Compare · ModelsLive · 3 picked · head to head

Claude 2 vs PaLM 2-L vs GPT-3.5 Turbo (older v0613)

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

Winner summary

Claude 2 wins 4 of 6 shared benchmarks. Leads in knowledge · math.

Category leads
knowledge·Claude 2math·Claude 2
Hype vs Reality
Claude 2
#186 by perf·no signal
QUIET
PaLM 2-L
#14 by perf·no signal
QUIET
GPT-3.5 Turbo (older v0613)
#139 by perf·no signal
QUIET
Best value
Claude 2
no price
PaLM 2-L
no price
GPT-3.5 Turbo (older v0613)
30.5 pts/$
$1.50/M
Vendor risk
Anthropic logo
Anthropic
$380.0B·Tier 1
Medium risk
U
Unknown
private · undisclosed
Unknown
OpenAI logo
OpenAI
$840.0B·Tier 1
Medium risk
Head to head
Claude 2PaLM 2-LGPT-3.5 Turbo (older v0613)
TriviaQA
Claude 2 leads by +1.4
TriviaQA · reading comprehension benchmark with trivia questions, requiring models to find and reason over evidence from provided documents.
Claude 2
87.5
PaLM 2-L
86.1
GPT-3.5 Turbo (older v0613)
85.8
ARC AI2
GPT-3.5 Turbo (older v0613) leads by +24.3
AI2 Reasoning Challenge · tests grade-school level science knowledge with multiple-choice questions requiring reasoning beyond simple retrieval.
PaLM 2-L
58.9
GPT-3.5 Turbo (older v0613)
83.2
GPQA diamond
Claude 2 leads by +10.0
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Claude 2
12.9
GPT-3.5 Turbo (older v0613)
2.9
MATH level 5
Claude 2 leads by +0.1
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
Claude 2
11.7
GPT-3.5 Turbo (older v0613)
11.6
MMLU
Claude 2 leads by +14.9
Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge.
Claude 2
71.3
GPT-3.5 Turbo (older v0613)
56.4
Winogrande
PaLM 2-L leads by +2.8
WinoGrande · large-scale commonsense reasoning benchmark where models must resolve ambiguous pronouns in carefully constructed sentence pairs.
PaLM 2-L
66.0
GPT-3.5 Turbo (older v0613)
63.2
Full benchmark table
BenchmarkClaude 2PaLM 2-LGPT-3.5 Turbo (older v0613)
TriviaQA
TriviaQA · reading comprehension benchmark with trivia questions, requiring models to find and reason over evidence from provided documents.
87.586.185.8
ARC AI2
AI2 Reasoning Challenge · tests grade-school level science knowledge with multiple-choice questions requiring reasoning beyond simple retrieval.
58.983.2
GPQA diamond
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
12.92.9
MATH level 5
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
11.711.6
MMLU
Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge.
71.356.4
Winogrande
WinoGrande · large-scale commonsense reasoning benchmark where models must resolve ambiguous pronouns in carefully constructed sentence pairs.
66.063.2
Pricing · per 1M tokens · projected $/mo at 10M tokens
ModelInputOutputContextProjected $/mo
Anthropic logoClaude 2
U
PaLM 2-L
OpenAI logoGPT-3.5 Turbo (older v0613)$1.00$2.004K tokens (~2 books)$12.50