Compare/Qwen3 VL 30B A3B Instruct vs Mercury 2

Qwen3 VL 30B A3B InstructvsMercury 2

Side-by-side comparison of pricing, 12 benchmarks, and generation speed.

Alibaba

Qwen3 VL 30B A3B Instruct

Input
$0.2/M
Output
$0.8/M
Speed
129 tok/s
TTFT
0.96s
Inception

Mercury 2

Input
$0.25/M
Output
$0.75/M
Speed
907 tok/s
TTFT
3.76s

Winner by Category

Cheaper
Qwen3 VL 30B A3B Instruct
Faster (tok/s)
Mercury 2
Lower Latency
Qwen3 VL 30B A3B Instruct
Benchmarks (4-7)
Mercury 2

Pricing Comparison

MetricQwen3 VL 30B A3B InstructMercury 2
Input ($/M tokens)$0.2$0.25
Output ($/M tokens)$0.8$0.75
Cost for 1M input + 100K output tokens:
Qwen3 VL 30B A3B Instruct$0.28
Mercury 2$0.33

Speed Comparison

Output Speed (tokens/s) — higher is better
Qwen3 VL 30B A3B Instruct
129 tok/s
Mercury 2
907 tok/s
Time to First Token (seconds) — lower is better
Qwen3 VL 30B A3B Instruct
0.96s
Mercury 2
3.76s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
16.132.8
Coding Index
14.330.6
Math Index
72.3
GPQA Diamond
69.5%77.0%
MMLU-Pro
76.4%
LiveCodeBench
47.6%
AIME 2025
72.3%
MATH-500
Humanity's Last Exam
6.4%15.5%
SciCode
30.8%38.7%
IFBench
33.1%69.8%
TerminalBench
6.1%26.5%
Qwen3 VL 30B A3B Instruct4 wins
7 winsMercury 2

Frequently Asked Questions

Which is cheaper, Qwen3 VL 30B A3B Instruct or Mercury 2?

Qwen3 VL 30B A3B Instruct is cheaper overall. Its blended price (3:1 input/output ratio) is $0.35/M tokens vs $0.38/M for Mercury 2.

Which model performs better on benchmarks?

Mercury 2 wins 7 out of 12 benchmarks compared to 4 for Qwen3 VL 30B A3B Instruct. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Mercury 2 generates tokens faster at 907 tok/s vs 129 tok/s. Qwen3 VL 30B A3B Instruct also has lower time-to-first-token (0.96s vs 3.76s).

When should I use Qwen3 VL 30B A3B Instruct vs Mercury 2?

Choose based on your priorities: Qwen3 VL 30B A3B Instruct for lower cost, Mercury 2 for stronger benchmark performance, and Mercury 2 for faster generation. For latency-sensitive apps, check the TTFT comparison above.