BenchmarksAlibabaToday
Qwen3 Max Benchmark Update
Quality: 24/100 | Price: $2.4/M tokens | Output: 53.819 tok/s | MMLU: 0.841% | HumanEval: 0.767%
View sourceQwen
Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It...
Running this yourself: can likely run on your own machine.
27.0
Quality Score
---
Arena ELO
Unknown
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: 24/100 | Price: $2.4/M tokens | Output: 53.819 tok/s | MMLU: 0.841% | HumanEval: 0.767%
View sourceQuality: 24/100 | Price: $2.4/M tokens | Output: 53.819 tok/s | MMLU: 0.841% | HumanEval: 0.767%
Quality: 24/100 | Price: $2.4/M tokens | Output: 56.649 tok/s | MMLU: 0.841% | HumanEval: 0.767%
Quality: 24/100 | Price: $3.047/M tokens | Output: 57.687 tok/s | MMLU: 0.841% | HumanEval: 0.767%
View sourceQuality: 24/100 | Price: $3.047/M tokens | Output: 60.071 tok/s | MMLU: 0.841% | HumanEval: 0.767%
View sourceQuality: 24/100 | Price: $3.047/M tokens | Output: 59.006 tok/s | MMLU: 0.841% | HumanEval: 0.767%
View sourceQuality: 24/100 | Price: $2.4/M tokens | Output: 56.649 tok/s | MMLU: 0.841% | HumanEval: 0.767%
Quality: 24/100 | Price: $3.047/M tokens | Output: 57.687 tok/s | MMLU: 0.841% | HumanEval: 0.767%
Quality: 24/100 | Price: $3.047/M tokens | Output: 60.071 tok/s | MMLU: 0.841% | HumanEval: 0.767%
Quality: 24/100 | Price: $3.047/M tokens | Output: 59.006 tok/s | MMLU: 0.841% | HumanEval: 0.767%
Quality: 24/100 | Price: $3.047/M tokens | Output: 61.051 tok/s | MMLU: 0.841% | HumanEval: 0.767%
Quality: 24/100 | Price: $3.047/M tokens | Output: 58.576 tok/s | MMLU: 0.841% | HumanEval: 0.767%
Quality: 24/100 | Price: $3.047/M tokens | Output: 59.11 tok/s | MMLU: 0.841% | HumanEval: 0.767%
Quality: 24/100 | Price: $3.047/M tokens | Output: 59.128 tok/s | MMLU: 0.841% | HumanEval: 0.767%
Quality: 24/100 | Price: $3.047/M tokens | Output: 59.364 tok/s | MMLU: 0.841% | HumanEval: 0.767%
Quality: 24/100 | Price: $3.047/M tokens | Output: 59.364 tok/s | MMLU: 0.841% | HumanEval: 0.767%
Quality: 24/100 | Price: $3.047/M tokens | Output: 55.205 tok/s | MMLU: 0.841% | HumanEval: 0.767%
Quality: 24/100 | Price: $3.047/M tokens | Output: 51.993 tok/s | MMLU: 0.841% | HumanEval: 0.767%
Quality: 24/100 | Price: $3.047/M tokens | Output: 51.993 tok/s | MMLU: 0.841% | HumanEval: 0.767%
Quality: 24/100 | Price: $3.047/M tokens | Output: 53.114 tok/s | MMLU: 0.841% | HumanEval: 0.767%
Quality: 24/100 | Price: $3.047/M tokens | Output: 57.921 tok/s | MMLU: 0.841% | HumanEval: 0.767%
Quality: 24/100 | Price: $3.047/M tokens | Output: 58.764 tok/s | MMLU: 0.841% | HumanEval: 0.767%
Quality: 24/100 | Price: $3.047/M tokens | Output: 58.273 tok/s | MMLU: 0.841% | HumanEval: 0.767%
Quality: 24/100 | Price: $3.047/M tokens | Output: 57.299 tok/s | MMLU: 0.841% | HumanEval: 0.767%
Qwen3 Max is now available through local Ollama runtime. 40K context window listed. Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.