DeepSeek V4 Pro (Reasoning, High Effort)
DeepSeekDeepSeek
Release Date
2026-04-24
Parameters
—
Context Length
1.0M
Modalities
text
Capability Radar
42
general
57
coding
91
reasoning
64
science
81
agents
0
multimodal
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 91 | 73.0 | AA |
| General Ranking | 49 | 79.0 | AA |
| Science | 59 | 78.0 | AA |
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))No benchmark data available
AA Evaluation Indices
(Artificial Analysis)Coding Index(Artificial Analysis)58.7
Intelligence Index(Artificial Analysis)43.7
Tau2(Sierra + U Toronto + Vector Institute (2025))0.9
Gpqa(NYU + Cohere + Anthropic (2023))0.9
Ifbench(Google Research (2023))0.7
Lcr(Artificial Analysis)0.7
Terminalbench V2 10.6
Scicode(UIUC + Argonne National Lab (2024))0.5
Terminalbench Hard(Stanford × Laude Institute (2026))0.4
Hle(Center for AI Safety + Scale AI (2025))0.4
Tau Banking0.3
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
Cache Read Price$0.00363 / 1M tokens
Speed
Tokens/sec61.2
Time to First Token1.40s
Time to Answer33.97s
Provider Price Ranking
Provider Price Ranking
1 providers
ProviderInputOutput
1DeepSeekPRIMARY
$0.435
$0.87
Compare pricing across different API providers for this model.