Noometry

Model comparison

Gemini 4 Argon vs Kimi K3

Kimi K3 is the stronger model overall, scoring 59.5 to 56.5 on the Noometry Index.

Last verified . 21 shared benchmarks.

Gemini 4 Argon Google

56.5

Rank #24 Confirmed

Kimi K3 Moonshot AI

59.5

Rank #15 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Gemini 4 Argon scores higher in 6 categories and Kimi K3 in 4 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Kimi K3 leads 63.2 to 43.9.
  • The biggest single-benchmark swing is APEX-Agents: 82.2% for Gemini 4 Argon and 50.6% for Kimi K3.
  • Kimi K3 has downloadable open weights; the other is API-only.

Side by side

Gemini 4 ArgonKimi K3
ProviderGoogleMoonshot AI
Noometry Index56.559.5
Released2026-09-302026-07-16
WeightsProprietaryOpen
Context window—1.05M
Max output—1.05M
Input $ / M tokens—$3
Output $ / M tokens—$15
Results tracked2153

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

Category by category

Coding Gemini 4 Argon leads

Gemini 4 Argon: 62.0 (#9), Kimi K3: 61.0 (#10)

BenchmarkGemini 4 ArgonKimi K3
LMArena WebDev16781654
FrontierSWE55%25.9%
SciCode61.8%59.5%
LMArena Coding15501508
DeepSWE—68.5%
FrontierCode—44.2%
WeirdML—82.6%
ALE-Bench—1,524

Agentic & Tool Use Gemini 4 Argon leads

Gemini 4 Argon: 49.2 (#8), Kimi K3: 41.8 (#20)

BenchmarkGemini 4 ArgonKimi K3
APEX-Agents82.2%50.6%
Vending-Bench 213,7185,165
τ²-bench Banking—37.1%
PostTrainBench—32%
GBAEval—48.3%
GDP.pdf—19%

Reasoning Kimi K3 leads

Gemini 4 Argon: 44.2 (#47), Kimi K3: 63.0 (#17)

BenchmarkGemini 4 ArgonKimi K3
CritPt27.1%23.4%
LMArena Hard Prompts15481496
ARC-AGI-2—60.4%
SimpleBench—60.7%
NYT Connections (extended)—93.6%
ARC-AGI-1—94.5%
Chess Puzzles—39%
Mystery Game Puzzles—26%
DTBench—91.2%
LMCA—52.7%
Surface Evolver Bench—95%
Epoch Capabilities Index—157.45
ForecastBench—61.1

Math Too close to call

Gemini 4 Argon: 73.9 (#17), Kimi K3: 74.2 (#16)

BenchmarkGemini 4 ArgonKimi K3
ProofBench99%87%
LMArena Math15361491
FrontierMath (Tiers 1-3)—72.2%
FrontierMath Tier 4—39%
MathArena Final-Answer Competitions—87.8%
OTIS Mock AIME 2024-2025—97.2%

Knowledge Kimi K3 leads

Gemini 4 Argon: 43.9 (#89), Kimi K3: 63.2 (#21)

BenchmarkGemini 4 ArgonKimi K3
LMArena Expert15531521
GPQA Diamond—93.1%
SimpleQA Verified—50.6%

Multimodal Gemini 4 Argon leads

Gemini 4 Argon: 46.5 (#14), Kimi K3: 37.8 (#70)

BenchmarkGemini 4 ArgonKimi K3
Blueprint-Bench 254.4%29.5%
Furniture Assembly—34.2%

Multilingual Gemini 4 Argon leads

Gemini 4 Argon: 60.3 (#1), Kimi K3: 56.3 (#21)

BenchmarkGemini 4 ArgonKimi K3
LMArena Non-English15231466
LMArena Chinese16101529
LMArena Russian15371482
LMArena Spanish14971472
LMArena French—1491
LMArena German—1488
LMArena Japanese—1487
LMArena Korean—1458

Instruction Following Gemini 4 Argon leads

Gemini 4 Argon: 80.1 (#2), Kimi K3: 77.7 (#14)

BenchmarkGemini 4 ArgonKimi K3
LMArena Instruction Following15381483

Long Context Gemini 4 Argon leads

Gemini 4 Argon: 47.6 (#15), Kimi K3: 45.8 (#29)

BenchmarkGemini 4 ArgonKimi K3
LMArena Longer Query15491494

Writing & Preference Kimi K3 leads

Gemini 4 Argon: 71.4 (#19), Kimi K3: 76.6 (#4)

BenchmarkGemini 4 ArgonKimi K3
LMArena Text15341476
LMArena Creative Writing15311454
LMArena Multi-Turn15571488
EQ-Bench Creative Writing—2082
EQ-Bench 4—1339

Frequently asked questions

Is Gemini 4 Argon better than Kimi K3?

Kimi K3 is the stronger model overall, scoring 59.5 to 56.5 on the Noometry Index.

Is Gemini 4 Argon or Kimi K3 better for coding?

Gemini 4 Argon scores higher on coding benchmarks: 62.0 versus 61.0 in the Noometry coding category.

How many benchmarks do Gemini 4 Argon and Kimi K3 share?

21 benchmarks have published results for both models. Gemini 4 Argon has 21 scored results on Noometry and Kimi K3 has 53.

Related comparisons

Go deeper