Noometry

Model comparison

Gemini 3.8 Flash vs Kimi K3

Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 59.5 on the Noometry Index.

Last verified . 46 shared benchmarks.

Gemini 3.8 Flash Google

61.8

Rank #11 Confirmed

Kimi K3 Moonshot AI

59.5

Rank #15 Confirmed

Summary

  • They share 46 benchmarks with published results for both. Gemini 3.8 Flash scores higher in 6 categories and Kimi K3 in 4 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.8 Flash leads 76.9 to 63.0.
  • The biggest single-benchmark swing is ProofBench: 48% for Gemini 3.8 Flash and 87% for Kimi K3.
  • Gemini 3.8 Flash is cheaper at $0.75 / $3.75 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 3.8 FlashKimi K3
ProviderGoogleMoonshot AI
Noometry Index61.859.5
Released2026-09-022026-07-16
WeightsProprietaryOpen
Context window1.05M1.05M
Max output66K1.05M
Input $ / M tokens$0.75$3
Output $ / M tokens$3.75$15
Results tracked5053

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

Category by category

Coding Kimi K3 leads

Gemini 3.8 Flash: 59.2 (#15), Kimi K3: 61.0 (#10)

BenchmarkGemini 3.8 FlashKimi K3
DeepSWE73.8%68.5%
FrontierCode41.2%44.2%
LMArena WebDev15841654
FrontierSWE19.6%25.9%
SciCode56.6%59.5%
WeirdML84.8%82.6%
LMArena Coding15101508
ALE-Bench1,2701,524
CursorBench39.6%—

Agentic & Tool Use Too close to call

Gemini 3.8 Flash: 41.8 (#21), Kimi K3: 41.8 (#20)

BenchmarkGemini 3.8 FlashKimi K3
APEX-Agents64.3%50.6%
GDP.pdf23.4%19%
Vending-Bench 25,0945,165
Remote Labor Index5.8%—
τ²-bench Banking—37.1%
PostTrainBench—32%
GBAEval—48.3%

Reasoning Gemini 3.8 Flash leads

Gemini 3.8 Flash: 76.9 (#5), Kimi K3: 63.0 (#17)

BenchmarkGemini 3.8 FlashKimi K3
ARC-AGI-289.2%60.4%
NYT Connections (extended)97.4%93.6%
ARC-AGI-198.5%94.5%
CritPt18.3%23.4%
Chess Puzzles61%39%
LMArena Hard Prompts15081496
Mystery Game Puzzles47%26%
DTBench95.7%91.2%
LMCA52.9%52.7%
Surface Evolver Bench76.9%95%
Epoch Capabilities Index156.71157.45
SimpleBench—60.7%
ForecastBench—61.1

Math Kimi K3 leads

Gemini 3.8 Flash: 65.3 (#28), Kimi K3: 74.2 (#16)

BenchmarkGemini 3.8 FlashKimi K3
FrontierMath (Tiers 1-3)68.4%72.2%
FrontierMath Tier 422%39%
OTIS Mock AIME 2024-202598.9%97.2%
ProofBench48%87%
LMArena Math15281491
MathArena Final-Answer Competitions—87.8%

Knowledge Gemini 3.8 Flash leads

Gemini 3.8 Flash: 74.8 (#2), Kimi K3: 63.2 (#21)

BenchmarkGemini 3.8 FlashKimi K3
GPQA Diamond95.4%93.1%
SimpleQA Verified69.7%50.6%
LMArena Expert15241521
Humanity's Last Exam44.5%—

Multimodal Gemini 3.8 Flash leads

Gemini 3.8 Flash: 40.7 (#45), Kimi K3: 37.8 (#70)

BenchmarkGemini 3.8 FlashKimi K3
Blueprint-Bench 238.6%29.5%
Furniture Assembly31.7%34.2%
LMArena Vision1314—

Multilingual Gemini 3.8 Flash leads

Gemini 3.8 Flash: 58.0 (#5), Kimi K3: 56.3 (#21)

BenchmarkGemini 3.8 FlashKimi K3
LMArena Non-English14911466
LMArena Chinese15541529
LMArena French14981491
LMArena German14931488
LMArena Japanese15021487
LMArena Korean14591458
LMArena Russian15151482
LMArena Spanish14851472

Instruction Following Too close to call

Gemini 3.8 Flash: 78.0 (#13), Kimi K3: 77.7 (#14)

BenchmarkGemini 3.8 FlashKimi K3
LMArena Instruction Following14901483

Long Context Too close to call

Gemini 3.8 Flash: 46.3 (#24), Kimi K3: 45.8 (#29)

BenchmarkGemini 3.8 FlashKimi K3
LMArena Longer Query15081494

Writing & Preference Kimi K3 leads

Gemini 3.8 Flash: 72.2 (#15), Kimi K3: 76.6 (#4)

BenchmarkGemini 3.8 FlashKimi K3
LMArena Text14991476
LMArena Creative Writing14921454
EQ-Bench Creative Writing17482082
LMArena Multi-Turn15011488
EQ-Bench 4—1339

Frequently asked questions

Is Gemini 3.8 Flash better than Kimi K3?

Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 59.5 on the Noometry Index.

Which is cheaper, Gemini 3.8 Flash or Kimi K3?

Gemini 3.8 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; Kimi K3 lists at $3 and $15.

Is Gemini 3.8 Flash or Kimi K3 better for coding?

Kimi K3 scores higher on coding benchmarks: 61.0 versus 59.2 in the Noometry coding category.

Which has the bigger context window?

Both accept 1.05M tokens.

How many benchmarks do Gemini 3.8 Flash and Kimi K3 share?

46 benchmarks have published results for both models. Gemini 3.8 Flash has 50 scored results on Noometry and Kimi K3 has 53.

Related comparisons

Go deeper