BenchLeader

DeepSeek V4 Pro vs Gemini 3.1 Pro

Verdict
  • DeepSeek V4 Pro (max) and Gemini 3.1 Pro are level on quality (64.2 vs 63.9).
  • DeepSeek V4 Pro (max) is stronger in agents & tools, composite, instruction following, reasoning.
  • Gemini 3.1 Pro is stronger in coding, knowledge, long context, maths, human preference, multimodal.
  • DeepSeek V4 Pro (max) is 8.3× cheaper ($0.544 vs $4.50 per 1M blended).
  • Gemini 3.1 Pro streams 1.5× faster (121 vs 81 tokens per second).
MetricDeepSeek V4 Pro (max)Gemini 3.1 Pro
BenchLeader Index64.263.9
Agents & tools score70.260.4
Coding score58.859.8
Composite score75.067.5
Instruction following score74.369.7
Knowledge score58.165.9
Long context score66.667.5
Maths score53.761.9
Reasoning score70.970.8
Human preference score59.8
Multimodal score66.0
Blended price $/M$0.544$4.50
Output speed81 tok/s121 tok/s
Time to first answer55.6 s34.8 s
Context window1M1.0M
GPQA Diamond89.7%94.1%
FrontierMath Tiers 1–345.3%59.6%
FrontierMath Tier 42.4%26.8%
OTIS Mock AIME96.7%95.6%
SWE-bench Verified (Epoch)77.6%
SimpleQA Verified47.0%
Humanity's Last Exam46.4%
Terminal-Bench80.2%
SimpleBench79.6%
SciCode50.0%58.9%
WeirdML48.9%72.1%
APEX-Agents33.5%
ProofBench16.0%26.0%
GSO-Bench22.6%
Epoch Capabilities Index155
LMArena Text1487
LMArena Hard Prompts1508
LMArena Coding1520
LMArena WebDev1447
LMArena Vision1296
LMArena Agent-5.8
AA Intelligence Index36.330.4
IFBench76.5%77.1%
AA-LCR80.3%82.0%
MMMU-Pro82.4%
AA-Omniscience0.831.9
Terminal-Bench Hard46.2%53.8%
GPQA Diamond (AA)92.8%94.1%
Humanity's Last Exam (AA)41.0%47.0%
SciCode (AA)51.0%58.7%
τ²-Bench Telecom (AA)96.2%95.6%
LiveCodeBench87.5%
MMLU-Pro87.3%
LegalBench80.3%
CorpFin61.4%
TaxEval72.1%
SWE-bench (Vals)77.4%
GPQA Diamond (Vals)89.4%
Vals Index42.9
AIME 202696.7%98.3%
HMMT February 202693.9%94.7%
MathArena Apex28.1%60.9%
MultiChallenge71.4%
PRBench Finance41.9%
PRBench Legal44.0%
MultiNRC64.7%
HiL-Bench35.3%
TutorBench53.0%
EQ-Bench 41142
ARC-AGI-198.0%
ARC-AGI-277.1%
ARC-AGI-30.4%
CritPt18.0%17.7%
GDPval (AA)49.7%20.2%
τ²-Bench Banking (AA)39.6%21.4%
ITBench SRE (AA)38.3%30.3%
Analyst Agent (AA)18.8%41.3%
APEX-Agents (AA)24.3%32.0%
CaseLaw v259.4%
Code Migration26.2%
CyberBench36.4%
Excel Modeling Benchmark51.6%
Finance Agent v244.1%
Harvey's Legal Agent Benchmark3.8%
Legal Research Bench23.1%
MedCode40.5%
MedScribe75.1%
ProgramBench0.0%
Public Benefits Bench62.9%
SkillsBench51.3%
Vibe Code Bench v1.149.9%
FORTRESS29.8%
MASK42.4%
SWE Atlas: Codebase QnA13.5%
SWE Atlas: Refactoring33.8%
SWE Atlas: Test Writing29.8%
VTB29.0%
LMArena Maths1489
LMArena Creative Writing1480
LMArena Instruction Following1481
LMArena Multi-turn1495
LMArena Longer Queries1500
LMArena Document1459
Chess Puzzles20.0%55.0%
EBR-bench14.3%
BALROG57.0%
PostTrainBench22.0%
ExploitBench26.1%
CL-bench20.8%
CL-bench Life16.9%
METR Time Horizons77.0%
DeepSWE11.7%
LMCA41.2%
DTBench90.7%
ForecastBench59.0%
GBAEval0.8%
ALE-Bench1160.6
AlgoTune2.0
Vending-Bench 2911.2
Blueprint-Bench 226.5%
GDP.pdf17.0%

Data as of 2026-09-19. Best configuration of each model; every score links to its source on the model pages.

DeepSeek V4 Pro vs Gemini 3.1 Pro: questions

Is DeepSeek V4 Pro better than Gemini 3.1 Pro?
DeepSeek V4 Pro (max) and Gemini 3.1 Pro are level on quality (64.2 vs 63.9). The BenchLeader Index combines every independent quality benchmark; DeepSeek V4 Pro (max) is ahead overall as of 2026-09-19, but check the category scores for your use.
Is DeepSeek V4 Pro better than Gemini 3.1 Pro for coding?
Gemini 3.1 Pro scores higher in coding (60 vs 59 on the category index, where 50 is average).
Is DeepSeek V4 Pro better than Gemini 3.1 Pro for agentic tasks?
DeepSeek V4 Pro scores higher in agentic tasks (70 vs 60 on the category index, where 50 is average).
Which is cheaper, DeepSeek V4 Pro or Gemini 3.1 Pro?
DeepSeek V4 Pro is cheaper: $0.544 against $4.50 per million tokens, blended at three input tokens per output token.
Which is faster, DeepSeek V4 Pro or Gemini 3.1 Pro?
Gemini 3.1 Pro streams faster: 121 against 81 output tokens per second.
Which has the larger context window?
Gemini 3.1 Pro accepts more context: 1.0M against 1M tokens.