Navigate
Advertise here

DeepSeek V4.1 Flash (max) vs GPT-5.2 (medium)

GPT-5.2 (medium) leads on average score with 8.7 vs 8.6. DeepSeek V4.1 Flash (max) has the lower benchmark cost at $1.204 vs $1.558. GPT-5.2 (medium) is faster at 31.29s vs 61.58s, with pass rates of 69.6% vs 73.9%.

Last updated at: 2026-10-24

Compared models

Rank
#73
Total Output Tokens
908,171
Response Time (avg)
61.58s
Total Cost
$1.204
Rank
#68
Total Output Tokens
80,538
Response Time (avg)
31.29s
Total Cost
$1.558
Recommended model GPT-5.2 (medium)

It has the best score here (8.7), while responding about 2.0x faster than DeepSeek V4.1 Flash (max).

Detailed comparison

Metric DeepSeek V4.1 Flash DeepSeek V4.1 Flash max Release: 2026-09-10 GPT-5.2 GPT-5.2 medium Release: 2025-12-11
Score 8.6 8.7
Rank #73 #68
Reliability 9.4 10.0
Consistency 9.3 8.5
Attempts 69/69 69/69
Tests Correct
Attempt pass rate 69.6% 73.9%
Flaky tests 2 4
Total Runs 69 69
Cost per result 3.715 10.261
Total Cost $1.204 $1.558
Input Price $0.013 / 1M $1.750 / 1M
Output Price $1.320 / 1M $14.000 / 1M
Cache Read Price $0.013 / 1M $0.175 / 1M
Cache Write Price N/A N/A
Total Input Tokens 414,054 235,207
Output Tokens 7,635 11,065
Reasoning Tokens 900,536 69,473
Response Time (avg) 61.58s 31.29s
Response Time (max) 335.08s 116.86s
Response Time (total) 1416.24s 531.98s
Parameters 748B total (16B active) ~1.2T total (~80B active)
Availability Open source Closed

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.

#73 DeepSeek V4.1 Flash

max
Cost
$0.066
Time
211.0s
Tokens
54,712 tok

#68 GPT-5.2

medium
Cost
$0.047
Time
49.2s
Tokens
3,396 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 V4.1 Flash 10.0 10.0 100.0% 0 62.50s 7,509 373 132,357
GPT-5.2 10.0 10.0 100.0% 0 22.73s 7,302 511 11,912

Switch Comparison Pair