Qwen3 235B A22B 2507 Instruct
AlibabaQwenOpen WeightApache 2.0 · Commercial OK
Description
Qwen3-235B-A22B-Instruct-2507 is the updated instruct version of Qwen3-235B-A22B featuring significant improvements in general capabilities including instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage. It provides substantial gains in long-tail knowledge coverage across multiple languages and markedly better alignment with user preferences in subjective and open-ended tasks.
Release Date
2025-07-21
Parameters
235.0B
Context Length
262K
Modalities
text
Capability Radar
70
general
60
coding
70
reasoning
68
scienceest.
60
agents
0
multimodal
Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.
Rankings
No ranking data available
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))Chat
IFEvalGoogle Research (2023)
88.7%SR
Multi-IF
77.5%SR
Tau2 Airline
44.0%SR
Communication
Tau2 Retail
71.3%SR
Creativity
Creative Writing v3
87.5%SR
Factuality
SimpleQA
54.3%SR
General
MultiPL-E
87.9%SR
CSimpleQA
84.3%SR
Include
79.5%SR
Arena-Hard v2
79.2%SR
BFCL-v3
70.9%SR
Aider-Polyglot
57.3%SR
Language
MMLU-Redux
93.1%SR
MMLU-Pro
83.0%SR
MMLU-ProX
79.4%SR
Math
LiveBench 20241125
75.4%SR
AIME 2025
70.3%SR
HMMT25
55.4%SR
PolyMATH
50.2%SR
Reasoning
ZebraLogic
95.0%SR
GPQANYU + Cohere + Anthropic (2023)
77.5%SR
SuperGPQA
62.6%SR
LiveCodeBench v6
51.8%SR
ARC-AGI
41.8%SR
Writing
WritingBench
85.2%SR
AA Evaluation Indices
(Artificial Analysis)No AA evaluation data available
LLM Stats Category Scores
(LLM Stats (zeroeval))Instruction Following80
Language80
Legal80
Structured Output80
Finance80
Healthcare80
Biology80
Creativity80
Writing80
Chat70
Math70
Physics70
Reasoning70
General70
Agents70
Chemistry70
Communication70
Code60
Economics60
Tool Calling60
Multimodal50
Spatial Reasoning50
Factuality50
Vision50
Pricing
Input Price$0.22 / 1M tokens
Output Price$0.88 / 1M tokens
Blended Price (3:1)$0.205 / 1M tokens
Cache Read Price$0.05 / 1M tokens
Speed
Tokens/sec43.4
Time to First Token1.17s
Time to Answer1.17s
Provider Price Ranking
Provider Price Ranking
8 providers
Cheapest: DeepInfraMost Expensive: GreenPT
ProviderInputOutput
1DeepInfraCheapest
$0.09
$0.55
2Venice AI
$0.15
$0.75
3Cortecs
$0.199
$0.598
4AlibabaPRIMARY
$0.22
$0.88
5Qiniu
$0.28986
$1.15942
6302.AI
$0.29
$1.143
7Scaleway
$0.84113
$2.52338
8GreenPT
$1.026
$3.078
Compare pricing across different API providers for this model.