Navigate
Advertise here

DeepSeek V3.2 (medium) vs GPT-6 Luna (low)

The average score is effectively tied at 7.0 vs 7.0. GPT-6 Luna (low) has the lower benchmark cost at $0.020 vs $0.078. GPT-6 Luna (low) is faster at 21.96s vs 68.43s, with pass rates of 65.2% vs 62.1%.

Last updated at: 2026-09-23

Compared models

Rank
#160
Total Output Tokens
128,787
Response Time (avg)
68.43s
Total Cost
$0.078
Rank
#159
Total Output Tokens
22,605
Response Time (avg)
21.96s
Total Cost
$0.020
Recommended model GPT-6 Luna (low)

It has the best score here (7.0), while costing about 4.0x less than DeepSeek V3.2 (medium).

Detailed comparison

Metric DeepSeek V3.2 DeepSeek V3.2 medium Release: 2025-12-01 GPT-6 Luna GPT-6 Luna low Release: 2026-09-23
Score 7.0 7.0
Rank #160 #159
Reliability 10.0 9.6
Consistency 7.4 8.5
Attempts 66/66 66/66
Tests Correct
Attempt pass rate 65.2% 62.1%
Flaky tests 7 4
Total Runs 66 66
Cost per result 0.672 0.176
Total Cost $0.078 $0.020
Input Price $0.269 / 1M $0.100 / 1M
Output Price $0.400 / 1M $0.500 / 1M
Total Input Tokens 101,056 80,159
Output Tokens 11,832 4,623
Reasoning Tokens 116,955 17,982
Response Time (avg) 68.43s 21.96s
Response Time (max) 376.10s 89.37s
Response Time (total) 1505.53s 483.19s
Parameters 671B total (37B active) ~400B total (~17B active)
Availability Open source Closed

Model generation showcase

Hamster playing table tennis

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

#160 DeepSeek V3.2

medium
Cost
$0.001
Time
53.6s
Tokens
1,932 tok

#159 GPT-6 Luna

low
Cost
$0.002
Time
19.2s
Tokens
2,598 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
DeepSeek V3.2 6.0 7.2 55.6% 1 248.68s 5,717 649 52,014
GPT-6 Luna 6.0 7.2 55.6% 1 15.39s 7,302 493 6,655

Quick Compare

Switch Comparison Pair