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

Anthropic: Claude Opus 4.6 vs StepFun: Step 3.7 Flash

Claude Opus 4.6 (medium) leads on average score with 7.7 vs 7.3. Step 3.7 Flash (low) has the lower benchmark cost at $0.454 vs $3.059. Step 3.7 Flash (low) is faster at 20.68s vs 34.27s, with pass rates of 63.6% vs 68.2%.

Recommended modelStep 3.7 Flash (low)Its score stays close to the best score here (7.3 vs 7.7), while costing about 6.7x less than Claude Opus 4.6 (medium).

Last updated at: 2026-07-25

Metric Claude Opus 4.6 Claude Opus 4.6 medium Release: 2026-02-05 Step 3.7 Flash Step 3.7 Flash low Release: 2026-05-29
Score 7.7 7.3
Rank #50 #75
Reliability 10.0 10.0
Consistency 8.8 8.1
Tests Correct
Attempt pass rate 63.6% 68.2%
Flaky tests 3 5
Total Runs 66 66
Cost per result 23.524 3.782
Total Cost $3.059 $0.454
Input Price $5.000 / 1M $0.200 / 1M
Output Price $25.000 / 1M $1.150 / 1M
Total Input Tokens 108,615 103,833
Output Tokens 72,286 376,581
Reasoning Tokens 28,315 0
Response Time (avg) 34.27s 20.68s
Response Time (max) 151.51s 124.75s
Response Time (total) 513.99s 455.01s

Hamster playing table tennis

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

#50 Claude Opus 4.6

medium
Invalid SVG
Cost
$0.000
Time
300.0s
Tokens
0 tok

#75 Step 3.7 Flash

low
Invalid SVG
Cost
$0.004
Time
25.3s
Tokens
3,072 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
Claude Opus 4.6 5.7 7.1 44.4% 1 30.10s 8,522 13,057 4,121
Step 3.7 Flash 8.2 7.2 88.9% 1 9.46s 7,437 18,685 0

Quick Compare

Switch Comparison Pair