modelbenchmark.io

DeepSeek V4 Pro 0813

DeepSeek · deepseek-v4-pro-ga-260813

Compare

DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes

Specification

most-agreed values

Context
1M
Max output
384K
Released
2026-08-12
Knowledge cutoff
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$1.3359
Output
$4.0077
Cache read
$0.0445

Quality

8 benchmarks · 2 sources

Composite
91st
percentile of 334 scored models
Rank
30 / 334
±0.08 sd
Evidence
8 × 2
3 or more benchmarks, from 2 or more sources
Effort range
one configuration only
reasoning97th3/4 bench
math83rd3/7 bench
knowledge78th1/1 bench
general71st1/1 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
Chess Puzzles47.0 ±5.0maxEpoch AI2026-08-18
Mystery Game Puzzles43.0 ±5.0maxEpoch AI2026-08-19
OTIS Mock AIME 2024-202598.6 ±1.0maxEpoch AI2026-08-18
GPQA diamond91.7 ±1.5maxEpoch AI2026-08-18
FrontierMath-Tiers-1-3-v264.6 ±2.8maxEpoch AI2026-08-19
SimpleQA Verified52.9 ±1.6maxEpoch AI2026-08-27
LiveBench78.2default · 23 runsLiveBench2026-06-25
FrontierMath-Tier-4-v226.8 ±7.0maxEpoch AI2026-08-19

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
volcengine$1.3359$4.0077$0.04451M384K

More from DeepSeek

most-hosted first