Compare/Qwen2.5 Instruct 72B vs Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)

Qwen2.5 Instruct 72BvsGemini 2.5 Flash-Lite Preview (Sep '25) (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
1.12s
Google

Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)

Input
$0.1/M
Output
$0.4/M
Speed
TTFT

Winner by Category

Cheaper
Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)
Faster (tok/s)
Qwen2.5 Instruct 72B
Lower Latency
Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)
Benchmarks (1-11)
Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)

Pricing Comparison

MetricQwen2.5 Instruct 72BGemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)
Input ($/M tokens)$0.36$0.1
Output ($/M tokens)$0.4$0.4
Cost for 1M input + 100K output tokens:
Qwen2.5 Instruct 72B$0.40
Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)$0.14

Speed Comparison

Output Speed (tokens/s) — higher is better
Qwen2.5 Instruct 72B
55 tok/s
Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)
Time to First Token (seconds) — lower is better
Qwen2.5 Instruct 72B
1.12s
Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
15.621.6
Coding Index
11.918.2
Math Index
14.068.7
GPQA Diamond
49.1%70.9%
MMLU-Pro
72.0%80.8%
LiveCodeBench
27.6%68.8%
AIME 2025
14.0%68.7%
MATH-500
85.8%
Humanity's Last Exam
4.2%6.6%
SciCode
26.7%28.7%
IFBench
36.9%52.6%
TerminalBench
4.5%12.9%
Qwen2.5 Instruct 72B1 wins
11 winsGemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)

Frequently Asked Questions

Which is cheaper, Qwen2.5 Instruct 72B or Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)?

Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.17/M tokens vs $0.37/M for Qwen2.5 Instruct 72B.

Which model performs better on benchmarks?

Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) wins 11 out of 12 benchmarks compared to 1 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 55 tok/s vs 0 tok/s. However, Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) has lower time-to-first-token (0.00s vs 1.12s).

When should I use Qwen2.5 Instruct 72B vs Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)?

Choose based on your priorities: Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) for lower cost, Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) for stronger benchmark performance, and Qwen2.5 Instruct 72B for faster generation. For latency-sensitive apps, check the TTFT comparison above.