Navigate
Advertise here

GPT-5.2 (medium) vs Inkling Small (high)

The average score is effectively tied at 8.4 vs 8.4. Inkling Small (high) has the lower benchmark cost at $0.398 vs $1.182. GPT-5.2 (medium) is faster at 28.51s vs 30.43s, with pass rates of 72.7% vs 69.7%.

Last updated at: 2026-09-10

Compared models

Rank
#58
Total Output Tokens
71,252
Response Time (avg)
28.51s
Total Cost
$1.182
Rank
#61
Total Output Tokens
298,893
Response Time (avg)
30.43s
Total Cost
$0.398
Recommended model Inkling Small (high)

It has the best score here (8.4), while costing about 3.0x less than GPT-5.2 (medium).

Detailed comparison

Metric GPT-5.2 GPT-5.2 medium Release: 2025-12-11 Inkling Small Inkling Small high Release: 2026-08-01
Score 8.4 8.4
Rank #58 #61
Reliability 10.0 10.0
Consistency 8.5 9.2
Attempts 66/66 66/66
Tests Correct
Attempt pass rate 72.7% 69.7%
Flaky tests 4 2
Total Runs 66 66
Cost per result 8.438 2.868
Total Cost $1.182 $0.398
Input Price $1.750 / 1M $0.450 / 1M
Output Price $14.000 / 1M $1.200 / 1M
Total Input Tokens 105,013 85,669
Output Tokens 9,914 6,092
Reasoning Tokens 61,338 292,801
Response Time (avg) 28.51s 30.43s
Response Time (max) 116.86s 122.60s
Response Time (total) 456.13s 669.38s
Parameters ~1.2T total (~80B active) 276B total (12B active)
Availability Closed Closed

Model generation showcase

Hamster playing table tennis

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

#58 GPT-5.2

medium
Cost
$0.047
Time
49.2s
Tokens
3,396 tok

#61 Thinking Machines: Inkling Small

high
Cost
$0.006
Time
34.7s
Tokens
4,735 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-5.2 10.0 10.0 100.0% 0 22.73s 7,302 511 11,912
Inkling Small 10.0 10.0 100.0% 0 93.23s 7,374 463 120,474

Quick Compare

Switch Comparison Pair