Compare/Step 3.5 Flash 2603 vs gpt-oss-20B (high)

Step 3.5 Flash 2603vsgpt-oss-20B (high)

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

StepFun

Step 3.5 Flash 2603

Input
$0/M
Output
$0/M
Speed
158 tok/s
TTFT
0.81s
OpenAI

gpt-oss-20B (high)

Input
$0.05/M
Output
$0.2/M
Speed
260 tok/s
TTFT
0.40s

Winner by Category

Cheaper
Step 3.5 Flash 2603
Faster (tok/s)
gpt-oss-20B (high)
Lower Latency
gpt-oss-20B (high)
Benchmarks (7-4)
Step 3.5 Flash 2603

Pricing Comparison

MetricStep 3.5 Flash 2603gpt-oss-20B (high)
Input ($/M tokens)$0$0.05
Output ($/M tokens)$0$0.2
Cost for 1M input + 100K output tokens:
Step 3.5 Flash 2603$0.00
gpt-oss-20B (high)$0.07

Speed Comparison

Output Speed (tokens/s) — higher is better
Step 3.5 Flash 2603
158 tok/s
gpt-oss-20B (high)
260 tok/s
Time to First Token (seconds) — lower is better
Step 3.5 Flash 2603
0.81s
gpt-oss-20B (high)
0.40s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
38.524.5
Coding Index
34.618.5
Math Index
89.3
GPQA Diamond
82.6%68.8%
MMLU-Pro
74.8%
LiveCodeBench
77.7%
AIME 2025
89.3%
MATH-500
Humanity's Last Exam
22.6%9.8%
SciCode
38.5%34.4%
IFBench
66.5%65.1%
TerminalBench
32.6%10.6%
Step 3.5 Flash 26037 wins
4 winsgpt-oss-20B (high)

Frequently Asked Questions

Which is cheaper, Step 3.5 Flash 2603 or gpt-oss-20B (high)?

Step 3.5 Flash 2603 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?

Step 3.5 Flash 2603 wins 7 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 260 tok/s vs 158 tok/s. However, gpt-oss-20B (high) has lower time-to-first-token (0.40s vs 0.81s).

When should I use Step 3.5 Flash 2603 vs gpt-oss-20B (high)?

Choose based on your priorities: Step 3.5 Flash 2603 for lower cost, Step 3.5 Flash 2603 for stronger benchmark performance, and gpt-oss-20B (high) for faster generation. For latency-sensitive apps, check the TTFT comparison above.