Navigate
AI BENCHY
Advertise here

AI BENCHY Compare

Anthropic: Claude Opus 4.8 vs MoonshotAI: Kimi K3

Summary

Claude Opus 4.8 (medium) leads on average score with 8.8 vs 8.5. Claude Opus 4.8 (medium) has the lower benchmark cost at $1.107 vs $3.112. Claude Opus 4.8 (medium) is faster at 9.72s vs 122.48s, with pass rates of 84.1% vs 82.5%.

Recommended modelClaude Opus 4.8 (medium)It has the best score here (8.8), while costing about 2.8x less than Kimi K3 (max).

Last updated at: 2026-07-16

Metric Claude Opus 4.8 Claude Opus 4.8 medium Release: 2026-05-28 Kimi K3 Kimi K3 max Release: 2026-07-16
Score 8.8 8.5
Rank #16 #21
Reliability 10.0 9.4
Consistency 9.6 9.2
Tests Correct
Attempt pass rate 84.1% 82.5%
Flaky tests 1 2
Total Runs 63 63
Cost per result 6.512 19.446
Total Cost $1.107 $3.112
Input Price $5.000 / 1M $3.000 / 1M
Output Price $25.000 / 1M $15.000 / 1M
Total Input Tokens 61,007 34,916
Output Tokens 26,495 2,910
Reasoning Tokens 5,901 197,529
Response Time (avg) 9.72s 122.48s
Response Time (max) 38.03s 766.58s
Response Time (total) 204.19s 2327.06s

Generation showcase

Hamster playing table tennis

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

#16 Claude Opus 4.8

medium
Cost
$0.057
Time
23.1s
Tokens
2,412 tok

#21 MoonshotAI: Kimi K3

max
Cost
$0.281
Time
506.9s
Tokens
18,863 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 Opus 4.8 10.0 10.0 100.0% 0 15.33s 10,590 9,945 1,381
Kimi K3 10.0 10.0 100.0% 0 325.79s 8,061 460 84,012

Quick Compare

Switch Comparison Pair