Compare · ModelsLive · 2 picked · head to head
Claude 3 Sonnet vs GPT-4o (2024-11-20)
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
GPT-4o (2024-11-20) wins on 6/6 benchmarks
GPT-4o (2024-11-20) wins 6 of 6 shared benchmarks. Leads in general · knowledge · math.
Category leads
general·GPT-4o (2024-11-20)knowledge·GPT-4o (2024-11-20)math·GPT-4o (2024-11-20)coding·GPT-4o (2024-11-20)
Hype vs Reality
Attention vs performance
Claude 3 Sonnet
#266 by perf·no signal
GPT-4o (2024-11-20)
#242 by perf·no signal
Best value
GPT-4o (2024-11-20)
Claude 3 Sonnet
n/a
no price
GPT-4o (2024-11-20)
5.2 pts/$
$6.25/M
Vendor risk
Who is behind the model
Anthropic
$965.0B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
6 benchmarks · 2 models
Claude 3 SonnetGPT-4o (2024-11-20)
Dtbench
GPT-4o (2024-11-20) leads by +18.2
Claude 3 Sonnet
22.7
GPT-4o (2024-11-20)
40.9
GPQA diamond
GPT-4o (2024-11-20) leads by +11.5
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Claude 3 Sonnet
20.8
GPT-4o (2024-11-20)
32.3
MATH level 5
GPT-4o (2024-11-20) leads by +35.1
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
Claude 3 Sonnet
18.2
GPT-4o (2024-11-20)
53.3
MMLU
GPT-4o (2024-11-20) leads by +11.2
Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge.
Claude 3 Sonnet
67.9
GPT-4o (2024-11-20)
79.1
OTIS Mock AIME 2024-2025
GPT-4o (2024-11-20) leads by +3.9
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Claude 3 Sonnet
2.4
GPT-4o (2024-11-20)
6.3
WeirdML
GPT-4o (2024-11-20) leads by +15.0
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
Claude 3 Sonnet
10.2
GPT-4o (2024-11-20)
25.1
Full benchmark table
| Benchmark | Claude 3 Sonnet | GPT-4o (2024-11-20) |
|---|---|---|
Dtbench | 22.7 | 40.9 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 20.8 | 32.3 |
MATH level 5 MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics. | 18.2 | 53.3 |
MMLU Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge. | 67.9 | 79.1 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 2.4 | 6.3 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 10.2 | 25.1 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| — | — | — | — | |
| $2.50 | $10.00 | 128K tokens (~64 books) | $43.75 |