Compare/Nova Pro vs Qwen3.5 122B A10B (Reasoning)

Nova ProvsQwen3.5 122B A10B (Reasoning)

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

Amazon

Nova Pro

Input
$0.8/M
Output
$3.2/M
Speed
TTFT
Alibaba

Qwen3.5 122B A10B (Reasoning)

Input
$0.4/M
Output
$3.2/M
Speed
135 tok/s
TTFT
1.02s

Winner by Category

Cheaper
Qwen3.5 122B A10B (Reasoning)
Faster (tok/s)
Qwen3.5 122B A10B (Reasoning)
Lower Latency
Nova Pro
Benchmarks (5-7)
Qwen3.5 122B A10B (Reasoning)

Pricing Comparison

MetricNova ProQwen3.5 122B A10B (Reasoning)
Input ($/M tokens)$0.8$0.4
Output ($/M tokens)$3.2$3.2
Cost for 1M input + 100K output tokens:
Nova Pro$1.12
Qwen3.5 122B A10B (Reasoning)$0.72

Speed Comparison

Output Speed (tokens/s) — higher is better
Nova Pro
Qwen3.5 122B A10B (Reasoning)
135 tok/s
Time to First Token (seconds) — lower is better
Nova Pro
Qwen3.5 122B A10B (Reasoning)
1.02s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
13.541.6
Coding Index
11.034.7
Math Index
7.0
GPQA Diamond
49.9%85.7%
MMLU-Pro
69.1%
LiveCodeBench
23.3%
AIME 2025
7.0%
MATH-500
78.6%
Humanity's Last Exam
3.4%23.4%
SciCode
20.8%42.0%
IFBench
38.1%75.7%
TerminalBench
6.1%31.1%
Nova Pro5 wins
7 winsQwen3.5 122B A10B (Reasoning)

Frequently Asked Questions

Which is cheaper, Nova Pro or Qwen3.5 122B A10B (Reasoning)?

Qwen3.5 122B A10B (Reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $1.10/M tokens vs $1.40/M for Nova Pro.

Which model performs better on benchmarks?

Qwen3.5 122B A10B (Reasoning) wins 7 out of 12 benchmarks compared to 5 for Nova Pro. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Qwen3.5 122B A10B (Reasoning) generates tokens faster at 135 tok/s vs 0 tok/s. Nova Pro also has lower time-to-first-token (0.00s vs 1.02s).

When should I use Nova Pro vs Qwen3.5 122B A10B (Reasoning)?

Choose based on your priorities: Qwen3.5 122B A10B (Reasoning) for lower cost, Qwen3.5 122B A10B (Reasoning) for stronger benchmark performance, and Qwen3.5 122B A10B (Reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.