Navigate
AI BENCHY
Compare Charts
❤️ Made by XCS
Your ad here

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 medium Release: Unknown release date OpenAI: GPT-5.3-Codex medium Release: Unknown release date
Rank #8 #7
Score 7.43 7.93
Consistency 9.40 8.84
Cost per result 8.105 4.641
Total Cost $0.811 $0.465
Tests Correct
Wrong Tests 4 4
Attempt pass rate 73.8% 78.6%
Flaky tests 1 2
Output Tokens 29,098 1,201
Reasoning Tokens 20,435 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 7.00 10.00 66.7% 0 1,031 1,093
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% 0 727 907
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 1.00 7.21 11.1% 1 25,790 16,919
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 10.00 10.00 100.0% 0 316 523
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 10.00 10.00 100.0% 0 579 642
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% 0 655 351
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...