Compare Charts

Language:

❤️ Made by XCS

AI BENCHY Compare

Anthropic: Claude Sonnet 4.6 vs OpenAI: GPT-5.3-Codex

Model Name:

Last updated at : 2026-02-27 15:16

Summary

Metric	Anthropic: Claude Sonnet 4.6 none Release: Unknown release date	OpenAI: GPT-5.3-Codex medium Release: Unknown release date
Rank	#14	#7
Score	6.36	7.93
Consistency	9.50	8.84
Cost per result	1.325	4.641
Total Cost	$0.106	$0.465
Tests Correct
Wrong Tests	6	4
Attempt pass rate	59.5%	78.6%
Flaky tests	1	2
Output Tokens	2,637	1,201
Reasoning Tokens	0	30,056

Category Breakdown

Anti-AI Tricks	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Output Tokens	Reasoning Tokens
Anthropic: Claude Sonnet 4.6	4.00	10.00	33.3%	0		1,199	0
OpenAI: GPT-5.3-Codex	10.00	10.00	100.0%	0		216	1,421

Data parsing and extraction	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Output Tokens	Reasoning Tokens
Anthropic: Claude Sonnet 4.6	10.00	10.00	100.0%	0		252	0
OpenAI: GPT-5.3-Codex	10.00	10.00	100.0%	0		234	735

Domain specific	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Output Tokens	Reasoning Tokens
Anthropic: Claude Sonnet 4.6	7.00	10.00	66.7%	0		54	0
OpenAI: GPT-5.3-Codex	4.00	7.21	55.6%	1		64	25,308

Instructions following	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Output Tokens	Reasoning Tokens
Anthropic: Claude Sonnet 4.6	5.50	10.00	50.0%	0		90	0
OpenAI: GPT-5.3-Codex	9.00	10.00	50.0%	0		93	693

Puzzle Solving	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Output Tokens	Reasoning Tokens
Anthropic: Claude Sonnet 4.6	5.00	7.68	44.4%	1		595	0
OpenAI: GPT-5.3-Codex	7.00	7.38	77.8%	1		340	1,407

Tool Calling	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Output Tokens	Reasoning Tokens
Anthropic: Claude Sonnet 4.6	10.00	10.00	100.0%	0		447	0
OpenAI: GPT-5.3-Codex	10.00	10.00	100.0%	0		254	492

Switch Comparison Pair

Compare Anthropic: Claude Sonnet 4.6 against...

Compare OpenAI: GPT-5.3-Codex against...