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 on 4/6 benchmarks
Claude 2 wins 4 of 6 shared benchmarks. Leads in knowledge · math.
Category leads
knowledge·Claude 2math·Claude 2
Hype vs Reality
Attention vs performance
Claude 2
#186 by perf·no signal
PaLM 2-L
#14 by perf·no signal
GPT-3.5 Turbo (older v0613)
#139 by perf·no signal
Best value
GPT-3.5 Turbo (older v0613)
Claude 2
—
no price
PaLM 2-L
—
no price
GPT-3.5 Turbo (older v0613)
30.5 pts/$
$1.50/M
Vendor risk
Who is behind the model
Anthropic
$380.0B·Tier 1
U
Unknown
private · undisclosed
OpenAI
$840.0B·Tier 1
Head to head
6 benchmarks · 3 models
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
| Benchmark | Claude 2 | PaLM 2-L | GPT-3.5 Turbo (older v0613) |
|---|---|---|---|
TriviaQA TriviaQA · reading comprehension benchmark with trivia questions, requiring models to find and reason over evidence from provided documents. | 87.5 | 86.1 | 85.8 |
ARC AI2 AI2 Reasoning Challenge · tests grade-school level science knowledge with multiple-choice questions requiring reasoning beyond simple retrieval. | — | 58.9 | 83.2 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 12.9 | — | 2.9 |
MATH level 5 MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics. | 11.7 | — | 11.6 |
MMLU Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge. | 71.3 | — | 56.4 |
Winogrande WinoGrande · large-scale commonsense reasoning benchmark where models must resolve ambiguous pronouns in carefully constructed sentence pairs. | — | 66.0 | 63.2 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| — | — | — | — | |
U PaLM 2-L | — | — | — | — |
| $1.00 | $2.00 | 4K tokens (~2 books) | $12.50 |