Compare/Olmo 3.1 32B Think vs gpt-oss-20B (low)

Olmo 3.1 32B Thinkvsgpt-oss-20B (low)

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

Allen Institute for AI

Olmo 3.1 32B Think

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

gpt-oss-20B (low)

Input
$0.06/M
Output
$0.2/M
Speed
280 tok/s
TTFT
0.45s

Winner by Category

Cheaper
Olmo 3.1 32B Think
Faster (tok/s)
gpt-oss-20B (low)
Lower Latency
Olmo 3.1 32B Think
Benchmarks (6-5)
Olmo 3.1 32B Think

Pricing Comparison

MetricOlmo 3.1 32B Thinkgpt-oss-20B (low)
Input ($/M tokens)$0$0.06
Output ($/M tokens)$0$0.2
Cost for 1M input + 100K output tokens:
Olmo 3.1 32B Think$0.00
gpt-oss-20B (low)$0.08

Speed Comparison

Output Speed (tokens/s) — higher is better
Olmo 3.1 32B Think
gpt-oss-20B (low)
280 tok/s
Time to First Token (seconds) — lower is better
Olmo 3.1 32B Think
gpt-oss-20B (low)
0.45s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
13.920.8
Coding Index
9.814.4
Math Index
77.362.3
GPQA Diamond
59.1%61.1%
MMLU-Pro
76.3%71.8%
LiveCodeBench
69.5%65.2%
AIME 2025
77.3%62.3%
MATH-500
Humanity's Last Exam
6.0%5.1%
SciCode
29.3%34.0%
IFBench
66.0%57.8%
TerminalBench
0.0%4.5%
Olmo 3.1 32B Think6 wins
5 winsgpt-oss-20B (low)

Frequently Asked Questions

Which is cheaper, Olmo 3.1 32B Think or gpt-oss-20B (low)?

Olmo 3.1 32B Think is cheaper overall. Its blended price (3:1 input/output ratio) is $0.00/M tokens vs $0.10/M for gpt-oss-20B (low).

Which model performs better on benchmarks?

Olmo 3.1 32B Think wins 6 out of 12 benchmarks compared to 5 for gpt-oss-20B (low). 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 280 tok/s vs 0 tok/s. Olmo 3.1 32B Think also has lower time-to-first-token (0.00s vs 0.45s).

When should I use Olmo 3.1 32B Think vs gpt-oss-20B (low)?

Choose based on your priorities: Olmo 3.1 32B Think for lower cost, Olmo 3.1 32B Think for stronger benchmark performance, and gpt-oss-20B (low) for faster generation. For latency-sensitive apps, check the TTFT comparison above.