Compare/DeepSeek R1 0528 (May '25) vs GLM-5.1 (Non-reasoning)

DeepSeek R1 0528 (May '25)vsGLM-5.1 (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
Z AI

GLM-5.1 (Non-reasoning)

Input
$1.4/M
Output
$4.4/M
Speed
46 tok/s
TTFT
1.03s

Winner by Category

Cheaper
DeepSeek R1 0528 (May '25)
Faster (tok/s)
GLM-5.1 (Non-reasoning)
Lower Latency
DeepSeek R1 0528 (May '25)
Benchmarks (6-6)
Tie

Pricing Comparison

MetricDeepSeek R1 0528 (May '25)GLM-5.1 (Non-reasoning)
Input ($/M tokens)$1.35$1.4
Output ($/M tokens)$4.2$4.4
Cost for 1M input + 100K output tokens:
DeepSeek R1 0528 (May '25)$1.77
GLM-5.1 (Non-reasoning)$1.84

Speed Comparison

Output Speed (tokens/s) — higher is better
DeepSeek R1 0528 (May '25)
GLM-5.1 (Non-reasoning)
46 tok/s
Time to First Token (seconds) — lower is better
DeepSeek R1 0528 (May '25)
GLM-5.1 (Non-reasoning)
1.03s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
27.143.8
Coding Index
24.035.8
Math Index
76.0
GPQA Diamond
81.3%83.9%
MMLU-Pro
84.9%
LiveCodeBench
77.0%
AIME 2025
76.0%
MATH-500
98.3%
Humanity's Last Exam
14.9%25.6%
SciCode
40.3%36.1%
IFBench
39.6%52.0%
TerminalBench
15.9%35.6%
DeepSeek R1 0528 (May '25)6 wins
6 winsGLM-5.1 (Non-reasoning)

Frequently Asked Questions

Which is cheaper, DeepSeek R1 0528 (May '25) or GLM-5.1 (Non-reasoning)?

DeepSeek R1 0528 (May '25) is cheaper overall. Its blended price (3:1 input/output ratio) is $2.06/M tokens vs $2.15/M for GLM-5.1 (Non-reasoning).

Which model performs better on benchmarks?

It's a tie — both models win 6 benchmarks each across 12 evaluated categories. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

GLM-5.1 (Non-reasoning) generates tokens faster at 46 tok/s vs 0 tok/s. DeepSeek R1 0528 (May '25) also has lower time-to-first-token (0.00s vs 1.03s).

When should I use DeepSeek R1 0528 (May '25) vs GLM-5.1 (Non-reasoning)?

Choose based on your priorities: DeepSeek R1 0528 (May '25) for lower cost, both perform similarly on benchmarks, and GLM-5.1 (Non-reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.