Navigate
AI BENCHY
AD
Track all your projects in one dashboard. Get 📊stats, 🔥heatmaps and 👀recordings in one self-hosted dashboard.
uxwizz.com

OpenAI: gpt-oss-120b vs StepFun: Step 3.5 Flash

gpt-oss-120b (medium) leads on average score with 6.1 vs 6.0. gpt-oss-120b (medium) has the lower benchmark cost at $0.019 vs $0.108. gpt-oss-120b (medium) is faster at 21.91s vs 174.22s, with pass rates of 50.0% vs 51.5%.

Recommended modelgpt-oss-120b (medium)It has the best score here (6.1), while costing about 5.7x less than Step 3.5 Flash (medium).

Last updated at: 2026-07-18

Metric gpt-oss-120b gpt-oss-120b medium Release: 2025-08-05 Step 3.5 Flash Step 3.5 Flash medium Release: 2026-02-01
Score 6.1 6.0
Rank #117 #126
Reliability 10.0 9.2
Consistency 8.0 9.0
Tests Correct
Attempt pass rate 50.0% 51.5%
Flaky tests 5 1
Total Runs 66 63
Cost per result 0.221 0.540
Total Cost $0.019 $0.108
Input Price $0.037 / 1M $0.100 / 1M
Output Price $0.170 / 1M $0.300 / 1M
Total Input Tokens 108,747 65,707
Output Tokens 29,772 108,561
Reasoning Tokens 68,044 293,993
Response Time (avg) 21.91s 174.22s
Response Time (max) 68.16s 1597.85s
Response Time (total) 328.70s 2613.32s

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#117 gpt-oss-120b

medium
Cost
$0.001
Time
26.7s
Tokens
555 tok

#126 Step 3.5 Flash

medium
Cost
$0.008
Time
277.1s
Tokens
23,695 tok

Top Models by Score

Score vs Total Cost

Response Time (avg)

Score vs Response Time (avg)

Total Output Tokens

Score vs Total Output Tokens

Category Breakdown

Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
gpt-oss-120b 5.9 7.0 55.6% 1 38.37s 7,782 3,365 11,973
Step 3.5 Flash 2.4 5.2 0.0% 0 258.38s 2,211 13,207 22,429

Quick Compare

Switch Comparison Pair