BenchLeader

Deepseek v4 Pro vs Kimi K3

Verdict
  • Kimi K3 leads on quality: 66.5 vs 60.4.
  • Deepseek v4 Pro (high) is stronger in reasoning.
  • Kimi K3 is stronger in coding, human preference, maths, agents & tools, composite, knowledge, long context, multimodal.
MetricDeepseek v4 Pro (high)Kimi K3
BenchLeader Index60.466.5
Coding score59.465.0
Human preference score65.871.2
Maths score66.278.1
Reasoning score66.0
Agents & tools score67.4
Composite score74.2
Knowledge score68.2
Long context score71.1
Multimodal score65.0
Blended price $/M$6.00
Output speed38 tok/s
Time to first answer56.3 s
Context window1.0M
GPQA Diamond90.9%
OTIS Mock AIME95.6%
SciCode46.4%58.7%
WeirdML46.5%
APEX-Agents39.3%
FrontierCode44.2%
ProofBench87.0%
Epoch Capabilities Index157.6
LMArena Text1460
LMArena Hard Prompts1482
LMArena Coding1505
LMArena WebDev1580
LiveBench79.2%
LiveBench Reasoning90.7%
LiveBench Coding81.5%
LiveBench Agentic Coding62.2%
LiveBench Mathematics84.4%
LiveBench Data Analysis78.7%
LiveBench Language85.5%
AA Intelligence Index43.8
AA-LCR88.7%
MMMU-Pro80.5%
AA-Omniscience19.7
GPQA Diamond (AA)93.5%
Humanity's Last Exam (AA)46.9%
SciCode (AA)59.5%
LegalBench86.0%
CorpFin71.6%
TaxEval75.7%
Terminal-Bench 2.1 (Vals)80.9%
SWE-bench (Vals)93.4%
GPQA Diamond (Vals)92.9%
Vals Index57.8
EQ-Bench 41339

Data as of 2026-09-10. Best configuration of each model; every score links to its source on the model pages.

Deepseek v4 Pro vs Kimi K3: questions

Is Deepseek v4 Pro better than Kimi K3?
Kimi K3 leads on quality: 66.5 vs 60.4. The BenchLeader Index combines every independent quality benchmark; Kimi K3 is ahead overall as of 2026-09-10, but check the category scores for your use.
Is Deepseek v4 Pro better than Kimi K3 for coding?
Kimi K3 scores higher in coding (65 vs 59 on the category index, where 50 is average).