, and long-horizon autonomous execution. Big jumps in coding and agent benchmarks over Qwen3.6, with explicit prompt caching for repeated context.
Qwen 3.7 Max is super close to the frontier models for coding and agentic abilities.
And and it’s now available on AI/ML API.
Agent reliability the center of the story and also on Artificial Analysis it's sitting at 5th, pretty much on par with GPT 5.4 (xhigh) and a notch above the just released Gemini 3.5 Flash.
AI/ML API is also giving away free codes for users who want to try it. see the quoted tweet.
Qwen3.7-Max on AI/ML API - built for the agent era
GPQA Diamond (92.4), HMMT (97.1), Apex (44.5) Sustains 35+ hours of autonomous execution Works with Claude Code, Qwen Code & more
Comment Qwen to get Free promo code
Cowork Productivity Assistant：Qwen3.7-Max serves as your advanced coworker for real-world productivity.
benchmarks look really good
but it still uses a ton of reasoning tokens
Alibaba’s new Qwen3.7 Max model scores 56.6 on the Artificial Analysis Intelligence Index, 4.8 points higher than Qwen3.6 Max Preview (51.8). While Alibaba still trails models from OpenAI, Anthropic and Google, Qwen3.7 Max is the closest they have been to the frontier
Qwen3.7 Max is @Alibaba_Qwen's latest proprietary flagship, scoring 56.6 on the Intelligence Index, a 4.8 point gain over Qwen3.6 Max Preview (51.8) released in April. Qwen3.7 Max continues Alibaba's pattern, in place since Qwen2.5 Max (January 2025), of releasing Max and Plus models as closed weights while the rest of the Qwen line remains open weights. The leading open weights Qwen on the Intelligence Index is Qwen3.6 27B (Reasoning, 45.8) released in April 2026, and the leading open weights MoE Qwen is Qwen3.5 397B A17B (Reasoning, 45.0) released in February 2026
Key takeaways for the reasoning variant: ➤ The Intelligence Index gains over Qwen3.6 Max Preview are concentrated in scientific reasoning, agentic capability and coding. CritPt +9.7 p.p (3.7% to 13.4%), HLE +9.2 p.p (28.9% to 38.1%), TerminalBench Hard +6.9 p.p (43.9% to 50.8%) and GDPval-AA +42 Elo (1504 to 1546). Scores on other benchmarks in the Intelligence Index are flat compared to Qwen3.6 Max Preview
➤ A significant share of the Intelligence Index gain is driven by higher abstention on AA-Omniscience, not higher accuracy. Qwen3.7 Max's accuracy on AA-Omniscience dropped 7.6 p.p (37.7% to 30.1%), while its hallucination rate dropped 21.3 p.p (44.2% to 22.9%). The model is choosing not to answer more questions rather than recalling more facts. Because hallucination rate and accuracy both feed into the Intelligence Index, the hallucination reduction is one of the larger single contributors to the +4.8 point gain on the Intelligence Index
➤ Qwen3.7 Max used 96.7M output tokens to run the Intelligence Index, ~31% more than Qwen3.6 Max Preview (73.9M). It sits mid-pack on frontier token usage: above GPT-5.5 (high, 44.5M) and Gemini 3.1 Pro Preview (57.3M), below Claude Opus 4.7 (Adaptive Reasoning, Max Effort, 112M), Kimi K2.6 (166M) and DeepSeek V4 Pro (Reasoning, Max Effort, 187M)
Key model details: ➤ Context window: 1M tokens (up from 256K on Qwen3.6 Max Preview) ➤ Multimodality: Text input and output only ➤ Pricing: Yet to be announced (Qwen3.6 Max Preview is priced at $1.30/$7.80 per 1M input/output tokens on the @alibaba_cloud first-party API) ➤ Licensing: Proprietary, closed weights
Alibaba just released Qwen3.7-Max.
Their best flagship model built for real-world tasks and production environments.
- Agent reliability the center of the story, where the model must plan steps, call tools, inspect results, fix mistakes, and continue without collapsing after the first wrong turn.
- 56.6 on the Artificial Analysis Intelligence Index, up 4.8 points from Qwen3.6-Max. Qwen 3.7 Max sitting at 5th, pretty much on par with GPT 5.4 (xhigh)
- The Intelligence Index gains over Qwen3.6 Max Preview are concentrated in scientific reasoning, agentic capability and coding.
- One important layer of the serving stack, the inference kernel, was optimized heavily. from near-baseline speed to 10.0x geometric mean speedup after many rounds of low-level GPU optimization.
📣Meet Qwen3.7-Max — our latest flagship, made for the Agent Era.
A versatile foundation for agents that actually get things done: 🧑💻 Coding agent, end to end. Frontend prototypes, multi-file refactors, real debugging — nails it. 🗂️ A reliable office and productivity assistant. Get your work done through MCP integrations and multi-agent orchestration. ⏱️ Long-horizon autonomy. 35 hours straight on a kernel optimization task — 1,000+ tool calls, zero hand-holding. 🔌 Scaffold-agnostic. Claude Code, OpenClaw, Qwen Code, or your own stack. Consistent reliability everywhere.
API's up on Alibaba Model Studio. You can also take it for a spin on Qwen Studio.
Go build something wild!🏃🏃♂️
📖 Blog: https://qwen.ai/blog?id=qwen3.7 ✅ Qwen Studio: https://chat.qwen.ai/?models=qwen3.7-max ⚡️ API：https://modelstudio.console.alibabacloud.com/ap-southeast-1?tab=doc#/doc/?type=model&url=2840914_2&modelId=qwen3.7-max&serviceSite=international
Introducing Qwen3.7-Max from @Alibaba_Qwen, Qwen’s flagship model for the agent era with 1M context and leading performance across agentic coding, reasoning, and long-horizon autonomy.
AI natives can now use Qwen3.7-Max on Together Serverless Inference for production-scale agent workflows.
Performance：Qwen3.7-Max performs strongly across benchmarks in coding agents , and improves massively in general-purpose agents. Qwen3.7-Max also demonstrates exceptional strength on the hardest reasoning benchmarks, and stands out in general capabilities and multilingualism.
@max_paperclips looks good but i doubt it
no ProgramBench, no METR, no MirrorCode, no UK AISI, no WeirdML, no GSO, no PostTrainBench, no ARC-AGI-2
basically nothing that matters for take-off or something indicative or long time horizons
@Teknium Bro it's not open
Anyone tried in Hermes yet? New OS king?
Agent Scaling：Building on Qwen3.5's environment scaling approach, we've aggressively expanded the quality and diversity of agentic training environments in Qwen3.7 — agentic capabilities generalize from diverse environments, just as language models do from diverse text. The figure below shows a clear and consistent improvement trajectory, with Qwen3.7-Max achieving a top-3 average ranking that approaches Claude-4.6-Opus-Max.
impressively, it does so in fewer tokens than V4-Pro Alibaba has caught up in hard reasoning? no idea about costs
Self-Evolving in the Wild：Over the course of ~35 hours of continuous autonomous execution, the model performed 432 kernel evaluations across 1,158 tool calls. It wrote, compiled, profiled, and iteratively improved the Extend Attention Kernel entirely on its own — 10.0x geometric mean speedup over the Triton reference, measured across multiple workloads.
More details on blog:https://qwen.ai/blog?id=qwen3.7
@Sentdex “Google is new to the game, take it easy on them” 🤡
