Noometry

Model comparison

Gemini 3.1 Pro Preview vs Grok 4.6

Gemini 3.1 Pro Preview and Grok 4.6 score almost the same on the Noometry Index (56.7 vs 56.9), so choose on price, context window or the category you care about most.

Last verified . 46 shared benchmarks.

Gemini 3.1 Pro Preview Google

56.7

Rank #23 Confirmed

Grok 4.6 xAI

56.9

Rank #21 Confirmed

Summary

  • They share 46 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 6 categories and Grok 4.6 in 4 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Grok 4.6 leads 58.5 to 42.5.
  • The biggest single-benchmark swing is DeepSWE: 11.7% for Gemini 3.1 Pro Preview and 67.5% for Grok 4.6.
  • Grok 4.6 is cheaper at $2 / $6 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.
  • Gemini 3.1 Pro Preview accepts more context: 1.05M tokens versus 500K.

Side by side

Gemini 3.1 Pro PreviewGrok 4.6
ProviderGooglexAI
Noometry Index56.756.9
Released2026-02-192026-08-12
WeightsProprietaryProprietary
Context window1.05M500K
Max output66K500K
Input $ / M tokens$2$2
Output $ / M tokens$12$6
Results tracked7149

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

Category by category

Coding Grok 4.6 leads

Gemini 3.1 Pro Preview: 42.5 (#99), Grok 4.6: 58.5 (#16)

BenchmarkGemini 3.1 Pro PreviewGrok 4.6
DeepSWE11.7%67.5%
LMArena WebDev14471617
SciCode58.9%56.5%
WeirdML72.1%67.3%
LMArena Coding14841465
ALE-Bench1,1611,508
SWE-bench Verified75.6%—
FrontierCode—48%
CursorBench—41.4%
FrontierSWE—25.3%
GSO22.6%—
MirrorCode8.9%—
AlgoTune2.02—

Agentic & Tool Use Grok 4.6 leads

Gemini 3.1 Pro Preview: 37.7 (#34), Grok 4.6: 39.4 (#27)

BenchmarkGemini 3.1 Pro PreviewGrok 4.6
APEX-Agents35.3%65.3%
GDP.pdf17%17.2%
Vending-Bench 23,7749,047
Terminal-Bench80.2%—
τ²-bench Banking26%—
DeepResearch Bench47.8%—
PostTrainBench22%—
BALROG57%—
ExploitBench26.1%—
GBAEval0.8%—
LMArena Search1211—
METR Time Horizons77%—

Reasoning Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.7 (#12), Grok 4.6: 61.4 (#20)

BenchmarkGemini 3.1 Pro PreviewGrok 4.6
ARC-AGI-277.1%67.1%
SimpleBench79.6%75.9%
NYT Connections (extended)97.4%80%
ARC-AGI-198%87.5%
CritPt17.7%19.7%
Chess Puzzles55%40%
EBR-Bench14.3%30.5%
LMArena Hard Prompts14851447
Mystery Game Puzzles34%34%
DTBench97.1%97.3%
LMCA53.8%48.5%
Epoch Capabilities Index154.77156.44
EnigmaEval36.8%—
Thematic Generalization79.4%—
ForecastBench59—

Math Grok 4.6 leads

Gemini 3.1 Pro Preview: 62.1 (#34), Grok 4.6: 67.0 (#24)

BenchmarkGemini 3.1 Pro PreviewGrok 4.6
FrontierMath (Tiers 1-3)59.6%66%
FrontierMath Tier 426.8%31.7%
OTIS Mock AIME 2024-202595.6%99.2%
ProofBench26%51%
LMArena Math14851423
MathArena Final-Answer Competitions86.5%—
FrontierMath (Feb 2025 set)36.9%—
FrontierMath Tier 4 (v1)16.7%—

Knowledge Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.8 (#3), Grok 4.6: 63.3 (#20)

BenchmarkGemini 3.1 Pro PreviewGrok 4.6
GPQA Diamond94.4%94%
SimpleQA Verified73.5%49.3%
LMArena Expert14851467
Humanity's Last Exam46.4%—
Vectara Hallucination Rate10.4%—

Multimodal Grok 4.6 leads

Gemini 3.1 Pro Preview: 37.9 (#69), Grok 4.6: 43.6 (#23)

BenchmarkGemini 3.1 Pro PreviewGrok 4.6
LMArena Vision12961263
Blueprint-Bench 226.5%33.2%
Furniture Assembly26.7%40%
LMArena Document14441452

Multilingual Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 57.0 (#12), Grok 4.6: 53.0 (#74)

BenchmarkGemini 3.1 Pro PreviewGrok 4.6
LMArena Non-English14771420
LMArena Chinese15291480
LMArena French14871461
LMArena German14911431
LMArena Japanese14931376
LMArena Korean14551397
LMArena Russian14981422
LMArena Spanish14791404

Instruction Following Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 77.0 (#32), Grok 4.6: 75.4 (#63)

BenchmarkGemini 3.1 Pro PreviewGrok 4.6
LMArena Instruction Following14661431

Long Context Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 47.4 (#18), Grok 4.6: 44.5 (#66)

BenchmarkGemini 3.1 Pro PreviewGrok 4.6
LMArena Longer Query14831454
CL-bench20.8%—
CL-bench Life16.9%—

Writing & Preference Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 66.1 (#37), Grok 4.6: 62.3 (#80)

BenchmarkGemini 3.1 Pro PreviewGrok 4.6
LMArena Text14811428
LMArena Creative Writing14821428
LMArena Multi-Turn14881425
EQ-Bench Creative Writing1491—
EQ-Bench 41142—

Frequently asked questions

Is Gemini 3.1 Pro Preview better than Grok 4.6?

Gemini 3.1 Pro Preview and Grok 4.6 score almost the same on the Noometry Index (56.7 vs 56.9), so choose on price, context window or the category you care about most.

Which is cheaper, Gemini 3.1 Pro Preview or Grok 4.6?

Grok 4.6 is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.

Is Gemini 3.1 Pro Preview or Grok 4.6 better for coding?

Grok 4.6 scores higher on coding benchmarks: 58.5 versus 42.5 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.1 Pro Preview does, with 1.05M tokens against 500K.

How many benchmarks do Gemini 3.1 Pro Preview and Grok 4.6 share?

46 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and Grok 4.6 has 49.

Related comparisons

Go deeper