Qwen3 30B A3B (Reasoning) vs Qwen3 VL 30B A3B (Reasoning)
Comparing 2 AI models · 6 benchmarks · Alibaba
Most Affordable
Al
Qwen3 30B A3B (Reasoning)
$0.20/1M
Highest Intelligence
Al
Qwen3 VL 30B A3B (Reasoning)
72.0% GPQA
Best for Coding
Al
Qwen3 VL 30B A3B (Reasoning)
34.5 Coding Index
Price Difference
1.0x
input cost range
Composite Indices
Intelligence, Coding, Math
Standard Benchmarks
Academic and industry benchmarks
Benchmark Winners
6 tests
Al
Qwen3 30B A3B (Reasoning)
1
- MATH 500
Al
Qwen3 VL 30B A3B (Reasoning)
5
- GPQA
- MMLU Pro
- HLE
- LiveCodeBench
- AIME 2025
| Metric | Al Qwen3 30B A3B (Reasoning) | Al Qwen3 VL 30B A3B (Reasoning) |
|---|---|---|
| Pricing Per 1M tokens | ||
| Input Cost | $0.20/1M | $0.20/1M |
| Output Cost | $2.40/1M | $2.40/1M |
| Blended Cost 3:1 input/output ratio | $0.75/1M | $0.75/1M |
| Specifications | ||
| Organization Model creator | Alibaba | Alibaba |
| Release Date Launch date | Apr 28, 2025 | Oct 3, 2025 |
| Performance & Speed | ||
| Throughput Output speed | 77.4 tok/s | 104.5 tok/s |
| Time to First Token (TTFT) Initial response delay | 1141ms | 956ms |
| Latency Time to first answer token | 26994ms | 20090ms |
| Composite Indices | ||
| Intelligence Index Overall reasoning capability | 36.7 | 45.3 |
| Coding Index Programming ability | 27.1 | 34.5 |
| Math Index Mathematical reasoning | 72.3 | 82.3 |
| Standard Benchmarks | ||
| GPQA Graduate-level reasoning | 61.6% | 72.0% |
| MMLU Pro Advanced knowledge | 77.7% | 80.7% |
| HLE Hard language evaluation | 6.6% | 8.7% |
| LiveCodeBench Real-world coding tasks | 50.6% | 69.7% |
| MATH 500 Mathematical problems | 95.9% | — |
| AIME 2025 Advanced math competition | 72.3% | 82.3% |
| AIME (Original) Math olympiad problems | 75.3% | — |