Compare/Kimi K2.5 (Reasoning) vs Gemini 3 Flash Preview (Non-reasoning)

Kimi K2.5 (Reasoning)vsGemini 3 Flash Preview (Non-reasoning)

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

Kimi

Kimi K2.5 (Reasoning)

Input
$0.6/M
Output
$3/M
Speed
39 tok/s
TTFT
1.28s
Google

Gemini 3 Flash Preview (Non-reasoning)

Input
$0.5/M
Output
$3/M
Speed
209 tok/s
TTFT
0.72s

Winner by Category

Cheaper
Gemini 3 Flash Preview (Non-reasoning)
Faster (tok/s)
Gemini 3 Flash Preview (Non-reasoning)
Lower Latency
Gemini 3 Flash Preview (Non-reasoning)
Benchmarks (5-5)
Tie

Pricing Comparison

MetricKimi K2.5 (Reasoning)Gemini 3 Flash Preview (Non-reasoning)
Input ($/M tokens)$0.6$0.5
Output ($/M tokens)$3$3
Cost for 1M input + 100K output tokens:
Kimi K2.5 (Reasoning)$0.90
Gemini 3 Flash Preview (Non-reasoning)$0.80

Speed Comparison

Output Speed (tokens/s) — higher is better
Kimi K2.5 (Reasoning)
39 tok/s
Gemini 3 Flash Preview (Non-reasoning)
209 tok/s
Time to First Token (seconds) — lower is better
Kimi K2.5 (Reasoning)
1.28s
Gemini 3 Flash Preview (Non-reasoning)
0.72s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
38.127.4
Coding Index
Math Index
55.7
GPQA Diamond
87.9%81.2%
MMLU-Pro
88.2%
LiveCodeBench
79.7%
AIME 2025
55.7%
MATH-500
Humanity's Last Exam
29.4%14.1%
SciCode
49.0%49.9%
IFBench
70.2%55.1%
TerminalBench
34.8%31.8%
Kimi K2.5 (Reasoning)5 wins
5 winsGemini 3 Flash Preview (Non-reasoning)

Frequently Asked Questions

Which is cheaper, Kimi K2.5 (Reasoning) or Gemini 3 Flash Preview (Non-reasoning)?

Gemini 3 Flash Preview (Non-reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $1.13/M tokens vs $1.20/M for Kimi K2.5 (Reasoning).

Which model performs better on benchmarks?

It's a tie — both models win 5 benchmarks each across 12 evaluated categories. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Gemini 3 Flash Preview (Non-reasoning) generates tokens faster at 209 tok/s vs 39 tok/s. However, Gemini 3 Flash Preview (Non-reasoning) has lower time-to-first-token (0.72s vs 1.28s).

When should I use Kimi K2.5 (Reasoning) vs Gemini 3 Flash Preview (Non-reasoning)?

Choose based on your priorities: Gemini 3 Flash Preview (Non-reasoning) for lower cost, both perform similarly on benchmarks, and Gemini 3 Flash Preview (Non-reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.