Navigate
AI BENCHY
Advertise here

AI BENCHY Compare

Inception: Mercury 2 vs OpenAI: GPT-5.5

Summary

Mercury 2 vs GPT-5.5 benchmark comparison: Mercury 2 leads on average score with 6.6 vs 6.4. Mercury 2 has the lower benchmark cost at $0.058 vs $0.231. GPT-5.5 is faster at 1.89s vs 2.24s, with pass rates of 54.0% vs 54.0%.

Recommended model: Mercury 2 - It has the best score here (6.6), while costing about 4.0x less than GPT-5.5.

Last updated at: 2026-06-04

Metric Mercury 2 Mercury 2 medium Release: 2026-02-24 GPT-5.5 GPT-5.5 none Release: 2026-04-24
Score 6.6 6.4
Rank #81 #91
Reliability 10.0 10.0
Consistency 8.8 8.8
Tests Correct
Attempt pass rate 54.0% 54.0%
Flaky tests 3 3
Total Runs 63 63
Cost per result 0.578 2.302
Total Cost $0.058 $0.231
Input Price $0.250 / 1M $5.000 / 1M
Output Price $0.750 / 1M $30.000 / 1M
Total Input Tokens 35,116 34,212
Output Tokens 4,048 1,971
Reasoning Tokens 61,219 0
Response Time (avg) 2.24s 1.89s
Response Time (max) 14.63s 5.56s
Response Time (total) 44.72s 39.64s

Generation showcase

Hamster playing table tennis

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

#81 Mercury 2

medium
Cost
$0.002
Time
2.1s
Tokens
1,702 tok

#91 GPT-5.5

none
Cost
$0.090
Time
54.3s
Tokens
3,063 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
Mercury 2 6.9 9.9 50.0% 0 1.12s 554 2,546 2,609
GPT-5.5 6.9 7.9 66.7% 1 1.31s 606 213 0
Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Mercury 2 8.2 7.7 77.8% 1 2.04s 7,065 296 11,328
GPT-5.5 5.5 10.0 33.3% 0 1.35s 7,305 462 0
Combined Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Mercury 2 10.0 10.0 100.0% 0 3.28s 12,909 268 4,887
GPT-5.5 3.0 10.0 0.0% 0 5.56s 11,019 300 0
Data parsing and extraction Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Mercury 2 7.3 5.9 83.3% 1 1.11s 6,234 183 1,656
GPT-5.5 10.0 10.0 100.0% 0 1.18s 7,140 222 0
Domain specific Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Mercury 2 2.9 7.2 11.1% 1 6.48s 695 41 30,754
GPT-5.5 2.9 7.2 11.1% 1 1.31s 723 52 0
General Intelligence Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Mercury 2 4.8 10.0 0.0% 0 821ms 456 137 542
GPT-5.5 10.0 10.0 100.0% 0 3.41s 477 124 0
Instructions following Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Mercury 2 10.0 10.0 100.0% 0 1.07s 340 14 958
GPT-5.5 6.2 5.8 66.7% 1 1.15s 660 81 0
Puzzle Solving Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Mercury 2 5.4 10.0 33.3% 0 949ms 601 361 2,781
GPT-5.5 7.7 10.0 66.7% 0 1.29s 642 252 0
Tool Calling Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Mercury 2 10.0 10.0 100.0% 0 1.89s 6,080 180 1,956
GPT-5.5 10.0 10.0 100.0% 0 3.90s 5,445 247 0
Trivia Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Mercury 2 3.0 10.0 0.0% 0 2.58s 182 22 3,748
GPT-5.5 3.0 10.0 0.0% 0 5.01s 195 18 0

Quick Compare

Switch Comparison Pair

Gemini 3.1 Flash LiteminimalvsGPT-5.5noneGemma 4 31BnoneFree AvailablevsMercury 2mediumClaude Sonnet 4.6nonevsMercury 2mediumGemini 3.1 Flash LiteminimalvsMercury 2mediumMercury 2mediumvsQwen3.7 PlusnoneMercury 2mediumvsQwen3.6 Max PreviewnoneGemini 3.1 Flash LitenonevsMercury 2mediumGPT-5.5nonevsQwen3.6 27BmediumMercury 2mediumvsStep 3.7 FlashhighDeepSeek V4 ProhighvsGPT-5.5noneMercury 2mediumvsQwen3.5 Plus 2026-02-15noneClaude Opus 4.8nonevsMercury 2medium