Compare/GLM-4.6V (Reasoning) vs Reka Flash 3

GLM-4.6V (Reasoning)vsReka Flash 3

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

Z AI

GLM-4.6V (Reasoning)

Input
$0.3/M
Output
$0.9/M
Speed
23 tok/s
TTFT
1.01s
Reka AI

Reka Flash 3

Input
$0.2/M
Output
$0.8/M
Speed
56 tok/s
TTFT
1.33s

Winner by Category

Cheaper
Reka Flash 3
Faster (tok/s)
Reka Flash 3
Lower Latency
GLM-4.6V (Reasoning)
Benchmarks (9-3)
GLM-4.6V (Reasoning)

Pricing Comparison

MetricGLM-4.6V (Reasoning)Reka Flash 3
Input ($/M tokens)$0.3$0.2
Output ($/M tokens)$0.9$0.8
Cost for 1M input + 100K output tokens:
GLM-4.6V (Reasoning)$0.39
Reka Flash 3$0.28

Speed Comparison

Output Speed (tokens/s) — higher is better
GLM-4.6V (Reasoning)
23 tok/s
Reka Flash 3
56 tok/s
Time to First Token (seconds) — lower is better
GLM-4.6V (Reasoning)
1.01s
Reka Flash 3
1.33s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
23.49.5
Coding Index
19.78.9
Math Index
85.333.7
GPQA Diamond
71.9%52.9%
MMLU-Pro
79.9%66.9%
LiveCodeBench
16.0%43.5%
AIME 2025
85.3%33.7%
MATH-500
89.3%
Humanity's Last Exam
8.9%5.1%
SciCode
30.4%26.7%
IFBench
30.1%30.4%
TerminalBench
14.4%0.0%
GLM-4.6V (Reasoning)9 wins
3 winsReka Flash 3

Frequently Asked Questions

Which is cheaper, GLM-4.6V (Reasoning) or Reka Flash 3?

Reka Flash 3 is cheaper overall. Its blended price (3:1 input/output ratio) is $0.35/M tokens vs $0.45/M for GLM-4.6V (Reasoning).

Which model performs better on benchmarks?

GLM-4.6V (Reasoning) wins 9 out of 12 benchmarks compared to 3 for Reka Flash 3. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Reka Flash 3 generates tokens faster at 56 tok/s vs 23 tok/s. GLM-4.6V (Reasoning) also has lower time-to-first-token (1.01s vs 1.33s).

When should I use GLM-4.6V (Reasoning) vs Reka Flash 3?

Choose based on your priorities: Reka Flash 3 for lower cost, GLM-4.6V (Reasoning) for stronger benchmark performance, and Reka Flash 3 for faster generation. For latency-sensitive apps, check the TTFT comparison above.