DeepSeek V4 Pro 0424 (Reasoning, Max Effort)

DeepSeekDeepSeek

Release Date

2026-04-24

Parameters

—

Context Length

—

Modalities

—

Capability Radar

general

coding

reasoning

science

agents

multimodal

Rankings

Domain	#Rank	Score	Source
Code Ranking	133	75.0	AA
General Ranking	53	72.0	AA
Science	87	75.0	AA

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

No benchmark data available

AA Evaluation Indices

(Artificial Analysis)

Tau2(Sierra + U Toronto + Vector Institute (2025))

96.2

Gpqa(NYU + Cohere + Anthropic (2023))

88.8

Ifbench(Google Research (2023))

76.5

Lcr(Artificial Analysis)

74.7

Terminalbench V2 1

64.0

Coding Index(Artificial Analysis)

59.4

Scicode(UIUC + Argonne National Lab (2024))

50.8

Terminalbench Hard(Stanford × Laude Institute (2026))

46.2

Hle(Center for AI Safety + Scale AI (2025))

37.5

Intelligence Index(Artificial Analysis)

30.4

Tau Banking

30.1

LLM Stats Category Scores

(LLM Stats (zeroeval))

No category score data available

Pricing

Input Price$0.435 / 1M tokens

Output Price$0.87 / 1M tokens

Blended Price (3:1)$0.544 / 1M tokens

Speed

Tokens/sec0.0

Time to First Token0.00s

Time to Answer0.00s

Provider Price Ranking

1 providers

ProviderInputOutput

1DeepSeekPRIMARY

$0.435

$0.87

Compare pricing across different API providers for this model.

External Sources

Artificial Analysis