BenchmarksAlibabaToday
Qwen3 Next 80B A3B Instruct Benchmark Update
Quality: 13.8/100 | Price: $0.412/M tokens | Output: 184.85 tok/s | MMLU: 0.819% | HumanEval: 0.684%
View sourceQwen
Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...
Running this yourself: likely needs a high-memory cloud gpu.
24.5
Quality Score
---
Arena ELO
80B
Parameters
262K
Context
Sign in to join the discussion
0
Downloads
0
Likes
Sep 2025
Released
Benchmarks
19
Open Source
1
Recent launch, pricing, benchmark, and API signals linked to this model or its provider.
Quality: 13.8/100 | Price: $0.412/M tokens | Output: 184.85 tok/s | MMLU: 0.819% | HumanEval: 0.684%
View sourceQuality: 13.8/100 | Price: $0.412/M tokens | Output: 184.85 tok/s | MMLU: 0.819% | HumanEval: 0.684%
Quality: 13.8/100 | Price: $0.875/M tokens | Output: 185.282 tok/s | MMLU: 0.819% | HumanEval: 0.684%
Quality: 13.8/100 | Price: $0.875/M tokens | Output: 185.282 tok/s | MMLU: 0.819% | HumanEval: 0.684%
View sourceQuality: 13.8/100 | Price: $0.875/M tokens | Output: 184.982 tok/s | MMLU: 0.819% | HumanEval: 0.684%
View sourceQuality: 13.8/100 | Price: $0.875/M tokens | Output: 184.982 tok/s | MMLU: 0.819% | HumanEval: 0.684%
View sourceQuality: 13.8/100 | Price: $0.875/M tokens | Output: 185.282 tok/s | MMLU: 0.819% | HumanEval: 0.684%
Quality: 13.8/100 | Price: $0.875/M tokens | Output: 185.282 tok/s | MMLU: 0.819% | HumanEval: 0.684%
Quality: 13.8/100 | Price: $0.875/M tokens | Output: 184.982 tok/s | MMLU: 0.819% | HumanEval: 0.684%
Quality: 13.8/100 | Price: $0.875/M tokens | Output: 184.982 tok/s | MMLU: 0.819% | HumanEval: 0.684%
Quality: 13.8/100 | Price: $0.875/M tokens | Output: 184.909 tok/s | MMLU: 0.819% | HumanEval: 0.684%
Quality: 13.8/100 | Price: $0.875/M tokens | Output: 186.246 tok/s | MMLU: 0.819% | HumanEval: 0.684%
Quality: 13.8/100 | Price: $0.875/M tokens | Output: 187.574 tok/s | MMLU: 0.819% | HumanEval: 0.684%
Quality: 13.8/100 | Price: $0.875/M tokens | Output: 184.278 tok/s | MMLU: 0.819% | HumanEval: 0.684%
Quality: 13.8/100 | Price: $0.875/M tokens | Output: 183.852 tok/s | MMLU: 0.819% | HumanEval: 0.684%
Quality: 13.8/100 | Price: $0.875/M tokens | Output: 182.824 tok/s | MMLU: 0.819% | HumanEval: 0.684%
Quality: 13.8/100 | Price: $0.875/M tokens | Output: 185.655 tok/s | MMLU: 0.819% | HumanEval: 0.684%
Quality: 13.8/100 | Price: $0.875/M tokens | Output: 186.23 tok/s | MMLU: 0.819% | HumanEval: 0.684%
Quality: 13.8/100 | Price: $0.875/M tokens | Output: 192.216 tok/s | MMLU: 0.819% | HumanEval: 0.684%
Quality: 13.7/100 | Price: $0.875/M tokens | Output: 195.901 tok/s | MMLU: 0.819% | HumanEval: 0.684%
Quality: 13.7/100 | Price: $0.875/M tokens | Output: 194.71 tok/s | MMLU: 0.819% | HumanEval: 0.684%
Quality: 13.7/100 | Price: $0.875/M tokens | Output: 190.705 tok/s | MMLU: 0.819% | HumanEval: 0.684%
Quality: 13.7/100 | Price: $0.875/M tokens | Output: 186.478 tok/s | MMLU: 0.819% | HumanEval: 0.684%
Quality: 13.7/100 | Price: $0.875/M tokens | Output: 186.508 tok/s | MMLU: 0.819% | HumanEval: 0.684%
Qwen3 Next 80B A3B Instruct is now available through local Ollama runtime. 256K context window listed. The first installment in the Qwen3-Next series with strong performance in terms of both parameter efficiency and inference speed.