Compare · ModelsLive · 2 picked · head to head

Claude 3.5 Sonnet vs GPT-5 Nano

Side by side · benchmarks, pricing, and signals you can act on.

Winner summary

GPT-5 Nano wins 11 of 11 shared benchmarks. Leads in math · knowledge · language.

Category leads
math·GPT-5 Nanoknowledge·GPT-5 Nanolanguage·GPT-5 Nanoreasoning·GPT-5 Nanocoding·GPT-5 Nano
Hype vs Reality
Claude 3.5 Sonnet
#129 by perf·no signal
QUIET
GPT-5 Nano
#114 by perf·no signal
QUIET
Best value
Claude 3.5 Sonnet
no price
GPT-5 Nano
201.3 pts/$
$0.23/M
Vendor risk
Anthropic logo
Anthropic
$380.0B·Tier 1
Medium risk
OpenAI logo
OpenAI
$840.0B·Tier 1
Medium risk
Head to head
Claude 3.5 SonnetGPT-5 Nano
FrontierMath-2025-02-28-Private
GPT-5 Nano leads by +7.2
FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning.
Claude 3.5 Sonnet
1.0
GPT-5 Nano
8.3
FrontierMath-Tier-4-2025-07-01-Private
GPT-5 Nano leads by +2.0
FrontierMath Tier 4 (Jul 2025) · the most challenging tier of frontier mathematics, containing problems that push the absolute limits of AI mathematical reasoning.
Claude 3.5 Sonnet
0.1
GPT-5 Nano
2.1
GPQA diamond
GPT-5 Nano leads by +20.5
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Claude 3.5 Sonnet
38.7
GPT-5 Nano
59.3
HELM · GPQA
GPT-5 Nano leads by +11.4
Claude 3.5 Sonnet
56.5
GPT-5 Nano
67.9
HELM · IFEval
GPT-5 Nano leads by +7.6
Claude 3.5 Sonnet
85.6
GPT-5 Nano
93.2
HELM · MMLU-Pro
GPT-5 Nano leads by +0.1
Claude 3.5 Sonnet
77.7
GPT-5 Nano
77.8
HELM · Omni-MATH
GPT-5 Nano leads by +27.1
Claude 3.5 Sonnet
27.6
GPT-5 Nano
54.7
HELM · WildBench
GPT-5 Nano leads by +1.4
Claude 3.5 Sonnet
79.2
GPT-5 Nano
80.6
MATH level 5
GPT-5 Nano leads by +43.6
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
Claude 3.5 Sonnet
51.7
GPT-5 Nano
95.2
OTIS Mock AIME 2024-2025
GPT-5 Nano leads by +74.7
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Claude 3.5 Sonnet
6.4
GPT-5 Nano
81.1
WeirdML
GPT-5 Nano leads by +7.1
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
Claude 3.5 Sonnet
31.0
GPT-5 Nano
38.1
Full benchmark table
BenchmarkClaude 3.5 SonnetGPT-5 Nano
FrontierMath-2025-02-28-Private
FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning.
1.08.3
FrontierMath-Tier-4-2025-07-01-Private
FrontierMath Tier 4 (Jul 2025) · the most challenging tier of frontier mathematics, containing problems that push the absolute limits of AI mathematical reasoning.
0.12.1
GPQA diamond
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
38.759.3
HELM · GPQA
56.567.9
HELM · IFEval
85.693.2
HELM · MMLU-Pro
77.777.8
HELM · Omni-MATH
27.654.7
HELM · WildBench
79.280.6
MATH level 5
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
51.795.2
OTIS Mock AIME 2024-2025
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
6.481.1
WeirdML
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
31.038.1
Pricing · per 1M tokens · projected $/mo at 10M tokens
ModelInputOutputContextProjected $/mo
Anthropic logoClaude 3.5 Sonnet
OpenAI logoGPT-5 Nano$0.05$0.40400K tokens (~200 books)$1.38
People also compared