Compare/GPT-5 Codex (high) vs Mercury 2

GPT-5 Codex (high)vsMercury 2

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

OpenAI

GPT-5 Codex (high)

Input
$1.25/M
Output
$10/M
Speed
216 tok/s
TTFT
12.05s
Inception

Mercury 2

Input
$0.25/M
Output
$0.75/M
Speed
907 tok/s
TTFT
3.76s

Winner by Category

Cheaper
Mercury 2
Faster (tok/s)
Mercury 2
Lower Latency
Mercury 2
Benchmarks (11-0)
GPT-5 Codex (high)

Pricing Comparison

MetricGPT-5 Codex (high)Mercury 2
Input ($/M tokens)$1.25$0.25
Output ($/M tokens)$10$0.75
Cost for 1M input + 100K output tokens:
GPT-5 Codex (high)$2.25
Mercury 2$0.33

Speed Comparison

Output Speed (tokens/s) — higher is better
GPT-5 Codex (high)
216 tok/s
Mercury 2
907 tok/s
Time to First Token (seconds) — lower is better
GPT-5 Codex (high)
12.05s
Mercury 2
3.76s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
44.632.8
Coding Index
38.930.6
Math Index
98.7
GPQA Diamond
83.7%77.0%
MMLU-Pro
86.5%
LiveCodeBench
84.0%
AIME 2025
98.7%
MATH-500
Humanity's Last Exam
25.6%15.5%
SciCode
40.9%38.7%
IFBench
74.1%69.8%
TerminalBench
37.9%26.5%
GPT-5 Codex (high)11 wins
0 winsMercury 2

Frequently Asked Questions

Which is cheaper, GPT-5 Codex (high) or Mercury 2?

Mercury 2 is cheaper overall. Its blended price (3:1 input/output ratio) is $0.38/M tokens vs $3.44/M for GPT-5 Codex (high).

Which model performs better on benchmarks?

GPT-5 Codex (high) wins 11 out of 12 benchmarks compared to 0 for Mercury 2. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Mercury 2 generates tokens faster at 907 tok/s vs 216 tok/s. However, Mercury 2 has lower time-to-first-token (3.76s vs 12.05s).

When should I use GPT-5 Codex (high) vs Mercury 2?

Choose based on your priorities: Mercury 2 for lower cost, GPT-5 Codex (high) for stronger benchmark performance, and Mercury 2 for faster generation. For latency-sensitive apps, check the TTFT comparison above.