Compare/Mistral Small (Feb '24) vs Kimi K2.5 (Non-reasoning)

Mistral Small (Feb '24)vsKimi K2.5 (Non-reasoning)

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

Mistral

Mistral Small (Feb '24)

Input
$1/M
Output
$3/M
Speed
174 tok/s
TTFT
0.41s
Kimi

Kimi K2.5 (Non-reasoning)

Input
$0.6/M
Output
$3/M
Speed
33 tok/s
TTFT
1.40s

Winner by Category

Cheaper
Kimi K2.5 (Non-reasoning)
Faster (tok/s)
Mistral Small (Feb '24)
Lower Latency
Mistral Small (Feb '24)
Benchmarks (3-7)
Kimi K2.5 (Non-reasoning)

Pricing Comparison

MetricMistral Small (Feb '24)Kimi K2.5 (Non-reasoning)
Input ($/M tokens)$1$0.6
Output ($/M tokens)$3$3
Cost for 1M input + 100K output tokens:
Mistral Small (Feb '24)$1.30
Kimi K2.5 (Non-reasoning)$0.90

Speed Comparison

Output Speed (tokens/s) — higher is better
Mistral Small (Feb '24)
174 tok/s
Kimi K2.5 (Non-reasoning)
33 tok/s
Time to First Token (seconds) — lower is better
Mistral Small (Feb '24)
0.41s
Kimi K2.5 (Non-reasoning)
1.40s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
9.037.3
Coding Index
25.8
Math Index
GPQA Diamond
30.2%78.9%
MMLU-Pro
41.9%
LiveCodeBench
11.1%
AIME 2025
MATH-500
56.2%
Humanity's Last Exam
4.4%12.3%
SciCode
13.4%39.6%
IFBench
43.7%
TerminalBench
18.9%
Mistral Small (Feb '24)3 wins
7 winsKimi K2.5 (Non-reasoning)

Frequently Asked Questions

Which is cheaper, Mistral Small (Feb '24) or Kimi K2.5 (Non-reasoning)?

Kimi K2.5 (Non-reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $1.20/M tokens vs $1.50/M for Mistral Small (Feb '24).

Which model performs better on benchmarks?

Kimi K2.5 (Non-reasoning) wins 7 out of 12 benchmarks compared to 3 for Mistral Small (Feb '24). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Mistral Small (Feb '24) generates tokens faster at 174 tok/s vs 33 tok/s. Mistral Small (Feb '24) also has lower time-to-first-token (0.41s vs 1.40s).

When should I use Mistral Small (Feb '24) vs Kimi K2.5 (Non-reasoning)?

Choose based on your priorities: Kimi K2.5 (Non-reasoning) for lower cost, Kimi K2.5 (Non-reasoning) for stronger benchmark performance, and Mistral Small (Feb '24) for faster generation. For latency-sensitive apps, check the TTFT comparison above.