Navigate
AI BENCHY
Advertise here

Step 3.7 Flash (medium) vs Inkling (medium)

The average score is effectively tied at 7.9 vs 8.0. Inkling (medium) has the lower benchmark cost at $0.377 vs $0.495. Inkling (medium) is faster at 15.66s vs 23.51s, with pass rates of 68.2% vs 75.8%.

Last updated at: 2026-08-29

Rank
#61
Total Output Tokens
409,709
Response Time (avg)
23.51s
Total Cost
$0.495
Rank
#57
Total Output Tokens
63,842
Response Time (avg)
15.66s
Total Cost
$0.377
Recommended model Inkling (medium)

It has the best score here (8.0), while responding about 1.5x faster than Step 3.7 Flash (medium).

Detailed comparison

Metric Step 3.7 Flash Step 3.7 Flash medium Release: 2026-05-29 Inkling Inkling medium Release: 2026-07-18
Score 7.9 8.0
Rank #61 #57
Reliability 10.0 10.0
Consistency 8.9 8.5
Attempts 66/66 66/66
Tests Correct
Attempt pass rate 68.2% 75.8%
Flaky tests 3 4
Total Runs 66 66
Cost per result 3.801 2.551
Total Cost $0.495 $0.377
Input Price $0.200 / 1M $0.950 / 1M
Output Price $1.150 / 1M $4.050 / 1M
Total Input Tokens 114,191 124,062
Output Tokens 409,709 12,190
Reasoning Tokens 0 51,652
Response Time (avg) 23.51s 15.66s
Response Time (max) 152.83s 85.12s
Response Time (total) 517.21s 344.52s
Parameters 198B total (11B active) 975B total (41B active)
Availability Open source Open source

Model generation showcase

Hamster playing table tennis

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

#61 Step 3.7 Flash

medium
Cost
$0.006
Time
46.2s
Tokens
4,466 tok

#57 Thinking Machines: Inkling

medium
Cost
$0.004
Time
11.2s
Tokens
852 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
Step 3.7 Flash 8.8 7.8 88.9% 1 27.42s 7,437 44,797 0
Inkling 8.4 7.8 77.8% 1 25.20s 7,374 525 14,457

Quick Compare

Switch Comparison Pair