DeepSeek-V2.5 (Dec ’24)

DeepSeek-V2.5 (Dec ’24)

DeepSeek · Released Dec 10, 2024 Emerging
Intelligence #500 / 556
10.7 Our Score
AA Index #267 / 365
12.5 Artificial Analysis
Input
Not priced
Output
Not priced
Context
Not reported

Analysis Summary

DeepSeek-V2.5 (Dec ’24) sits in the Emerging tier on our leaderboard, ranked #500 of 556 published models on overall intelligence. At $0.000 input and $0.000 output per 1M tokens, it is among the most expensive on the market.

Editorial notes

DeepSeek-V2.5 (Dec 2024) has limited benchmark data beyond its intelligence index and has been superseded by DeepSeek V3 and V4 releases with substantially stronger performance.

Assessed May 14, 2026

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

Performance Profile

Intelligence2.3Technical0Value0Content2.5
Intelligence 2.3/10
Technical 0/10
Content 2.5/10
Value 0/10

Performance Indices

Source: Artificial Analysis

12.5 Intelligence Index

Benchmark Scores

Intelligence

MATH 500 76.3% Mathematical problem-solving

Benchmark data from Artificial Analysis and Hugging Face

How does DeepSeek-V2.5 (Dec ’24) stack up?

Compare side-by-side with other emerging models.

Compare Models

Model Information

ProviderDeepSeek
Release Date December 10, 2024
Status Active