Model comparison

Claude 2 vs Palm 2

Palm 2 is the stronger model overall, scoring 30.0 to 25.0 on the Noometry Index.

Last verified . 0 shared benchmarks.

Claude 2 Anthropic

25.0

Rank #346 Reported

Palm 2 Google

30.0

Rank #298 Confirmed

Summary

  • The widest gap is in math, where Palm 2 leads 30.8 to 9.3.

Side by side

Claude 2 and Palm 2 specifications
Claude 2Palm 2
ProviderAnthropicGoogle
Noometry Index25.030.0
Released2023-07-11—
WeightsProprietaryProprietary
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked810

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Not comparable

Claude 2: —, Palm 2: 29.0 (#311)

Coding benchmarks
BenchmarkClaude 2Palm 2
LMArena Coding—994
HumanEval+61.6%—

Reasoning Claude 2 leads

Claude 2: 21.7 (#216), Palm 2: 19.1 (#271)

Reasoning benchmarks
BenchmarkClaude 2Palm 2
LMArena Hard Prompts—1005
DTBench51.9%—
Epoch Capabilities Index120.13—

Math Palm 2 leads

Claude 2: 9.3 (#320), Palm 2: 30.8 (#231)

Math benchmarks
BenchmarkClaude 2Palm 2
OTIS Mock AIME 2024-20252.5%—
LMArena Math—1049
MATH Level 511.7%—

Knowledge Not comparable

Claude 2: 16.9 (#287), Palm 2: —

Knowledge benchmarks
BenchmarkClaude 2Palm 2
GPQA Diamond34.7%—
MMLU78.5%—
TriviaQA87.5%—

Multilingual Not comparable

Claude 2: —, Palm 2: 20.9 (#295)

Multilingual benchmarks
BenchmarkClaude 2Palm 2
LMArena Non-English—916
LMArena Chinese—887

Instruction Following Not comparable

Claude 2: —, Palm 2: 51.0 (#296)

Instruction Following benchmarks
BenchmarkClaude 2Palm 2
LMArena Instruction Following—1010

Long Context Not comparable

Claude 2: —, Palm 2: 30.8 (#285)

Long Context benchmarks
BenchmarkClaude 2Palm 2
LMArena Longer Query—1010

Writing & Preference Not comparable

Claude 2: —, Palm 2: 25.6 (#304)

Writing & Preference benchmarks
BenchmarkClaude 2Palm 2
LMArena Text—1027
LMArena Creative Writing—991
LMArena Multi-Turn—994

Frequently asked questions

Is Claude 2 better than Palm 2?

Palm 2 is the stronger model overall, scoring 30.0 to 25.0 on the Noometry Index.

How many benchmarks do Claude 2 and Palm 2 share?

0 benchmarks have published results for both models. Claude 2 has 8 scored results on Noometry and Palm 2 has 10.

Related comparisons

Go deeper