Noometry

Model comparison

Gemini 2.5 Flash vs Kimi K2.6

Kimi K2.6 is the stronger model overall, scoring 47.7 to 39.3 on the Noometry Index. Gemini 2.5 Flash costs 2.0× less per token, which makes it the better buy when Kimi K2.6's lead doesn't matter for your workload.

Last verified . 30 shared benchmarks.

Gemini 2.5 Flash Google

39.3

Rank #170 Confirmed

Kimi K2.6 Moonshot AI

47.7

Rank #60 Confirmed

Summary

  • They share 30 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 3 categories and Kimi K2.6 in 7 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Kimi K2.6 leads 40.5 to 18.1.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 73.1% for Gemini 2.5 Flash and 96.1% for Kimi K2.6.
  • Gemini 2.5 Flash is cheaper at $0.30 / $2.50 per million input/output tokens, against $0.95 / $4 for Kimi K2.6.
  • Gemini 2.5 Flash accepts more context: 1.05M tokens versus 262K.
  • Kimi K2.6 has downloadable open weights; the other is API-only.

Side by side

Gemini 2.5 FlashKimi K2.6
ProviderGoogleMoonshot AI
Noometry Index39.347.7
Released2025-04-172026-04-20
WeightsProprietaryOpen
Context window1.05M262K
Max output66K262K
Input $ / M tokens$0.30$0.95
Output $ / M tokens$2.50$4
Results tracked5451

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

Category by category

Coding Kimi K2.6 leads

Gemini 2.5 Flash: 35.8 (#220), Kimi K2.6: 50.7 (#43)

BenchmarkGemini 2.5 FlashKimi K2.6
WeirdML41.9%55.9%
LMArena Coding14241488
ALE-Bench661.881,093
SWE-bench Verified—76.7%
SWE-bench Verified (bash only)28.7%—
Aider Polyglot55.1%—
LMArena WebDev—1509
SciCode—53.5%

Agentic & Tool Use Gemini 2.5 Flash leads

Gemini 2.5 Flash: 30.8 (#74), Kimi K2.6: 21.9 (#137)

BenchmarkGemini 2.5 FlashKimi K2.6
Vending-Bench 2548.846,205
Terminal-Bench17.1%—
Berkeley Function Calling Leaderboard56.2%—
OSWorld 2.0—4.6%
TheAgentCompany41.1%—
BALROG33.5%—
ExploitBench—18.4%
GBAEval—0.9%
GDP.pdf—12%

Reasoning Kimi K2.6 leads

Gemini 2.5 Flash: 18.1 (#286), Kimi K2.6: 40.5 (#55)

BenchmarkGemini 2.5 FlashKimi K2.6
CritPt1.1%8%
LMArena Hard Prompts14221470
DTBench76.5%90.9%
LMCA27.5%37.3%
Epoch Capabilities Index143.03151.05
ARC-AGI-22.5%—
SimpleBench41.2%—
Kagi LLM Benchmark56.8%—
NYT Connections (extended)—87.2%
ARC-AGI-133.3%—
Chess Puzzles—26%
EnigmaEval2.7%—
EBR-Bench—2.4%
Mystery Game Puzzles—18%
ForecastBench60.6—

Math Kimi K2.6 leads

Gemini 2.5 Flash: 39.9 (#98), Kimi K2.6: 57.0 (#41)

BenchmarkGemini 2.5 FlashKimi K2.6
OTIS Mock AIME 2024-202573.1%96.1%
LMArena Math14151475
FrontierMath (Feb 2025 set)4.8%39%
FrontierMath Tier 4 (v1)4.2%14.6%
FrontierMath (Tiers 1-3)—57.2%
FrontierMath Tier 4—25.6%
MathArena Final-Answer Competitions—72.9%
ProofBench—16%
Omni-MATH38.5%—

Knowledge Kimi K2.6 leads

Gemini 2.5 Flash: 36.4 (#168), Kimi K2.6: 54.0 (#54)

BenchmarkGemini 2.5 FlashKimi K2.6
Vectara Hallucination Rate7.8%10.8%
LMArena Expert14261491
GPQA Diamond—90.8%
Humanity's Last Exam12.1%—
SimpleQA Verified—34.9%
MMLU-Pro63.9%—
Confabulations16.8%—
GPQA (HELM)39%—

Multimodal Gemini 2.5 Flash leads

Gemini 2.5 Flash: 41.8 (#32), Kimi K2.6: 31.6 (#103)

BenchmarkGemini 2.5 FlashKimi K2.6
LMArena Vision12531283
GeoBench76%—
VPCT46.2%—
Blueprint-Bench 2—3.9%
Furniture Assembly—21.7%
LMArena Document—1451
SpatialViz-Bench36.9%—

Multilingual Kimi K2.6 leads

Gemini 2.5 Flash: 52.3 (#88), Kimi K2.6: 54.9 (#37)

BenchmarkGemini 2.5 FlashKimi K2.6
LMArena Non-English14091446
LMArena Chinese14501521
LMArena French14331471
LMArena German14181450
LMArena Japanese14051443
LMArena Korean13851427
LMArena Russian14151446
LMArena Spanish14211464

Instruction Following Too close to call

Gemini 2.5 Flash: 75.7 (#54), Kimi K2.6: 76.3 (#43)

BenchmarkGemini 2.5 FlashKimi K2.6
LMArena Instruction Following14051451
IFEval89.8%—

Long Context Gemini 2.5 Flash leads

Gemini 2.5 Flash: 47.5 (#17), Kimi K2.6: 44.9 (#52)

BenchmarkGemini 2.5 FlashKimi K2.6
LMArena Longer Query14191468
Fiction.LiveBench77.8%—

Writing & Preference Kimi K2.6 leads

Gemini 2.5 Flash: 53.8 (#157), Kimi K2.6: 68.5 (#26)

BenchmarkGemini 2.5 FlashKimi K2.6
LMArena Text14171455
LMArena Creative Writing14001434
EQ-Bench Creative Writing11371725
LMArena Multi-Turn14081453
Short-Story Creative Writing76.5%—
WildBench81.7%—
EQ-Bench 4—1202

Frequently asked questions

Is Gemini 2.5 Flash better than Kimi K2.6?

Kimi K2.6 is the stronger model overall, scoring 47.7 to 39.3 on the Noometry Index. Gemini 2.5 Flash costs 2.0× less per token, which makes it the better buy when Kimi K2.6's lead doesn't matter for your workload.

Which is cheaper, Gemini 2.5 Flash or Kimi K2.6?

Gemini 2.5 Flash is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Kimi K2.6 lists at $0.95 and $4.

Is Gemini 2.5 Flash or Kimi K2.6 better for coding?

Kimi K2.6 scores higher on coding benchmarks: 50.7 versus 35.8 in the Noometry coding category.

Which has the bigger context window?

Gemini 2.5 Flash does, with 1.05M tokens against 262K.

How many benchmarks do Gemini 2.5 Flash and Kimi K2.6 share?

30 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Kimi K2.6 has 51.

Related comparisons

Go deeper