Compare/Granite 4.1 30B vs gpt-oss-20B (high)

Granite 4.1 30Bvsgpt-oss-20B (high)

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

IBM

Granite 4.1 30B

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

gpt-oss-20B (high)

Input
$0.07/M
Output
$0.2/M
Speed
240 tok/s
TTFT
0.31s

Winner by Category

Cheaper
Granite 4.1 30B
Faster (tok/s)
gpt-oss-20B (high)
Lower Latency
Granite 4.1 30B
Benchmarks (0-11)
gpt-oss-20B (high)

Pricing Comparison

MetricGranite 4.1 30Bgpt-oss-20B (high)
Input ($/M tokens)$0$0.07
Output ($/M tokens)$0$0.2
Cost for 1M input + 100K output tokens:
Granite 4.1 30B$0.00
gpt-oss-20B (high)$0.09

Speed Comparison

Output Speed (tokens/s) — higher is better
Granite 4.1 30B
gpt-oss-20B (high)
240 tok/s
Time to First Token (seconds) — lower is better
Granite 4.1 30B
gpt-oss-20B (high)
0.31s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
14.724.5
Coding Index
10.118.5
Math Index
89.3
GPQA Diamond
48.1%68.8%
MMLU-Pro
74.8%
LiveCodeBench
77.7%
AIME 2025
89.3%
MATH-500
Humanity's Last Exam
4.2%9.8%
SciCode
25.8%34.4%
IFBench
44.4%65.1%
TerminalBench
2.3%10.6%
Granite 4.1 30B0 wins
11 winsgpt-oss-20B (high)

Frequently Asked Questions

Which is cheaper, Granite 4.1 30B or gpt-oss-20B (high)?

Granite 4.1 30B is cheaper overall. Its blended price (3:1 input/output ratio) is $0.00/M tokens vs $0.10/M for gpt-oss-20B (high).

Which model performs better on benchmarks?

gpt-oss-20B (high) wins 11 out of 12 benchmarks compared to 0 for Granite 4.1 30B. 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 240 tok/s vs 0 tok/s. Granite 4.1 30B also has lower time-to-first-token (0.00s vs 0.31s).

When should I use Granite 4.1 30B vs gpt-oss-20B (high)?

Choose based on your priorities: Granite 4.1 30B 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.