AI BENCHY
Advertise here

#57

Claude Opus 4.6

Anthropic Release: 2026-02-05 Tested on: 2026-05-08 13:38 anthropic/claude-opus-4.6::medium

Score

7.4

Consistency

9.1

Reliability

10.0

Total Cost

$1.710

Total Output Tokens

59,264

Input Price

$5.000 / 1M

Output Price

$25.000 / 1M

Tests Correct

Wrong Tests: 7

Attempt pass rate: 66.7%

Flaky tests

2

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

24.59s

Response Time (max): 83.40s

Response Time (total): 295.08s

Extra formatting: 4 Wrong answer: 3

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Claude Opus 4.6mediumvsKimi K2.6mediumClaude Opus 4.6mediumvsGemini 3.1 Flash LitelowClaude Opus 4.6mediumvsGPT-5.2 ChatnoneClaude Opus 4.6mediumvsQwen3.5-FlashmediumClaude Opus 4.6mediumvsGemini 3.1 Flash Lite PreviewnoneClaude Opus 4.6mediumvsGPT-5.3 ChatnoneClaude Opus 4.6mediumvsGemini 3 Flash PreviewmediumClaude Opus 4.6mediumvsGemini 3.5 FlashlowClaude Opus 4.6mediumvsRing-2.6-1Tmedium

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 6.4 5.8
Coding 10.0 10.0
Combined 10.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 3.0 10.0
General Intelligence 10.0 10.0
Instructions following 10.0 10.0
Puzzle Solving 7.7 10.0
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models