DeepSeek V4 Pro 0813 vs GPT-5.6 Luna
Change modelsDeepSeek V4 Pro 0813DeepSeek
GPT-5.6 LunaOpenAI
IndexAll categories, out of 100.
65.5 ±3.7
65.5 ±2.1
GapIndex points below the top.
Top
Top
CoverageIndex weight that has results.
85%
100% best
SpeedOutput tokens per second.
42/s
51/s best
EloLMArena rating and rank.
—
1431
ReleasedMonth of release.
2026-08
2026-07
Input / 1MUS dollars per 1M input tokens.
$0.111 best
$0.20
Output / 1MUS dollars per 1M output tokens.
$4.44
$1.20 best
Batch output / 1MBatch price per 1M output tokens.
$1.98
$0.60 best
1K chats2K tokens in, 500 out, each.
$2.44
$1.00 best
1K documents20K tokens in, 1K out, each.
$6.66
$5.20 best
1K agent tasks200K tokens in, 20K out, each.
$111.00
$64.00 best
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
63.7
64.7 best
CodingCode writing and repair.
65.1
67.4 best
ReasoningLogic problems and puzzles.
68.5 best
66.3
MultimodalTasks with images and text.
—
65.8
KnowledgeFacts and expert knowledge.
65.0 best
62.1
MultilingualTasks in many languages.
—
53.1
InstructionTasks with strict prompt rules.
62.0 best
48.2
MathMath problems.
64.1
68.4 best
Benchmarks
60 sharedOnly DeepSeek V4 Pro 0813: 27Only GPT-5.6 Luna: 42
DeepSeek V4 Pro 0813
GPT-5.6 Luna