Navigate
Advertise here

GPT-6 Luna (high) vs Step 3.7 Flash (medium)

Step 3.7 Flash (medium) leads on average score with 7.8 vs 7.7. GPT-6 Luna (high) has the lower benchmark cost at $0.074 vs $0.571. GPT-6 Luna (high) is faster at 20.37s vs 26.57s, with pass rates of 73.9% vs 68.1%.

Last updated at: 2026-11-16

Compared models

Rank
#176
Total Output Tokens
101,587
Response Time (avg)
20.37s
Total Cost
$0.074
Rank
#170
Total Output Tokens
440,835
Response Time (avg)
26.57s
Total Cost
$0.571
Recommended model GPT-6 Luna (high)

Its score stays close to the best score here (7.7 vs 7.8), while costing about 7.7x less than Step 3.7 Flash (medium).

Detailed comparison

Metric GPT-6 Luna GPT-6 Luna high Release: 2026-09-23 Step 3.7 Flash Step 3.7 Flash medium Release: 2026-05-29
Score 7.7 7.8
Rank #176 #170
Reliability 10.0 10.0
Consistency 8.7 8.7
Attempts 69/69 69/69
Tests Correct
Attempt pass rate 73.9% 68.1%
Flaky tests 4 4
Total Runs 69 69
Cost per result 0.492 4.392
Total Cost $0.074 $0.571
Input Price $0.100 / 1M $0.200 / 1M
Output Price $0.500 / 1M $1.150 / 1M
Cache Read Price $0.010 / 1M $0.040 / 1M
Cache Write Price $0.125 / 1M N/A
Total Input Tokens 229,986 319,524
Output Tokens 6,037 440,835
Reasoning Tokens 95,550 0
Response Time (avg) 20.37s 26.57s
Response Time (max) 106.93s 152.83s
Response Time (total) 468.52s 611.09s
Parameters ~400B total (~17B active) 198B total (11B active)
Availability Closed Open source

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Model generation showcase

Hamster playing table tennis

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

#176 GPT-6 Luna

high
Cost
$0.003
Time
49.2s
Tokens
5,231 tok

#170 Step 3.7 Flash

medium
Cost
$0.006
Time
46.2s
Tokens
4,466 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-6 Luna 7.8 7.4 77.8% 1 24.69s 7,302 483 15,691
Step 3.7 Flash 8.8 7.8 88.9% 1 27.42s 7,437 44,797 0

Switch Comparison Pair