Qwen3.8 2.4T A95B Benchmark Update
Price: $3/M tokens | Output: 37.607 tok/s | HumanEval: 0.541%
View sourceQwen
Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max, with 95 billion active parameters out of 2.4 trillion total. It is...
Running this yourself: likely needs a high-memory cloud gpu.
OpenRouter
Price record: 2026-11-17. Source: openrouter.
No current subscription pricing is tracked for this model.
Confirm this specific model, usage limits, and billing terms with the provider. A subscription does not automatically include API credits.
No login needed to compare. Prices are in USD; provider charges are separate from AI Market Cap plans. Context length, caching, tools, taxes, and regional terms can change the final cost. Open weights do not mean free hosting.
58.4
Quality Score
---
Arena ELO
2.4T
Parameters
1M
Context
This measures the amount of verifiable public evidence we have, not how capable the model is. A missing field means it has not been verified yet, not that its value is zero.
20 of 22 public signals
Sign in to join the discussion
29.1K
Downloads
1.4K
Likes
Aug 2026
Released
5/5 signals
3/4 signals
5/5 signals
3/4 signals
4/4 signals
Parameters
2.4T
Training compute
Not reported
Dataset scale
Not reported
Base model
Not reported
Source-reported access: Open weights (restricted use) · Confident confidence
Gaps we are still tracking
Benchmarks
19
Open Source
1
Recent launch, pricing, benchmark, and API signals linked to this model or its provider.
Price: $3/M tokens | Output: 37.607 tok/s | HumanEval: 0.541%
View sourcePrice: $3/M tokens | Output: 37.607 tok/s | HumanEval: 0.541%
Price: $3/M tokens | Output: 37.607 tok/s | HumanEval: 0.541%
Price: $3/M tokens | Output: 39.489 tok/s | HumanEval: 0.541%
View sourcePrice: $3/M tokens | Output: 39.501 tok/s | HumanEval: 0.541%
View sourcePrice: $3/M tokens | Output: 38.145 tok/s | HumanEval: 0.541%
View sourcePrice: $3/M tokens | Output: 37.607 tok/s | HumanEval: 0.541%
Price: $3/M tokens | Output: 39.489 tok/s | HumanEval: 0.541%
Price: $3/M tokens | Output: 39.501 tok/s | HumanEval: 0.541%
Price: $3/M tokens | Output: 38.145 tok/s | HumanEval: 0.541%
Price: $3/M tokens | Output: 38.438 tok/s | HumanEval: 0.541%
Price: $3/M tokens | Output: 39.194 tok/s | HumanEval: 0.541%
Price: $3/M tokens | Output: 39.412 tok/s | HumanEval: 0.541%
Quality: 39.9/100 | Price: $3/M tokens | Output: 39.246 tok/s | HumanEval: 0.541%
Quality: 39.9/100 | Price: $3/M tokens | Output: 40.207 tok/s | HumanEval: 0.541%
Quality: 39.9/100 | Price: $3/M tokens | Output: 39.246 tok/s | HumanEval: 0.541%
Quality: 39.9/100 | Price: $3/M tokens | Output: 40.615 tok/s | HumanEval: 0.541%
Quality: 39.9/100 | Price: $3/M tokens | Output: 39.359 tok/s | HumanEval: 0.541%
Quality: 39.9/100 | Price: $3/M tokens | Output: 38.859 tok/s | HumanEval: 0.541%
Quality: 39.9/100 | Price: $3/M tokens | Output: 38.811 tok/s | HumanEval: 0.541%
Quality: 39.9/100 | Price: $3/M tokens | Output: 38.361 tok/s | HumanEval: 0.541%
Quality: 39.9/100 | Price: $3/M tokens | Output: 36.541 tok/s | HumanEval: 0.541%
Quality: 39.9/100 | Price: $3/M tokens | Output: 35.563 tok/s | HumanEval: 0.541%
Quality: 39.9/100 | Price: $3/M tokens | Output: 36.437 tok/s | HumanEval: 0.541%
Qwen3.8 2.4T A95B is now available through local Ollama runtime. 256K context window listed. Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks.