Navigate
Advertise here

GPT-6 Luna (high) vs GPT-6 Sol (low)

GPT-6 Sol (low) leads on average score with 8.4 vs 8.3. GPT-6 Luna (high) has the lower benchmark cost at $0.054 vs $0.273. GPT-6 Sol (low) is faster at 6.92s vs 17.53s, with pass rates of 75.8% vs 86.4%.

Last updated at: 2026-09-23

Compared models

Rank
#73
Total Output Tokens
91,405
Response Time (avg)
17.53s
Total Cost
$0.054
Rank
#68
Total Output Tokens
11,677
Response Time (avg)
6.92s
Total Cost
$0.273
Recommended model GPT-6 Luna (high)

Its score stays close to the best score here (8.3 vs 8.4), while costing about 5.1x less than GPT-6 Sol (low).

Detailed comparison

Metric GPT-6 Luna GPT-6 Luna high Release: 2026-09-23 GPT-6 Sol GPT-6 Sol low Release: 2026-09-23
Score 8.3 8.4
Rank #73 #68
Reliability 10.0 10.0
Consistency 9.0 8.5
Attempts 66/66 66/66
Tests Correct
Attempt pass rate 75.8% 86.4%
Flaky tests 3 4
Total Runs 66 66
Cost per result 0.359 1.604
Total Cost $0.054 $0.273
Input Price $0.100 / 1M $2.000 / 1M
Output Price $0.500 / 1M $10.000 / 1M
Total Input Tokens 80,441 77,882
Output Tokens 4,761 4,047
Reasoning Tokens 86,644 7,630
Response Time (avg) 17.53s 6.92s
Response Time (max) 106.93s 17.91s
Response Time (total) 385.74s 152.17s
Parameters ~400B total (~17B active) ~2T total (~150B active)
Availability Closed Closed

Model generation showcase

Hamster playing table tennis

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

#73 GPT-6 Luna

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

#68 GPT-6 Sol

low
Cost
$0.018
Time
17.4s
Tokens
1,850 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
GPT-6 Sol 6.2 4.8 66.7% 2 8.74s 7,302 405 1,296

Quick Compare

Switch Comparison Pair