Navigate
AI BENCHY
Advertise here

AI BENCHY Compare

Anthropic: Claude Opus 4.8 vs OpenAI: GPT-5.6 Luna

Summary

Claude Opus 4.8 (low) vs GPT-5.6 Luna (medium) benchmark comparison: Claude Opus 4.8 (low) leads on average score with 7.7 vs 7.6. GPT-5.6 Luna (medium) has the lower benchmark cost at $0.258 vs $1.270. GPT-5.6 Luna (medium) is faster at 6.70s vs 10.83s, with pass rates of 79.4% vs 63.5%.

Recommended model: GPT-5.6 Luna (medium) - Its score stays close to the best score here (7.6 vs 7.7), while costing about 4.9x less than Claude Opus 4.8 (low).

Last updated at: 2026-07-09

Metric Claude Opus 4.8 Claude Opus 4.8 low Release: 2026-05-28 GPT-5.6 Luna GPT-5.6 Luna medium Release: 2026-07-09
Score 7.7 7.6
Rank #45 #54
Reliability 10.0 10.0
Consistency 8.8 9.6
Tests Correct
Attempt pass rate 79.4% 63.5%
Flaky tests 3 1
Total Runs 63 63
Cost per result 8.466 1.978
Total Cost $1.270 $0.258
Input Price $5.000 / 1M $1.000 / 1M
Output Price $25.000 / 1M $6.000 / 1M
Total Input Tokens 60,946 35,699
Output Tokens 31,771 2,148
Reasoning Tokens 6,831 34,740
Response Time (avg) 10.83s 6.70s
Response Time (max) 127.97s 29.85s
Response Time (total) 227.39s 140.62s

Generation showcase

Hamster playing table tennis

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

#45 Claude Opus 4.8

low
Cost
$0.031
Time
14.1s
Tokens
1,345 tok

#54 GPT-5.6 Luna

medium
Cost
$0.014
Time
14.6s
Tokens
2,362 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
Claude Opus 4.8 10.0 10.0 100.0% 0 3.30s 834 793 371
GPT-5.6 Luna 8.3 10.0 75.0% 0 2.52s 606 160 987
Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Claude Opus 4.8 6.6 4.6 77.8% 2 7.58s 10,590 3,637 809
GPT-5.6 Luna 5.4 7.2 44.4% 1 10.38s 7,302 564 9,928
Combined Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Claude Opus 4.8 9.8 10.0 100.0% 0 20.84s 23,500 2,216 1,081
GPT-5.6 Luna 10.0 10.0 100.0% 0 9.53s 12,500 375 1,354
Data parsing and extraction Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Claude Opus 4.8 6.3 5.8 66.7% 1 2.27s 10,503 310 0
GPT-5.6 Luna 10.0 10.0 100.0% 0 1.95s 7,140 234 324
Domain specific Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Claude Opus 4.8 5.3 10.0 33.3% 0 45.53s 975 23,311 3,908
GPT-5.6 Luna 5.3 10.0 33.3% 0 17.37s 723 68 16,531
General Intelligence Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Claude Opus 4.8 10.0 10.0 100.0% 0 2.55s 708 231 0
GPT-5.6 Luna 5.1 10.0 0.0% 0 4.34s 477 112 496
Instructions following Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Claude Opus 4.8 9.8 10.0 100.0% 0 2.78s 909 111 221
GPT-5.6 Luna 9.9 10.0 100.0% 0 2.38s 660 95 393
Puzzle Solving Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Claude Opus 4.8 10.0 10.0 100.0% 0 3.01s 894 592 184
GPT-5.6 Luna 7.8 10.0 66.7% 0 4.04s 642 255 2,104
Tool Calling Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Claude Opus 4.8 10.0 10.0 100.0% 0 6.85s 11,775 370 35
GPT-5.6 Luna 10.0 10.0 100.0% 0 6.02s 5,454 256 244
Trivia Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Claude Opus 4.8 3.0 10.0 0.0% 0 5.48s 258 200 222
GPT-5.6 Luna 3.0 10.0 0.0% 0 6.64s 195 29 2,379

Quick Compare

Switch Comparison Pair