Qwen3 30B A3B
Zero-eval
#3Multi-IF
by Alibaba
About
Qwen3 30B A3B is a language model developed by Alibaba. It achieves strong performance with an average score of 73.3% across 8 benchmarks. It excels particularly in Arena Hard (91.0%), AIME 2024 (80.4%), LiveBench (74.3%). It supports a 256K token context window for handling large documents. The model is available through 3 API providers. It's licensed for commercial use, making it suitable for enterprise applications. Released in 2025, it represents Alibaba's latest advancement in AI technology.
Pricing Range
Input (per 1M)$0.10 -$0.89
Output (per 1M)$0.30 -$0.89
Providers3
Timeline
AnnouncedApr 29, 2025
ReleasedApr 29, 2025
Specifications
Training Tokens36.0T
License & Family
License
Apache 2.0
Benchmark Performance Overview
Performance metrics and category breakdown
Overall Performance
8 benchmarks
Average Score
73.3%
Best Score
91.0%
High Performers (80%+)
2Performance Metrics
Max Context Window
256.0KAvg Throughput
97.9 tok/sAvg Latency
1msTop Categories
general
74.9%
roleplay
74.3%
code
62.6%
Benchmark Performance
Top benchmark scores with normalized values (0-100%)
Ranking Across Benchmarks
Position relative to other models on each benchmark
Arena Hard
Rank #4 of 22
#1DeepSeek-R1
92.3%
#2Qwen3 32B
93.8%
#3Qwen3 235B A22B
95.6%
#4Qwen3 30B A3B
91.0%
#5Llama-3.3 Nemotron Super 49B v1
88.3%
#6Mistral Small 3 24B Instruct
87.6%
#7Qwen2.5 72B Instruct
81.2%
AIME 2024
Rank #19 of 41
#16Granite 3.3 8B Base
81.2%
#17Granite 3.3 8B Instruct
81.2%
#18Phi 4 Reasoning Plus
81.3%
#19Qwen3 30B A3B
80.4%
#20DeepSeek R1 Distill Qwen 14B
80.0%
#21DeepSeek R1 Distill Llama 8B
80.0%
#22Claude 3.7 Sonnet
80.0%
LiveBench
Rank #5 of 12
#2Qwen3 32B
74.9%
#3Kimi K2 Instruct
76.4%
#4Qwen3 235B A22B
77.1%
#5Qwen3 30B A3B
74.3%
#6QwQ-32B
73.1%
#7o1
67.0%
#8o1-preview
52.3%
Multi-IF
Rank #3 of 8
#1Qwen3-235B-A22B-Instruct-2507
77.5%
#2o3-mini
79.5%
#3Qwen3 30B A3B
72.2%
#4GPT-4.1
70.8%
#5GPT-4.5
70.8%
#6GPT-4.1 mini
67.0%
AIME 2025
Rank #20 of 36
#17Gemini 2.5 Flash
72.0%
#18Llama 3.1 Nemotron Ultra 253B v1
72.5%
#19Qwen3 32B
72.9%
#20Qwen3 30B A3B
70.9%
#21Claude Sonnet 4
70.5%
#22Magistral Medium
64.9%
#23Phi 4 Reasoning
62.9%
All Benchmark Results for Qwen3 30B A3B
Complete list of benchmark scores with detailed information
Arena Hard Arena Hard benchmark | general | text | 0.91 | 91.0% | Self-reported |
AIME 2024 AIME 2024 benchmark | general | text | 0.80 | 80.4% | Self-reported |
LiveBench LiveBench benchmark | roleplay | text | 0.74 | 74.3% | Self-reported |
Multi-IF Multi-IF benchmark | general | text | 0.72 | 72.2% | Self-reported |
AIME 2025 AIME 2025 benchmark | general | text | 0.71 | 70.9% | Self-reported |
BFCL BFCL benchmark | general | text | 0.69 | 69.1% | Self-reported |
GPQA GPQA benchmark | general | text | 0.66 | 65.8% | Self-reported |
LiveCodeBench LiveCodeBench benchmark | code | text | 0.63 | 62.6% | Self-reported |