Compare/GLM-4.6 (Reasoning) vs Kimi K2 0905

GLM-4.6 (Reasoning)vsKimi K2 0905

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

Z AI

GLM-4.6 (Reasoning)

Input
$0.575/M
Output
$2.2/M
Speed
84 tok/s
TTFT
0.67s
Kimi

Kimi K2 0905

Input
$0.8/M
Output
$2.25/M
Speed
63 tok/s
TTFT
0.78s

Winner by Category

Cheaper
GLM-4.6 (Reasoning)
Faster (tok/s)
GLM-4.6 (Reasoning)
Lower Latency
GLM-4.6 (Reasoning)
Benchmarks (11-0)
GLM-4.6 (Reasoning)

Pricing Comparison

MetricGLM-4.6 (Reasoning)Kimi K2 0905
Input ($/M tokens)$0.575$0.8
Output ($/M tokens)$2.2$2.25
Cost for 1M input + 100K output tokens:
GLM-4.6 (Reasoning)$0.79
Kimi K2 0905$1.03

Speed Comparison

Output Speed (tokens/s) — higher is better
GLM-4.6 (Reasoning)
84 tok/s
Kimi K2 0905
63 tok/s
Time to First Token (seconds) — lower is better
GLM-4.6 (Reasoning)
0.67s
Kimi K2 0905
0.78s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
32.530.9
Coding Index
29.525.9
Math Index
86.057.3
GPQA Diamond
78.0%76.7%
MMLU-Pro
82.9%81.9%
LiveCodeBench
69.5%61.0%
AIME 2025
86.0%57.3%
MATH-500
Humanity's Last Exam
13.3%6.3%
SciCode
38.4%30.7%
IFBench
43.4%41.7%
TerminalBench
25.0%23.5%
GLM-4.6 (Reasoning)11 wins
0 winsKimi K2 0905

Frequently Asked Questions

Which is cheaper, GLM-4.6 (Reasoning) or Kimi K2 0905?

GLM-4.6 (Reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.98/M tokens vs $1.14/M for Kimi K2 0905.

Which model performs better on benchmarks?

GLM-4.6 (Reasoning) wins 11 out of 12 benchmarks compared to 0 for Kimi K2 0905. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

GLM-4.6 (Reasoning) generates tokens faster at 84 tok/s vs 63 tok/s. GLM-4.6 (Reasoning) also has lower time-to-first-token (0.67s vs 0.78s).

When should I use GLM-4.6 (Reasoning) vs Kimi K2 0905?

Choose based on your priorities: GLM-4.6 (Reasoning) for lower cost, GLM-4.6 (Reasoning) for stronger benchmark performance, and GLM-4.6 (Reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.