New Finance Agent Benchmark Released
Logo
grok/grok-2-1212 Grok 2

Released Date: 12/11/2024

Avg. Accuracy:

66.4%

Latency:

21.85s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

CorpFin

58.2%

( 15 / 35 )

CaseLaw

78.6%

( 24 / 55 )

ContractLaw

58.0%

( 57 / 62 )

TaxEval

71.4%

( 21 / 42 )

Math500

78.4%

( 21 / 38 )

AIME

15.2%

( 23 / 34 )

MGSM

86.3%

( 27 / 36 )

MedQA

92.3%

( 7 / 40 )

GPQA

50.0%

( 23 / 35 )

MMLU Pro

75.5%

( 17 / 35 )

Academic Benchmarks
Proprietary Benchmarks (contact us to get access)

Cost Analysis

Input Cost

$2.00 / M Tokens

Output Cost

$10.00 / M Tokens

Input Cost (per char)

$0.53 / M chars

Output Cost (per char)

$2.88 / M chars

Overview

Grok 2 is the latest model from xAI. Unlike Grok 1, it is closed-source.

During its released, xAI claims that it surpasses Claude 3.5 Sonnet and GPT-4o Mini in the LMSYS chat-bot arena, although it loses to 4o and Gemini 1.5 Pro.

Key Specifications

  • Context Window: 131,072 tokens
  • Pricing:
    • Input: $2.00 per million tokens
    • Output: $10.00 per million tokens
Join our mailing list to receive benchmark updates on

Stay up to date as new benchmarks and models are released.