Noometry

Model comparison

Gemini 3.1 Pro Preview vs GPT-4V

Gemini 3.1 Pro Preview has enough public results to be ranked (#23); GPT-4V does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

Gemini 3.1 Pro Preview Google

56.7

Rank #23 Confirmed

GPT-4V OpenAI

36.4

Unranked Sparse

Summary

  • The widest gap is in multimodal, where Gemini 3.1 Pro Preview leads 37.9 to 33.2.

Side by side

Gemini 3.1 Pro PreviewGPT-4V
ProviderGoogleOpenAI
Noometry Index56.736.4
Released2026-02-192023-11-06
WeightsProprietaryProprietary
Context window1.05M—
Max output66K—
Input $ / M tokens$2—
Output $ / M tokens$12—
Results tracked711

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Not comparable

Gemini 3.1 Pro Preview: 42.5 (#99), GPT-4V: —

BenchmarkGemini 3.1 Pro PreviewGPT-4V
SWE-bench Verified75.6%—
DeepSWE11.7%—
LMArena WebDev1447—
SciCode58.9%—
GSO22.6%—
WeirdML72.1%—
LMArena Coding1484—
MirrorCode8.9%—
ALE-Bench1,161—
AlgoTune2.02—

Agentic & Tool Use Not comparable

Gemini 3.1 Pro Preview: 37.7 (#34), GPT-4V: —

BenchmarkGemini 3.1 Pro PreviewGPT-4V
Terminal-Bench80.2%—
APEX-Agents35.3%—
τ²-bench Banking26%—
DeepResearch Bench47.8%—
PostTrainBench22%—
BALROG57%—
ExploitBench26.1%—
GBAEval0.8%—
GDP.pdf17%—
LMArena Search1211—
METR Time Horizons77%—
Vending-Bench 23,774—

Reasoning Not comparable

Gemini 3.1 Pro Preview: 71.7 (#12), GPT-4V: —

BenchmarkGemini 3.1 Pro PreviewGPT-4V
ARC-AGI-277.1%—
SimpleBench79.6%—
NYT Connections (extended)97.4%—
ARC-AGI-198%—
CritPt17.7%—
Chess Puzzles55%—
EnigmaEval36.8%—
Thematic Generalization79.4%—
EBR-Bench14.3%—
LMArena Hard Prompts1485—
Mystery Game Puzzles34%—
DTBench97.1%—
LMCA53.8%—
Epoch Capabilities Index154.77—
ForecastBench59—

Math Not comparable

Gemini 3.1 Pro Preview: 62.1 (#34), GPT-4V: —

BenchmarkGemini 3.1 Pro PreviewGPT-4V
FrontierMath (Tiers 1-3)59.6%—
FrontierMath Tier 426.8%—
MathArena Final-Answer Competitions86.5%—
OTIS Mock AIME 2024-202595.6%—
ProofBench26%—
LMArena Math1485—
FrontierMath (Feb 2025 set)36.9%—
FrontierMath Tier 4 (v1)16.7%—

Knowledge Not comparable

Gemini 3.1 Pro Preview: 71.8 (#3), GPT-4V: —

BenchmarkGemini 3.1 Pro PreviewGPT-4V
GPQA Diamond94.4%—
Humanity's Last Exam46.4%—
SimpleQA Verified73.5%—
Vectara Hallucination Rate10.4%—
LMArena Expert1485—

Multimodal Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 37.9 (#69), GPT-4V: 33.2

BenchmarkGemini 3.1 Pro PreviewGPT-4V
LMArena Vision1296—
Video-MME—59.9%
Blueprint-Bench 226.5%—
Furniture Assembly26.7%—
LMArena Document1444—

Multilingual Not comparable

Gemini 3.1 Pro Preview: 57.0 (#12), GPT-4V: —

BenchmarkGemini 3.1 Pro PreviewGPT-4V
LMArena Non-English1477—
LMArena Chinese1529—
LMArena French1487—
LMArena German1491—
LMArena Japanese1493—
LMArena Korean1455—
LMArena Russian1498—
LMArena Spanish1479—

Instruction Following Not comparable

Gemini 3.1 Pro Preview: 77.0 (#32), GPT-4V: —

BenchmarkGemini 3.1 Pro PreviewGPT-4V
LMArena Instruction Following1466—

Long Context Not comparable

Gemini 3.1 Pro Preview: 47.4 (#18), GPT-4V: —

BenchmarkGemini 3.1 Pro PreviewGPT-4V
CL-bench20.8%—
CL-bench Life16.9%—
LMArena Longer Query1483—

Writing & Preference Not comparable

Gemini 3.1 Pro Preview: 66.1 (#37), GPT-4V: —

BenchmarkGemini 3.1 Pro PreviewGPT-4V
LMArena Text1481—
LMArena Creative Writing1482—
EQ-Bench Creative Writing1491—
EQ-Bench 41142—
LMArena Multi-Turn1488—

Frequently asked questions

Is Gemini 3.1 Pro Preview better than GPT-4V?

Gemini 3.1 Pro Preview has enough public results to be ranked (#23); GPT-4V does not yet, so treat this comparison as directional.

How many benchmarks do Gemini 3.1 Pro Preview and GPT-4V share?

0 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and GPT-4V has 1.

Related comparisons

Go deeper