The Model Index
Up to four models

DeepSeek-V4-Pro vs Gemini 3.1 Pro

On the index (GPT-4 = 100), DeepSeek-V4-Pro scores 163 and Gemini 3.1 Pro 161. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Next to DeepSeek-V4-Pro
Presets
DeepSeek-V4-Pro
163147–178
WeightsOpen
ReleasedAug 2026
Price in / out$0.11 / $4.44
Context1.05M
Core tests taken6 of 9
Gemini 3.1 Pro
161146–177
WeightsClosed
ReleasedFeb 2026
Price in / out$2.0 / $12
Context1.05M
Core tests taken9 of 9

DeepSeek-V4-Pro and Gemini 3.1 Pro are too close to call (1 point apart, within the uncertainty), ahead on 4 of 6 shared core tests, and costs 3.8× less.

Test by testthird-party results

DeepSeek-V4-ProGemini 3.1 Pro
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)GPQA Diamond (Vals AI)GPQA Diamond (Vals AI)MMLU ProMMLU ProSimpleQA VerifiedSimpleQA VerifiedMATHSFrontierMath (tiers 1-3)FrontierMath (tiers 1-3)AIME-style maths (OTIS mock)AIME-style maths (OTIS mock)ProofBench v1.1ProofBench v1.1Chess puzzlesChess puzzlesFrontierMath (tier 4)FrontierMath (tier 4)CODINGTerminal-Bench 4.0Terminal-Bench 4.0Code MigrationCode MigrationIOIIOILiveCodeBenchLiveCodeBenchProgramBenchProgramBenchSWE-benchSWE-benchVibe Code Bench 1-100Vibe Code Bench 1-100Vibe Code Bench v1.1Vibe Code Bench v1.1MirrorCodeMirrorCodeWeirdMLWeirdMLAGENTSAPEX-AgentsAPEX-AgentsSRE BenchSRE BenchTerminal-Bench-ScienceTerminal-Bench-ScienceDTBenchDTBenchLMCALMCAMystery game puzzlesMystery game puzzlesPROFESSIONAL WORKFinance Agent (v2)Finance Agent (v2)CorpFin v2CorpFin v2EMBEMBLegalBenchLegalBenchLegal Research BenchLegal Research BenchMedCodeMedCodeMedScribeMedScribeTax Agent BenchTax Agent BenchTaxEval v2TaxEval v2NOVEL PROBLEMSARC-AGI-2ARC-AGI-2ARC-AGI-1ARC-AGI-1
Every result as a table
TestDeepSeek-V4-ProGemini 3.1 Pro
Reasoning & knowledge
GPQA Diamond (Epoch AI)91.7%94.4%
GPQA Diamond (Vals AI)92.4%95.5%
MMLU Pro87.0%91.0%
SimpleQA Verified52.9%73.5%
Maths
FrontierMath (tiers 1-3)64.6%59.7%
AIME-style maths (OTIS mock)98.6%95.6%
ProofBench v1.150.0%26.0%
Chess puzzles46.0%51.0%
FrontierMath (tier 4)26.8%26.8%
Coding
Terminal-Bench 4.014.1%2.5%
Code Migration41.5%17.3%
IOI51.6%51.8%
LiveCodeBench87.5%88.5%
ProgramBench0.0%0.0%
SWE-bench96.4%78.8%
Vibe Code Bench 1-10017.5%6.7%
Vibe Code Bench v1.182.3%32.0%
MirrorCode33.3%8.9%
WeirdML66.2%72.1%
Agents
APEX-Agents47.3%35.1%
SRE Bench1.9%0.0%
Terminal-Bench-Science4.3%1.4%
DTBench93.9%97.1%
LMCA45.5%53.8%
Mystery game puzzles43.0%34.0%
Professional work
Finance Agent (v2)50.4%43.0%
CorpFin v265.4%64.5%
EMB52.8%52.6%
LegalBench82.4%87.4%
Legal Research Bench40.9%20.7%
MedCode42.5%59.1%
MedScribe80.2%76.1%
Tax Agent Bench26.8%9.3%
TaxEval v273.1%72.9%
Novel problems
ARC-AGI-261.3%77.1%
ARC-AGI-190.5%98.0%
Task length · METR46 sec

Tests at least two of these models have taken. Bold rows are the core tests.

This page as a chartDownload PNG