Compare/DeepSeek R1 0528 (May '25) vs Kimi K2.6 (Non-reasoning)

DeepSeek R1 0528 (May '25)vsKimi K2.6 (Non-reasoning)

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

DeepSeek

DeepSeek R1 0528 (May '25)

Input
$1.35/M
Output
$4.2/M
Speed
TTFT
Kimi

Kimi K2.6 (Non-reasoning)

Input
$0.95/M
Output
$4/M
Speed
43 tok/s
TTFT
1.29s

Winner by Category

Cheaper
Kimi K2.6 (Non-reasoning)
Faster (tok/s)
Kimi K2.6 (Non-reasoning)
Lower Latency
DeepSeek R1 0528 (May '25)
Benchmarks (7-5)
DeepSeek R1 0528 (May '25)

Pricing Comparison

MetricDeepSeek R1 0528 (May '25)Kimi K2.6 (Non-reasoning)
Input ($/M tokens)$1.35$0.95
Output ($/M tokens)$4.2$4
Cost for 1M input + 100K output tokens:
DeepSeek R1 0528 (May '25)$1.77
Kimi K2.6 (Non-reasoning)$1.35

Speed Comparison

Output Speed (tokens/s) — higher is better
DeepSeek R1 0528 (May '25)
Kimi K2.6 (Non-reasoning)
43 tok/s
Time to First Token (seconds) — lower is better
DeepSeek R1 0528 (May '25)
Kimi K2.6 (Non-reasoning)
1.29s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
27.142.9
Coding Index
24.038.4
Math Index
76.0
GPQA Diamond
81.3%78.8%
MMLU-Pro
84.9%
LiveCodeBench
77.0%
AIME 2025
76.0%
MATH-500
98.3%
Humanity's Last Exam
14.9%18.2%
SciCode
40.3%39.5%
IFBench
39.6%44.3%
TerminalBench
15.9%37.9%
DeepSeek R1 0528 (May '25)7 wins
5 winsKimi K2.6 (Non-reasoning)

Frequently Asked Questions

Which is cheaper, DeepSeek R1 0528 (May '25) or Kimi K2.6 (Non-reasoning)?

Kimi K2.6 (Non-reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $1.71/M tokens vs $2.06/M for DeepSeek R1 0528 (May '25).

Which model performs better on benchmarks?

DeepSeek R1 0528 (May '25) wins 7 out of 12 benchmarks compared to 5 for Kimi K2.6 (Non-reasoning). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Kimi K2.6 (Non-reasoning) generates tokens faster at 43 tok/s vs 0 tok/s. DeepSeek R1 0528 (May '25) also has lower time-to-first-token (0.00s vs 1.29s).

When should I use DeepSeek R1 0528 (May '25) vs Kimi K2.6 (Non-reasoning)?

Choose based on your priorities: Kimi K2.6 (Non-reasoning) for lower cost, DeepSeek R1 0528 (May '25) for stronger benchmark performance, and Kimi K2.6 (Non-reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.