Compare/Apriel-v1.5-15B-Thinker vs gpt-oss-20B (high)

Apriel-v1.5-15B-Thinkervsgpt-oss-20B (high)

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

ServiceNow

Apriel-v1.5-15B-Thinker

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

gpt-oss-20B (high)

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

Winner by Category

Cheaper
Apriel-v1.5-15B-Thinker
Faster (tok/s)
gpt-oss-20B (high)
Lower Latency
Apriel-v1.5-15B-Thinker
Benchmarks (6-4)
Apriel-v1.5-15B-Thinker

Pricing Comparison

MetricApriel-v1.5-15B-Thinkergpt-oss-20B (high)
Input ($/M tokens)$0$0.05
Output ($/M tokens)$0$0.2
Cost for 1M input + 100K output tokens:
Apriel-v1.5-15B-Thinker$0.00
gpt-oss-20B (high)$0.07

Speed Comparison

Output Speed (tokens/s) — higher is better
Apriel-v1.5-15B-Thinker
gpt-oss-20B (high)
256 tok/s
Time to First Token (seconds) — lower is better
Apriel-v1.5-15B-Thinker
gpt-oss-20B (high)
0.34s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
28.324.5
Coding Index
18.718.5
Math Index
87.589.3
GPQA Diamond
71.3%68.8%
MMLU-Pro
77.3%74.8%
LiveCodeBench
72.8%77.7%
AIME 2025
87.5%89.3%
MATH-500
Humanity's Last Exam
12.0%9.8%
SciCode
34.8%34.4%
IFBench
61.7%65.1%
TerminalBench
10.6%10.6%
Apriel-v1.5-15B-Thinker6 wins
4 winsgpt-oss-20B (high)

Frequently Asked Questions

Which is cheaper, Apriel-v1.5-15B-Thinker or gpt-oss-20B (high)?

Apriel-v1.5-15B-Thinker is cheaper overall. Its blended price (3:1 input/output ratio) is $0.00/M tokens vs $0.09/M for gpt-oss-20B (high).

Which model performs better on benchmarks?

Apriel-v1.5-15B-Thinker wins 6 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?

gpt-oss-20B (high) generates tokens faster at 256 tok/s vs 0 tok/s. Apriel-v1.5-15B-Thinker also has lower time-to-first-token (0.00s vs 0.34s).

When should I use Apriel-v1.5-15B-Thinker vs gpt-oss-20B (high)?

Choose based on your priorities: Apriel-v1.5-15B-Thinker for lower cost, Apriel-v1.5-15B-Thinker for stronger benchmark performance, and gpt-oss-20B (high) for faster generation. For latency-sensitive apps, check the TTFT comparison above.