Noometry

Model comparison

Gemini 2.5 Pro vs Kimi K3

Kimi K3 is the stronger model overall, scoring 59.5 to 45.0 on the Noometry Index. Gemini 2.5 Pro costs 1.7× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.

Last verified . 37 shared benchmarks.

Gemini 2.5 Pro Google

45.0

Rank #75 Confirmed

Kimi K3 Moonshot AI

59.5

Rank #15 Confirmed

Summary

  • They share 37 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 2 categories and Kimi K3 in 8 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in math, where Kimi K3 leads 74.2 to 32.5.
  • The biggest single-benchmark swing is ARC-AGI-2: 4.9% for Gemini 2.5 Pro and 60.4% for Kimi K3.
  • Gemini 2.5 Pro is cheaper at $1.25 / $10 per million input/output tokens, against $3 / $15 for Kimi K3.
  • Kimi K3 has downloadable open weights; the other is API-only.

Side by side

Gemini 2.5 ProKimi K3
ProviderGoogleMoonshot AI
Noometry Index45.059.5
Released2025-03-252026-07-16
WeightsProprietaryOpen
Context window1.05M1.05M
Max output66K1.05M
Input $ / M tokens$1.25$3
Output $ / M tokens$10$15
Results tracked7853

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

Category by category

Coding Kimi K3 leads

Gemini 2.5 Pro: 42.4 (#101), Kimi K3: 61.0 (#10)

BenchmarkGemini 2.5 ProKimi K3
LMArena WebDev12271654
SciCode42.8%59.5%
WeirdML54%82.6%
LMArena Coding14521508
ALE-Bench785.521,524
SWE-bench Verified57.6%—
DeepSWE—68.5%
FrontierCode—44.2%
SWE-bench Verified (bash only)53.6%—
Aider Polyglot83.1%—
FrontierSWE—25.9%
GSO3.9%—
LiveBench Coding85.9%—
CadEval64%—
AlgoTune1.51—

Agentic & Tool Use Kimi K3 leads

Gemini 2.5 Pro: 29.2 (#88), Kimi K3: 41.8 (#20)

BenchmarkGemini 2.5 ProKimi K3
τ²-bench Banking13.7%37.1%
Vending-Bench 2573.645,165
Terminal-Bench32.6%—
APEX-Agents—50.6%
GDPval23.3%—
Remote Labor Index0.8%—
TheAgentCompany30.3%—
DeepResearch Bench42.8%—
PostTrainBench—32%
BALROG43.3%—
GBAEval—48.3%
GDP.pdf—19%
LMArena Search1142—
METR Time Horizons55.4%—

Reasoning Kimi K3 leads

Gemini 2.5 Pro: 28.8 (#99), Kimi K3: 63.0 (#17)

BenchmarkGemini 2.5 ProKimi K3
ARC-AGI-24.9%60.4%
SimpleBench62.4%60.7%
ARC-AGI-141%94.5%
CritPt2%23.4%
Chess Puzzles20%39%
LMArena Hard Prompts14551496
DTBench82.4%91.2%
LMCA34.8%52.7%
Epoch Capabilities Index145.32157.45
ForecastBench61.361.1
Kagi LLM Benchmark70.3%—
NYT Connections (extended)—93.6%
EnigmaEval5.6%—
LiveBench Reasoning89.8%—
Mystery Game Puzzles—26%
LiveBench Data Analysis79.9%—
Surface Evolver Bench—95%
LiveBench82.3%—

Math Kimi K3 leads

Gemini 2.5 Pro: 32.5 (#213), Kimi K3: 74.2 (#16)

BenchmarkGemini 2.5 ProKimi K3
FrontierMath (Tiers 1-3)24.6%72.2%
FrontierMath Tier 40%39%
OTIS Mock AIME 2024-202584.7%97.2%
LMArena Math14501491
MathArena Final-Answer Competitions—87.8%
ProofBench—87%
Omni-MATH41.6%—
LiveBench Math90.2%—
MATH Level 595.9%—
FrontierMath (Feb 2025 set)14.1%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Kimi K3 leads

Gemini 2.5 Pro: 56.0 (#46), Kimi K3: 63.2 (#21)

BenchmarkGemini 2.5 ProKimi K3
GPQA Diamond85.3%93.1%
LMArena Expert14521521
Humanity's Last Exam21.6%—
SimpleQA Verified—50.6%
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), Kimi K3: 37.8 (#70)

BenchmarkGemini 2.5 ProKimi K3
LMArena Vision1263—
GeoBench86%—
VPCT48%—
Blueprint-Bench 2—29.5%
Furniture Assembly—34.2%
LMArena Document1421—
SpatialViz-Bench44.7%—

Multilingual Kimi K3 leads

Gemini 2.5 Pro: 55.3 (#31), Kimi K3: 56.3 (#21)

BenchmarkGemini 2.5 ProKimi K3
LMArena Non-English14511466
LMArena Chinese15071529
LMArena French14721491
LMArena German14871488
LMArena Japanese14611487
LMArena Korean14341458
LMArena Russian14611482
LMArena Spanish14731472

Instruction Following Kimi K3 leads

Gemini 2.5 Pro: 75.0 (#75), Kimi K3: 77.7 (#14)

BenchmarkGemini 2.5 ProKimi K3
LMArena Instruction Following14371483
LiveBench Instruction Following80.6%—
IFEval84%—

Long Context Gemini 2.5 Pro leads

Gemini 2.5 Pro: 59.8 (#5), Kimi K3: 45.8 (#29)

BenchmarkGemini 2.5 ProKimi K3
LMArena Longer Query14491494
Fiction.LiveBench91.7%—

Writing & Preference Kimi K3 leads

Gemini 2.5 Pro: 63.7 (#62), Kimi K3: 76.6 (#4)

BenchmarkGemini 2.5 ProKimi K3
LMArena Text14581476
LMArena Creative Writing14541454
EQ-Bench Creative Writing14212082
LMArena Multi-Turn14531488
Short-Story Creative Writing83.8%—
WildBench85.7%—
EQ-Bench 4—1339
LiveBench Language67.8%—

Frequently asked questions

Is Gemini 2.5 Pro better than Kimi K3?

Kimi K3 is the stronger model overall, scoring 59.5 to 45.0 on the Noometry Index. Gemini 2.5 Pro costs 1.7× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.

Which is cheaper, Gemini 2.5 Pro or Kimi K3?

Gemini 2.5 Pro is cheaper. It lists at $1.25 per million input tokens and $10 per million output tokens; Kimi K3 lists at $3 and $15.

Is Gemini 2.5 Pro or Kimi K3 better for coding?

Kimi K3 scores higher on coding benchmarks: 61.0 versus 42.4 in the Noometry coding category.

Which has the bigger context window?

Both accept 1.05M tokens.

How many benchmarks do Gemini 2.5 Pro and Kimi K3 share?

37 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and Kimi K3 has 53.

Related comparisons

Go deeper