Skip to main content
BenchLM
Advertise

Model comparison

DeepSeek V4 Flash (High) vs Gemini 3.1 Pro

Data verified

Head-to-head evidence from 17 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

53.95/100
Margin
1.3pts
winning →
55.3/100
1 category wins0 category wins

Public leaderboard positions: DeepSeek V4 Flash (High) #92 (Estimated); Gemini 3.1 Pro #83 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. DeepSeek V4 Flash (High) and Gemini 3.1 Pro share 17 comparable benchmark results. 1 of 8 categories are comparable. 21 results are unique to DeepSeek V4 Flash (High); 30 to Gemini 3.1 Pro.

Updated July 23, 2026
Shared results
17
DeepSeek V4 Flash (High) only
21
Gemini 3.1 Pro only
30
Comparable categories
1 / 8

Pick Gemini 3.1 Pro if you want the stronger benchmark profile. DeepSeek V4 Flash (High) only becomes the better choice if mathematics is the priority or you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 17 shared benchmark results across 6 evidence categories; 1 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Gemini 3.1 Pro has the cleaner BenchAlign overall profile here, landing at 55.3 versus 53.95. It is a real lead, but still close enough that category-level strengths matter more than the headline number.

Gemini 3.1 Pro is also the more expensive model on tokens at $2.00 input / $12.00 output per 1M tokens, versus $0.14 input / $0.28 output per 1M tokens for DeepSeek V4 Flash (High). That is roughly 42.9x on output cost alone. DeepSeek V4 Flash (High) is the reasoning model in the pair, while Gemini 3.1 Pro is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for DeepSeek V4 Flash (High) and Gemini 3.1 Pro
CategoryDeepSeek V4 Flash (High)ΔGemini 3.1 Pro
MathDeepSeek V4 Flash (High)91.9Margin← 60.1Gemini 3.1 Pro31.8
AgenticDeepSeek V4 Flash (High)55.3MarginNo overlapGemini 3.1 ProNot measured
CodingDeepSeek V4 Flash (High)68.5MarginNo overlapGemini 3.1 ProNot measured
ReasoningDeepSeek V4 Flash (High)Not measuredMarginNo overlapGemini 3.1 Pro77.1
KnowledgeDeepSeek V4 Flash (High)52.1MarginNo overlapGemini 3.1 ProNot measured
MultimodalDeepSeek V4 Flash (High)Not measuredMarginNo overlapGemini 3.1 Pro82.6

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricDeepSeek V4 Flash (High)Gemini 3.1 ProComparison
Input / output priceUSD per 1M tokensDeepSeek V4 Flash (High)$0.14 input / $0.28 outputGemini 3.1 Pro$2 input / $12 outputDeepSeek V4 Flash (High) has the lower combined listed price.
Generation speedtokens per secondDeepSeek V4 Flash (High)Not availableGemini 3.1 Pro109 tok/sA complete speed comparison is not available.
First-answer latencyseconds to first tokenDeepSeek V4 Flash (High)Not availableGemini 3.1 Pro29.71 sA complete latency comparison is not available.
Context windowmaximum listed tokensDeepSeek V4 Flash (High)1MGemini 3.1 Pro1MListed context windows are equal.

