Compare/Qwen2.5 Instruct 72B vs Gemma 4 26B A4B (Reasoning)

Qwen2.5 Instruct 72BvsGemma 4 26B A4B (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
56 tok/s
TTFT
1.06s
Google

Gemma 4 26B A4B (Reasoning)

Input
$0.13/M
Output
$0.4/M
Speed
TTFT

Winner by Category

Cheaper
Gemma 4 26B A4B (Reasoning)
Faster (tok/s)
Qwen2.5 Instruct 72B
Lower Latency
Gemma 4 26B A4B (Reasoning)
Benchmarks (5-7)
Gemma 4 26B A4B (Reasoning)

Pricing Comparison

MetricQwen2.5 Instruct 72BGemma 4 26B A4B (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 (Reasoning)$0.17

Speed Comparison

Output Speed (tokens/s) — higher is better
Qwen2.5 Instruct 72B
56 tok/s
Gemma 4 26B A4B (Reasoning)
Time to First Token (seconds) — lower is better
Qwen2.5 Instruct 72B
1.06s
Gemma 4 26B A4B (Reasoning)

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
15.631.2
Coding Index
11.922.4
Math Index
14.0
GPQA Diamond
49.1%79.2%
MMLU-Pro
72.0%
LiveCodeBench
27.6%
AIME 2025
14.0%
MATH-500
85.8%
Humanity's Last Exam
4.2%18.3%
SciCode
26.7%40.0%
IFBench
36.9%72.4%
TerminalBench
4.5%13.6%
Qwen2.5 Instruct 72B5 wins
7 winsGemma 4 26B A4B (Reasoning)

Frequently Asked Questions

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

Gemma 4 26B A4B (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 (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?

Qwen2.5 Instruct 72B generates tokens faster at 56 tok/s vs 0 tok/s. However, Gemma 4 26B A4B (Reasoning) has lower time-to-first-token (0.00s vs 1.06s).

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

Choose based on your priorities: Gemma 4 26B A4B (Reasoning) for lower cost, Gemma 4 26B A4B (Reasoning) for stronger benchmark performance, and Qwen2.5 Instruct 72B for faster generation. For latency-sensitive apps, check the TTFT comparison above.