Neura Intelligence Index

AI Model Benchmarks

Back to Leaderboard

Claude 3.5 Sonnet vs GPT-5 nano

Claude 3.5 Sonnet

Anthropic 🇺🇸

35.7

#213—

OpenAI 🇺🇸

36.7

#210—

Category Comparison

Benchmark-by-Benchmark

reasoning

Benchmark	Claude 3.5 Sonnet	GPT-5 nano
GPQA Diamond	59.4	71.2
Humanity's Last Exam	—	8.7

math

Benchmark	Claude 3.5 Sonnet	GPT-5 nano
AIME 2025	—	85.2
FrontierMath	—	9.6

Category Winners

math

GPT-5 nano

39.0

reasoning

Claude 3.5 Sonnet

35.7

Claude 3.5 Sonnet vs GPT-5 nano — Benchmark Comparison | Neura Market