Compare/Doubao Seed Code vs gpt-oss-120B (high)

Doubao Seed Codevsgpt-oss-120B (high)

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

ByteDance Seed

Doubao Seed Code

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

gpt-oss-120B (high)

Input
$0.15/M
Output
$0.6/M
Speed
235 tok/s
TTFT
0.50s

Winner by Category

Cheaper
Doubao Seed Code
Faster (tok/s)
gpt-oss-120B (high)
Lower Latency
Doubao Seed Code
Benchmarks (5-6)
gpt-oss-120B (high)

Pricing Comparison

MetricDoubao Seed Codegpt-oss-120B (high)
Input ($/M tokens)$0$0.15
Output ($/M tokens)$0$0.6
Cost for 1M input + 100K output tokens:
Doubao Seed Code$0.00
gpt-oss-120B (high)$0.21

Speed Comparison

Output Speed (tokens/s) — higher is better
Doubao Seed Code
gpt-oss-120B (high)
235 tok/s
Time to First Token (seconds) — lower is better
Doubao Seed Code
gpt-oss-120B (high)
0.50s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
33.533.3
Coding Index
31.328.6
Math Index
79.393.4
GPQA Diamond
76.4%78.2%
MMLU-Pro
85.4%80.8%
LiveCodeBench
76.6%87.8%
AIME 2025
79.3%93.4%
MATH-500
Humanity's Last Exam
13.3%18.5%
SciCode
40.7%38.9%
IFBench
51.4%69.0%
TerminalBench
26.5%23.5%
Doubao Seed Code5 wins
6 winsgpt-oss-120B (high)

Frequently Asked Questions

Which is cheaper, Doubao Seed Code or gpt-oss-120B (high)?

Doubao Seed Code is cheaper overall. Its blended price (3:1 input/output ratio) is $0.00/M tokens vs $0.26/M for gpt-oss-120B (high).

Which model performs better on benchmarks?

gpt-oss-120B (high) wins 6 out of 12 benchmarks compared to 5 for Doubao Seed Code. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

gpt-oss-120B (high) generates tokens faster at 235 tok/s vs 0 tok/s. Doubao Seed Code also has lower time-to-first-token (0.00s vs 0.50s).

When should I use Doubao Seed Code vs gpt-oss-120B (high)?

Choose based on your priorities: Doubao Seed Code for lower cost, gpt-oss-120B (high) for stronger benchmark performance, and gpt-oss-120B (high) for faster generation. For latency-sensitive apps, check the TTFT comparison above.