BenchmarksAlibabaToday
QwQ 32B Benchmark Update
Quality: 19.7/100 | Price: $0.745/M tokens | Output: 30.904 tok/s | MMLU: 0.764% | HumanEval: 0.631%
View sourceQwen
QwQ is the reasoning model of the Qwen series. Compared with conventional instruction-tuned models, QwQ, which is capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks,...
Running this yourself: likely needs a rented cloud gpu.
64.1
Quality Score
1332
Arena ELO
32B
Parameters
131K
Context
Sign in to join the discussion
0
Downloads
0
Likes
Mar 2025
Released
Benchmarks
20
Recent launch, pricing, benchmark, and API signals linked to this model or its provider.
Quality: 19.7/100 | Price: $0.745/M tokens | Output: 30.904 tok/s | MMLU: 0.764% | HumanEval: 0.631%
View sourcelanguage: 0.7 | coding: 1.0 | instruction_following: 1.0 | Overall: 0.9
View sourceArena-Hard-Auto official Gemini-2.5 judged score 43.5 with CI -2.5/2.1
View sourceQuality: 19.7/100 | Price: $0.745/M tokens | Output: 30.951 tok/s | MMLU: 0.764% | HumanEval: 0.631%
View sourcelanguage: 0.7 | coding: 1.0 | instruction_following: 1.0 | Overall: 0.9
View sourceQuality: 19.7/100 | Price: $0.745/M tokens | Output: 30.904 tok/s | MMLU: 0.764% | HumanEval: 0.631%
language: 0.7 | coding: 1.0 | instruction_following: 1.0 | Overall: 0.9
Quality: 19.7/100 | Price: $0.745/M tokens | Output: 30.951 tok/s | MMLU: 0.764% | HumanEval: 0.631%
Quality: 19.7/100 | Price: $0.745/M tokens | Output: 31.611 tok/s | MMLU: 0.764% | HumanEval: 0.631%
Quality: 19.7/100 | Price: $0.745/M tokens | Output: 31.659 tok/s | MMLU: 0.764% | HumanEval: 0.631%
Quality: 19.7/100 | Price: $0.745/M tokens | Output: 31.135 tok/s | MMLU: 0.764% | HumanEval: 0.631%
Quality: 19.7/100 | Price: $0.745/M tokens | Output: 31.599 tok/s | MMLU: 0.764% | HumanEval: 0.631%
Quality: 19.7/100 | Price: $0.745/M tokens | Output: 31.599 tok/s | MMLU: 0.764% | HumanEval: 0.631%
Quality: 19.7/100 | Price: $0.745/M tokens | Output: 30.709 tok/s | MMLU: 0.764% | HumanEval: 0.631%
Arena-Hard-Auto official Gemini-2.5 judged score 43.5 with CI -2.5/2.1
language: 0.7 | coding: 1.0 | instruction_following: 1.0 | Overall: 0.9
language: 0.7 | coding: 1.0 | instruction_following: 1.0 | Overall: 0.9
language: 0.7 | coding: 1.0 | instruction_following: 1.0 | Overall: 0.9
language: 0.7 | coding: 1.0 | instruction_following: 1.0 | Overall: 0.9
language: 0.7 | coding: 1.0 | instruction_following: 1.0 | Overall: 0.9
language: 0.7 | coding: 1.0 | instruction_following: 1.0 | Overall: 0.9
language: 0.7 | coding: 1.0 | instruction_following: 1.0 | Overall: 0.9
language: 0.7 | coding: 1.0 | instruction_following: 1.0 | Overall: 0.9
language: 0.7 | coding: 1.0 | instruction_following: 1.0 | Overall: 0.9
language: 0.7 | coding: 1.0 | instruction_following: 1.0 | Overall: 0.9