Navigate
AI BENCHY
Advertise here

AI BENCHY Compare

OpenAI: GPT-5.4 vs OpenAI: GPT-5.5

Summary

GPT-5.4 vs GPT-5.5 benchmark comparison: GPT-5.5 leads on average score with 9.0 vs 8.5. GPT-5.4 has the lower benchmark cost at $1.210 vs $3.679. GPT-5.4 is faster at 22.35s vs 37.98s, with pass rates of 76.2% vs 87.3%.

Recommended model: GPT-5.4 - Its score stays close to the best score here (8.5 vs 9.0), while costing about 3.0x less than GPT-5.5.

Last updated at: 2026-06-12

Metric GPT-5.4 GPT-5.4 medium Release: 2026-03-05 GPT-5.5 GPT-5.5 medium Release: 2026-04-24
Score 8.5 9.0
Rank #20 #12
Reliability 10.0 10.0
Consistency 8.6 8.9
Tests Correct
Attempt pass rate 76.2% 87.3%
Flaky tests 4 3
Total Runs 63 63
Cost per result 8.640 21.638
Total Cost $1.210 $3.679
Input Price $2.500 / 1M $5.000 / 1M
Output Price $15.000 / 1M $30.000 / 1M
Total Input Tokens 34,108 34,212
Output Tokens 2,242 1,985
Reasoning Tokens 72,707 114,925
Response Time (avg) 22.35s 37.98s
Response Time (max) 100.41s 332.10s
Response Time (total) 469.29s 797.60s

Generation showcase

Hamster playing table tennis

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

#20 GPT-5.4

medium
Cost
$0.214
Time
199.6s
Tokens
14,349 tok

#12 GPT-5.5

medium
Cost
$0.112
Time
71.9s
Tokens
3,807 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

Anti-AI Tricks Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
GPT-5.4 8.3 10.0 75.0% 0 4.11s 606 240 1,511
GPT-5.5 10.0 10.0 100.0% 0 4.66s 606 250 1,335
Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
GPT-5.4 8.8 7.8 88.9% 1 44.36s 7,305 433 24,216
GPT-5.5 8.8 7.8 88.9% 1 59.77s 7,305 362 24,959
Combined Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
GPT-5.4 10.0 10.0 100.0% 0 20.57s 11,019 301 3,543
GPT-5.5 10.0 10.0 100.0% 0 19.29s 11,019 312 2,841
Data parsing and extraction Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
GPT-5.4 10.0 10.0 100.0% 0 5.32s 7,140 234 804
GPT-5.5 10.0 10.0 100.0% 0 4.18s 7,140 234 593
Domain specific Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
GPT-5.4 5.3 7.2 44.4% 1 74.27s 619 61 34,748
GPT-5.5 5.3 7.2 44.4% 1 164.14s 723 67 79,625
General Intelligence Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
GPT-5.4 4.7 3.1 33.3% 1 4.92s 477 145 321
GPT-5.5 10.0 10.0 100.0% 0 4.16s 477 138 223
Instructions following Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
GPT-5.4 10.0 10.0 100.0% 0 3.11s 660 93 897
GPT-5.5 10.0 10.0 100.0% 0 3.36s 660 93 538
Puzzle Solving Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
GPT-5.4 8.2 7.2 88.9% 1 9.14s 642 441 3,815
GPT-5.5 10.0 10.0 100.0% 0 6.76s 642 241 2,225
Tool Calling Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
GPT-5.4 10.0 10.0 100.0% 0 13.28s 5,445 264 1,031
GPT-5.5 10.0 10.0 100.0% 0 10.57s 5,445 258 832
Trivia Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
GPT-5.4 3.0 10.0 0.0% 0 13.95s 195 30 1,821
GPT-5.5 2.8 1.6 33.3% 1 37.86s 195 30 1,754

Quick Compare

Switch Comparison Pair

Gemini 3.5 FlashlowvsGPT-5.5mediumDeepSeek V4 FlashhighvsGPT-5.4mediumGemini 3.5 FlashlowvsGPT-5.4mediumDeepSeek V4 FlashhighvsGPT-5.5mediumGPT-5.4mediumvsStep 3.7 FlashlowGemini 3.5 FlashhighvsGPT-5.5mediumGemini 3 Flash PreviewlowvsGPT-5.4mediumClaude Sonnet 4.6nonevsGPT-5.4mediumClaude Opus 4.8nonevsGPT-5.4mediumGPT-5.5mediumvsStep 3.7 FlashlowGemini 3.5 FlashhighvsGPT-5.4mediumGPT-5.4mediumvsQwen3.7 Plusnone