Benchmark Deep Dive

Agentic
BenchmarkDeepSeek V4 Flash (High)Gemini 3.1 ProResult
Terminal-Bench 2.0Source 56.6%—Not comparable
BrowseCompSource 53.5%—Not comparable
HLE w/ toolsSource 40.3%—Not comparable
MCP AtlasSource 67.4%—Not comparable
ToolathlonSource 43.5%—Not comparable
τ²-bench resultsSource 95.6%95.6%Tie
AA Agentic IndexSource 28.2%21.4%DeepSeek V4 Flash (High) leads
GDPval-AASource 32.4%23.3%DeepSeek V4 Flash (High) leads
GDPval-AASource 1147965DeepSeek V4 Flash (High) leads
Claw-EvalSource —57.8%Not comparable
DeepSearchQASource —69.7%Not comparable
APEX-Agents-AASource —32.0%Not comparable
Gert LabsSource —56.87%Not comparable
ResearchClawBenchSource —13.3%Not comparable
AA AutomationBenchSource —37.5%Not comparable
AA EnterpriseOps-GymSource —42.2%Not comparable
AA Harvey LABSource —58.9%Not comparable
AA ITBenchSource —30.3%Not comparable
AA Tau3 BankingSource —16.5%Not comparable
terminalBenchHardSource —53.8%Not comparable
aaTerminalBench21Source —73.8%Not comparable
Coding
BenchmarkDeepSeek V4 Flash (High)Gemini 3.1 ProResult
CodeforcesSource 2816.0—Not comparable
SWE-bench VerifiedSource 78.6%—Not comparable
SWE-bench ProSource 52.3%—Not comparable
SWE MultilingualSource 70.2%—Not comparable
Terminal-Bench 2.0Source 56.6%—Not comparable
AA-SciCodeSource 42.0%58.9%Gemini 3.1 Pro leads
AA Coding IndexSource 52.0%68.8%Gemini 3.1 Pro leads
LiveCodeBench ProSource —82.9%Not comparable
React Native EvalsSource —78.9%Not comparable
Vibe Code BenchSource —32.03%Not comparable
Reasoning
BenchmarkDeepSeek V4 Flash (High)Gemini 3.1 ProResult
MRCR 1MSource 76.9%—Not comparable
CorpusQA 1MSource 59.3%—Not comparable
AA-LCRSource 62.7%72.7%Gemini 3.1 Pro leads
CritPtSource 3.4%17.7%Gemini 3.1 Pro leads
ARC-AGI-2Source —77.1%Not comparable
Knowledge
BenchmarkDeepSeek V4 Flash (High)Gemini 3.1 ProResult
MMLU-ProSource 86.4%—Not comparable
SimpleQASource 28.9%—Not comparable
Chinese-SimpleQASource 73.2%—Not comparable
GPQASource 87.4%—Not comparable
GPQA-DSource 87.4%94.3%Gemini 3.1 Pro leads
HLESource 29.4%—Not comparable
Artificial Analysis Intelligence IndexSource 37.5%46.5%Gemini 3.1 Pro leads
AA-GPQA DiamondSource 86.7%94.1%Gemini 3.1 Pro leads
AA-HLESource 27.8%44.7%Gemini 3.1 Pro leads
AA-Omniscience IndexSource -22.3%32.9%Gemini 3.1 Pro leads
AA-Omniscience AccuracySource 35.5%55.3%Gemini 3.1 Pro leads
AA-Omniscience Hallucination RateSource 89.7%49.9%Gemini 3.1 Pro leads
HLE w/o toolsSource —45.4%Not comparable
HealthBench HardSource —20.6%Not comparable
MedXpertQA (Text)Source —71.5%Not comparable
MathDeepSeek V4 Flash (High) wins
BenchmarkDeepSeek V4 Flash (High)Gemini 3.1 ProResult
HMMT Feb 2026Source 91.9%—Not comparable
IMOAnswerBenchSource 85.1%—Not comparable
ApexSource 19.1%—Not comparable
Apex ShortlistSource 72.1%—Not comparable
FrontierMath v2 (Tiers 1-3)Source —36.900%Not comparable
FrontierMath v2 (Tier 4)Source —16.700%Not comparable
Multilingual
BenchmarkDeepSeek V4 Flash (High)Gemini 3.1 ProResult
AA Global-MMLU-LiteSource —93.2%Not comparable
Multimodal
BenchmarkDeepSeek V4 Flash (High)Gemini 3.1 ProResult
Design Arena WebsiteSource 12381281Gemini 3.1 Pro leads
MMMU-ProSource —83.9%Not comparable
CharXivSource —80.2%Not comparable
ERQASource —69.4%Not comparable
SimpleVQASource —72.4%Not comparable
ScreenSpot ProSource —84.4%Not comparable
ZeroBenchSource —29.0%Not comparable
MedXpertQA (MM)Source —81.3%Not comparable
AA-MMMU-ProSource —82.4%Not comparable
Inst. Following
BenchmarkDeepSeek V4 Flash (High)Gemini 3.1 ProResult
AA-IFBenchSource 73.5%77.1%Gemini 3.1 Pro leads
Frequently Asked Questions (2)

Which is better, DeepSeek V4 Flash (High) or Gemini 3.1 Pro?

Gemini 3.1 Pro is ahead on BenchLM's BenchAlign leaderboard, 55.3 to 53.95.

Which is better for math, DeepSeek V4 Flash (High) or Gemini 3.1 Pro?

DeepSeek V4 Flash (High) has the edge for math in this comparison, averaging 91.9 versus 31.8. Gemini 3.1 Pro stays close enough that the answer can still flip depending on your workload.

Related Comparisons

Explore More

DeepSeek Compare Pricing Methodology Find Your Best LLM Overall Rankings
Last updated: July 23, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.