Qwen3 235B A22B 2507 Instruct
AlibabaQwenOpen WeightApache 2.0 · Commercial OK
विवरण
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.
रिलीज़ तिथि
2025-07-21
पैरामीटर
235.0B
संदर्भ लंबाई
262K
मोडैलिटीज़
text
क्षमता रडार
40
general
34
coding
76
reasoning
49
scienceअनुमानित
60
agents
0
multimodal
समर्पित विज्ञान बेंचमार्क उपलब्ध न होने पर Science तर्क प्रॉक्सी का उपयोग करके अनुमान लगाता है।
रैंकिंग
| डोमेन | #रैंक | स्कोर | स्रोत |
|---|---|---|---|
| Agents & Tools | 13 | 71.0 | LS |
| Code Ranking | 218 | 39.0 | AA |
| General Ranking | 204 | 50.0 | AA |
| Math Reasoning | 96 | 78.0 | AA |
| Reasoning | 75 | 55.0 | LS |
| Science | 149 | 54.0 | AA |
बेंचमार्क स्कोर (LLM Stats)
Agents
BFCL-v3
70.9%स्वयं
Biology
GPQA
77.5%स्वयं
Chemistry
SuperGPQA
62.6%स्वयं
Code
Aider-Polyglot
57.3%स्वयं
Communication
WritingBench
85.2%स्वयं
Multi-IF
77.5%स्वयं
Tau2 Retail
71.3%स्वयं
Tau2 Airline
44.0%स्वयं
Creativity
Creative Writing v3
87.5%स्वयं
Arena-Hard v2
79.2%स्वयं
Factuality
SimpleQA
54.3%स्वयं
Finance
MMLU-Pro
83.0%स्वयं
MMLU-ProX
79.4%स्वयं
General
MMLU-Redux
93.1%स्वयं
IFEval
88.7%स्वयं
MultiPL-E
87.9%स्वयं
CSimpleQA
84.3%स्वयं
Include
79.5%स्वयं
LiveBench 20241125
75.4%स्वयं
LiveCodeBench v6
51.8%स्वयं
Math
AIME 2025
70.3%स्वयं
HMMT25
55.4%स्वयं
PolyMATH
50.2%स्वयं
Reasoning
ZebraLogic
95.0%स्वयं
ARC-AGI
41.8%स्वयं
AA मूल्यांकन सूचकांक
Math Index71.7
Intelligence Index25.0
Coding Index22.1
Math 5001.0
Mmlu Pro0.8
Gpqa0.8
Aime0.7
Aime 250.7
Livecodebench0.5
Ifbench0.5
Scicode0.4
Tau20.3
Lcr0.3
Terminalbench Hard0.2
Hle0.1
LLM Stats श्रेणी स्कोर
Structured Output80
Writing80
Biology80
Creativity80
Finance80
Healthcare80
Instruction Following80
Language80
Legal80
Agents70
Chemistry70
Communication70
General70
Math70
Physics70
Reasoning70
Tool Calling60
Code60
Economics60
Spatial Reasoning50
Vision50
Factuality50
Multimodal50
मूल्य निर्धारण
इनपुट मूल्य$0.2 / 1M tokens
आउटपुट मूल्य$0.825 / 1M tokens
मिश्रित मूल्य (3:1)$0.356 / 1M tokens
गति
टोकन/सेकंड67.8 tokens/s
पहले टोकन में देरी1.17s
पहले उत्तर में देरी1.17s
उपलब्ध प्रदाता
(LS आंतरिक इकाइयाँ)| प्रदाता | इनपुट मूल्य | आउटपुट मूल्य |
|---|---|---|
| Fireworks | 150K | 800K |