Compare/Apertus 8B Instruct vs gpt-oss-20B (high)

Apertus 8B Instructvsgpt-oss-20B (high)

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

Swiss AI Initiative

Apertus 8B Instruct

Input
$0.1/M
Output
$0.2/M
Speed
140 tok/s
TTFT
1.77s
OpenAI

gpt-oss-20B (high)

Input
$0.06/M
Output
$0.2/M
Speed
316 tok/s
TTFT
0.41s

Winner by Category

Cheaper
gpt-oss-20B (high)
Faster (tok/s)
gpt-oss-20B (high)
Lower Latency
gpt-oss-20B (high)
Benchmarks (0-11)
gpt-oss-20B (high)

Pricing Comparison

MetricApertus 8B Instructgpt-oss-20B (high)
Input ($/M tokens)$0.1$0.06
Output ($/M tokens)$0.2$0.2
Cost for 1M input + 100K output tokens:
Apertus 8B Instruct$0.12
gpt-oss-20B (high)$0.08

Speed Comparison

Output Speed (tokens/s) — higher is better
Apertus 8B Instruct
140 tok/s
gpt-oss-20B (high)
316 tok/s
Time to First Token (seconds) — lower is better
Apertus 8B Instruct
1.77s
gpt-oss-20B (high)
0.41s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
5.924.5
Coding Index
1.418.5
Math Index
89.3
GPQA Diamond
25.6%68.8%
MMLU-Pro
74.8%
LiveCodeBench
77.7%
AIME 2025
89.3%
MATH-500
Humanity's Last Exam
5.0%9.8%
SciCode
4.1%34.4%
IFBench
22.4%65.1%
TerminalBench
0.0%10.6%
Apertus 8B Instruct0 wins
11 winsgpt-oss-20B (high)

Frequently Asked Questions

Which is cheaper, Apertus 8B Instruct or gpt-oss-20B (high)?

gpt-oss-20B (high) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.09/M tokens vs $0.13/M for Apertus 8B Instruct.

Which model performs better on benchmarks?

gpt-oss-20B (high) wins 11 out of 12 benchmarks compared to 0 for Apertus 8B Instruct. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

gpt-oss-20B (high) generates tokens faster at 316 tok/s vs 140 tok/s. However, gpt-oss-20B (high) has lower time-to-first-token (0.41s vs 1.77s).

When should I use Apertus 8B Instruct vs gpt-oss-20B (high)?

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