Noometry

Model comparison

Gemini 2.5 Pro vs Grok 4.5

Grok 4.5 is the stronger model overall, scoring 55.0 to 45.0 on the Noometry Index.

Last verified . 40 shared benchmarks.

Gemini 2.5 Pro Google

45.0

Rank #75 Confirmed

Grok 4.5 xAI

55.0

Rank #25 Confirmed

Summary

  • They share 40 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 3 categories and Grok 4.5 in 7 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Grok 4.5 leads 60.9 to 32.5.
  • The biggest single-benchmark swing is ARC-AGI-2: 4.9% for Gemini 2.5 Pro and 52.6% for Grok 4.5.
  • Grok 4.5 is cheaper at $2 / $6 per million input/output tokens, against $1.25 / $10 for Gemini 2.5 Pro.
  • Gemini 2.5 Pro accepts more context: 1.05M tokens versus 500K.

Side by side

Gemini 2.5 ProGrok 4.5
ProviderGooglexAI
Noometry Index45.055.0
Released2025-03-252026-07-08
WeightsProprietaryProprietary
Context window1.05M500K
Max output66K500K
Input $ / M tokens$1.25$2
Output $ / M tokens$10$6
Results tracked7852

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

Category by category

Coding Grok 4.5 leads

Gemini 2.5 Pro: 42.4 (#101), Grok 4.5: 52.2 (#35)

BenchmarkGemini 2.5 ProGrok 4.5
LMArena WebDev12271553
SciCode42.8%54.1%
WeirdML54%46.4%
LMArena Coding14521474
ALE-Bench785.521,309
SWE-bench Verified57.6%—
DeepSWE—53.8%
FrontierCode—42.4%
SWE-bench Verified (bash only)53.6%—
Aider Polyglot83.1%—
GSO3.9%—
LiveBench Coding85.9%—
CadEval64%—
AlgoTune1.51—

Agentic & Tool Use Grok 4.5 leads

Gemini 2.5 Pro: 29.2 (#88), Grok 4.5: 44.4 (#17)

BenchmarkGemini 2.5 ProGrok 4.5
τ²-bench Banking13.7%47.9%
LMArena Search11421213
Vending-Bench 2573.643,887
Terminal-Bench32.6%—
APEX-Agents—56.2%
GDPval23.3%—
Remote Labor Index0.8%—
TheAgentCompany30.3%—
DeepResearch Bench42.8%—
PostTrainBench—23.4%
BALROG43.3%—
GBAEval—65.4%
GDP.pdf—14%
METR Time Horizons55.4%—

Reasoning Grok 4.5 leads

Gemini 2.5 Pro: 28.8 (#99), Grok 4.5: 56.1 (#25)

BenchmarkGemini 2.5 ProGrok 4.5
ARC-AGI-24.9%52.6%
SimpleBench62.4%70%
Kagi LLM Benchmark70.3%83.5%
ARC-AGI-141%87.2%
CritPt2%15.4%
Chess Puzzles20%36%
LMArena Hard Prompts14551462
DTBench82.4%96.5%
LMCA34.8%45.2%
Epoch Capabilities Index145.32153.92
NYT Connections (extended)—79.9%
EnigmaEval5.6%—
LiveBench Reasoning89.8%—
LiveBench Data Analysis79.9%—
Surface Evolver Bench—74.4%
ForecastBench61.3—
LiveBench82.3%—

Math Grok 4.5 leads

Gemini 2.5 Pro: 32.5 (#213), Grok 4.5: 60.9 (#35)

BenchmarkGemini 2.5 ProGrok 4.5
FrontierMath (Tiers 1-3)24.6%57.2%
FrontierMath Tier 40%24.4%
OTIS Mock AIME 2024-202584.7%97.8%
LMArena Math14501459
ProofBench—31%
Omni-MATH41.6%—
LiveBench Math90.2%—
MATH Level 595.9%—
FrontierMath (Feb 2025 set)14.1%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Grok 4.5 leads

Gemini 2.5 Pro: 56.0 (#46), Grok 4.5: 62.3 (#24)

BenchmarkGemini 2.5 ProGrok 4.5
GPQA Diamond85.3%93.4%
LMArena Expert14521466
Humanity's Last Exam21.6%—
SimpleQA Verified—48.3%
MMLU-Pro86.3%—
Confabulations10.6%—
Vectara Hallucination Rate7%—
GPQA (HELM)74.9%—

Multimodal Gemini 2.5 Pro leads

Gemini 2.5 Pro: 45.2 (#18), Grok 4.5: 37.6 (#72)

BenchmarkGemini 2.5 ProGrok 4.5
LMArena Vision12631288
LMArena Document14211452
GeoBench86%—
VPCT48%—
Blueprint-Bench 2—27.3%
Furniture Assembly—22.5%
SpatialViz-Bench44.7%—

Multilingual Too close to call

Gemini 2.5 Pro: 55.3 (#31), Grok 4.5: 54.4 (#42)

BenchmarkGemini 2.5 ProGrok 4.5
LMArena Non-English14511440
LMArena Chinese15071496
LMArena French14721456
LMArena German14871446
LMArena Japanese14611428
LMArena Korean14341404
LMArena Russian14611448
LMArena Spanish14731450

Instruction Following Grok 4.5 leads

Gemini 2.5 Pro: 75.0 (#75), Grok 4.5: 76.0 (#48)

BenchmarkGemini 2.5 ProGrok 4.5
LMArena Instruction Following14371446
LiveBench Instruction Following80.6%—
IFEval84%—

Long Context Gemini 2.5 Pro leads

Gemini 2.5 Pro: 59.8 (#5), Grok 4.5: 44.8 (#56)

BenchmarkGemini 2.5 ProGrok 4.5
LMArena Longer Query14491463
Fiction.LiveBench91.7%—

Writing & Preference Grok 4.5 leads

Gemini 2.5 Pro: 63.7 (#62), Grok 4.5: 65.8 (#42)

BenchmarkGemini 2.5 ProGrok 4.5
LMArena Text14581448
LMArena Creative Writing14541442
EQ-Bench Creative Writing14211579
LMArena Multi-Turn14531456
Short-Story Creative Writing83.8%—
WildBench85.7%—
LiveBench Language67.8%—

Frequently asked questions

Is Gemini 2.5 Pro better than Grok 4.5?

Grok 4.5 is the stronger model overall, scoring 55.0 to 45.0 on the Noometry Index.

Which is cheaper, Gemini 2.5 Pro or Grok 4.5?

Grok 4.5 is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; Gemini 2.5 Pro lists at $1.25 and $10.

Is Gemini 2.5 Pro or Grok 4.5 better for coding?

Grok 4.5 scores higher on coding benchmarks: 52.2 versus 42.4 in the Noometry coding category.

Which has the bigger context window?

Gemini 2.5 Pro does, with 1.05M tokens against 500K.

How many benchmarks do Gemini 2.5 Pro and Grok 4.5 share?

40 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and Grok 4.5 has 52.

Related comparisons

Go deeper