Compare/gpt-oss-20B (high) vs Mercury 2

gpt-oss-20B (high)vsMercury 2

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

OpenAI

gpt-oss-20B (high)

Input
$0.05/M
Output
$0.2/M
Speed
256 tok/s
TTFT
0.34s
Inception

Mercury 2

Input
$0.25/M
Output
$0.75/M
Speed
743 tok/s
TTFT
3.75s

Winner by Category

Cheaper
gpt-oss-20B (high)
Faster (tok/s)
Mercury 2
Lower Latency
gpt-oss-20B (high)
Benchmarks (4-7)
Mercury 2

Pricing Comparison

Metricgpt-oss-20B (high)Mercury 2
Input ($/M tokens)$0.05$0.25
Output ($/M tokens)$0.2$0.75
Cost for 1M input + 100K output tokens:
gpt-oss-20B (high)$0.07
Mercury 2$0.33

Speed Comparison

Output Speed (tokens/s) — higher is better
gpt-oss-20B (high)
256 tok/s
Mercury 2
743 tok/s
Time to First Token (seconds) — lower is better
gpt-oss-20B (high)
0.34s
Mercury 2
3.75s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
24.532.8
Coding Index
18.530.6
Math Index
89.3
GPQA Diamond
68.8%77.0%
MMLU-Pro
74.8%
LiveCodeBench
77.7%
AIME 2025
89.3%
MATH-500
Humanity's Last Exam
9.8%15.5%
SciCode
34.4%38.7%
IFBench
65.1%69.8%
TerminalBench
10.6%26.5%
gpt-oss-20B (high)4 wins
7 winsMercury 2

Frequently Asked Questions

Which is cheaper, gpt-oss-20B (high) or Mercury 2?

gpt-oss-20B (high) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.09/M tokens vs $0.38/M for Mercury 2.

Which model performs better on benchmarks?

Mercury 2 wins 7 out of 12 benchmarks compared to 4 for gpt-oss-20B (high). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Mercury 2 generates tokens faster at 743 tok/s vs 256 tok/s. gpt-oss-20B (high) also has lower time-to-first-token (0.34s vs 3.75s).

When should I use gpt-oss-20B (high) vs Mercury 2?

Choose based on your priorities: gpt-oss-20B (high) for lower cost, Mercury 2 for stronger benchmark performance, and Mercury 2 for faster generation. For latency-sensitive apps, check the TTFT comparison above.