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

gpt-oss-20B (low)vsApertus 8B Instruct

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

OpenAI

gpt-oss-20B (low)

Input
$0.06/M
Output
$0.2/M
Speed
321 tok/s
TTFT
0.46s
Swiss AI Initiative

Apertus 8B Instruct

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

Winner by Category

Cheaper
gpt-oss-20B (low)
Faster (tok/s)
gpt-oss-20B (low)
Lower Latency
gpt-oss-20B (low)
Benchmarks (10-0)
gpt-oss-20B (low)

Pricing Comparison

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

Speed Comparison

Output Speed (tokens/s) — higher is better
gpt-oss-20B (low)
321 tok/s
Apertus 8B Instruct
140 tok/s
Time to First Token (seconds) — lower is better
gpt-oss-20B (low)
0.46s
Apertus 8B Instruct
1.77s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
20.85.9
Coding Index
14.41.4
Math Index
62.3
GPQA Diamond
61.1%25.6%
MMLU-Pro
71.8%
LiveCodeBench
65.2%
AIME 2025
62.3%
MATH-500
Humanity's Last Exam
5.1%5.0%
SciCode
34.0%4.1%
IFBench
57.8%22.4%
TerminalBench
4.5%0.0%
gpt-oss-20B (low)10 wins
0 winsApertus 8B Instruct

Frequently Asked Questions

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

gpt-oss-20B (low) 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 (low) wins 10 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 (low) generates tokens faster at 321 tok/s vs 140 tok/s. gpt-oss-20B (low) also has lower time-to-first-token (0.46s vs 1.77s).

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

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