Compare/JT-MINI vs GPT-5.3 Codex (xhigh)

JT-MINIvsGPT-5.3 Codex (xhigh)

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

China Mobile

JT-MINI

Input
$0/M
Output
$0/M
Speed
TTFT
OpenAI

GPT-5.3 Codex (xhigh)

Input
$1.75/M
Output
$14/M
Speed
103 tok/s
TTFT
57.95s

Winner by Category

Cheaper
JT-MINI
Faster (tok/s)
GPT-5.3 Codex (xhigh)
Lower Latency
JT-MINI
Benchmarks (0-6)
GPT-5.3 Codex (xhigh)

Pricing Comparison

MetricJT-MINIGPT-5.3 Codex (xhigh)
Input ($/M tokens)$0$1.75
Output ($/M tokens)$0$14
Cost for 1M input + 100K output tokens:
JT-MINI$0.00
GPT-5.3 Codex (xhigh)$3.15

Speed Comparison

Output Speed (tokens/s) — higher is better
JT-MINI
GPT-5.3 Codex (xhigh)
103 tok/s
Time to First Token (seconds) — lower is better
JT-MINI
GPT-5.3 Codex (xhigh)
57.95s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
18.544.3
Coding Index
Math Index
GPQA Diamond
67.6%91.5%
MMLU-Pro
LiveCodeBench
AIME 2025
MATH-500
Humanity's Last Exam
6.6%39.9%
SciCode
27.2%53.2%
IFBench
36.7%75.4%
TerminalBench
18.2%53.0%
JT-MINI0 wins
6 winsGPT-5.3 Codex (xhigh)

Frequently Asked Questions

Which is cheaper, JT-MINI or GPT-5.3 Codex (xhigh)?

JT-MINI is cheaper overall. Its blended price (3:1 input/output ratio) is $0.00/M tokens vs $4.81/M for GPT-5.3 Codex (xhigh).

Which model performs better on benchmarks?

GPT-5.3 Codex (xhigh) wins 6 out of 12 benchmarks compared to 0 for JT-MINI. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

GPT-5.3 Codex (xhigh) generates tokens faster at 103 tok/s vs 0 tok/s. JT-MINI also has lower time-to-first-token (0.00s vs 57.95s).

When should I use JT-MINI vs GPT-5.3 Codex (xhigh)?

Choose based on your priorities: JT-MINI for lower cost, GPT-5.3 Codex (xhigh) for stronger benchmark performance, and GPT-5.3 Codex (xhigh) for faster generation. For latency-sensitive apps, check the TTFT comparison above.