Navigate
AI BENCHY
Advertise here

Anthropic: Claude Sonnet 4.6 vs Inception: Mercury 2

Claude Sonnet 4.6 leads on average score with 7.3 vs 7.0. Mercury 2 (medium) has the lower benchmark cost at $0.093 vs $0.661. Mercury 2 (medium) is faster at 2.72s vs 8.12s, with pass rates of 57.6% vs 51.5%.

Recommended modelMercury 2 (medium)Its score stays close to the best score here (7.0 vs 7.3), while costing about 7.1x less than Claude Sonnet 4.6.

Last updated at: 2026-07-25

Metric Claude Sonnet 4.6 Claude Sonnet 4.6 none Release: 2026-02-17 Mercury 2 Mercury 2 medium Release: 2026-02-24
Score 7.3 7.0
Rank #71 #86
Reliability 10.0 10.0
Consistency 9.7 8.8
Tests Correct
Attempt pass rate 57.6% 51.5%
Flaky tests 1 3
Total Runs 66 66
Cost per result 5.502 0.928
Total Cost $0.661 $0.093
Input Price $3.000 / 1M $0.250 / 1M
Output Price $15.000 / 1M $0.750 / 1M
Total Input Tokens 123,264 109,572
Output Tokens 19,362 10,313
Reasoning Tokens 0 76,806
Response Time (avg) 8.12s 2.72s
Response Time (max) 51.18s 14.63s
Response Time (total) 121.78s 57.12s

Hamster playing table tennis

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

#71 Claude Sonnet 4.6

none
Cost
$0.038
Time
27.3s
Tokens
2,598 tok

#86 Mercury 2

medium
Cost
$0.002
Time
2.1s
Tokens
1,702 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
Claude Sonnet 4.6 5.5 10.0 33.3% 0 5.19s 8,522 2,127 0
Mercury 2 8.2 7.7 77.8% 1 2.04s 7,065 296 11,328

Quick Compare

Switch Comparison Pair