Compare/Qwen2.5 Instruct 72B vs Gemma 4 26B A4B (Non-reasoning)

Qwen2.5 Instruct 72BvsGemma 4 26B A4B (Non-reasoning)

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

Alibaba

Qwen2.5 Instruct 72B

Input
$0.36/M
Output
$0.4/M
Speed
55 tok/s
TTFT
1.23s
Google

Gemma 4 26B A4B (Non-reasoning)

Input
$0.13/M
Output
$0.4/M
Speed
65 tok/s
TTFT
0.69s

Winner by Category

Cheaper
Gemma 4 26B A4B (Non-reasoning)
Faster (tok/s)
Gemma 4 26B A4B (Non-reasoning)
Lower Latency
Gemma 4 26B A4B (Non-reasoning)
Benchmarks (5-7)
Gemma 4 26B A4B (Non-reasoning)

Pricing Comparison

MetricQwen2.5 Instruct 72BGemma 4 26B A4B (Non-reasoning)
Input ($/M tokens)$0.36$0.13
Output ($/M tokens)$0.4$0.4
Cost for 1M input + 100K output tokens:
Qwen2.5 Instruct 72B$0.40
Gemma 4 26B A4B (Non-reasoning)$0.17

Speed Comparison

Output Speed (tokens/s) — higher is better
Qwen2.5 Instruct 72B
55 tok/s
Gemma 4 26B A4B (Non-reasoning)
65 tok/s
Time to First Token (seconds) — lower is better
Qwen2.5 Instruct 72B
1.23s
Gemma 4 26B A4B (Non-reasoning)
0.69s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
15.627.1
Coding Index
11.929.1
Math Index
14.0
GPQA Diamond
49.1%71.4%
MMLU-Pro
72.0%
LiveCodeBench
27.6%
AIME 2025
14.0%
MATH-500
85.8%
Humanity's Last Exam
4.2%10.7%
SciCode
26.7%37.3%
IFBench
36.9%45.4%
TerminalBench
4.5%25.0%
Qwen2.5 Instruct 72B5 wins
7 winsGemma 4 26B A4B (Non-reasoning)

Frequently Asked Questions

Which is cheaper, Qwen2.5 Instruct 72B or Gemma 4 26B A4B (Non-reasoning)?

Gemma 4 26B A4B (Non-reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.20/M tokens vs $0.37/M for Qwen2.5 Instruct 72B.

Which model performs better on benchmarks?

Gemma 4 26B A4B (Non-reasoning) wins 7 out of 12 benchmarks compared to 5 for Qwen2.5 Instruct 72B. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Gemma 4 26B A4B (Non-reasoning) generates tokens faster at 65 tok/s vs 55 tok/s. However, Gemma 4 26B A4B (Non-reasoning) has lower time-to-first-token (0.69s vs 1.23s).

When should I use Qwen2.5 Instruct 72B vs Gemma 4 26B A4B (Non-reasoning)?

Choose based on your priorities: Gemma 4 26B A4B (Non-reasoning) for lower cost, Gemma 4 26B A4B (Non-reasoning) for stronger benchmark performance, and Gemma 4 26B A4B (Non-reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.