Noometry

Model comparison

Gemini 2.5 Pro vs Kimi K2.6

Kimi K2.6 is the stronger model overall, scoring 47.7 to 45.0 on the Noometry Index.

Last verified . 38 shared benchmarks.

Gemini 2.5 Pro Google

45.0

Rank #75 Confirmed

Kimi K2.6 Moonshot AI

47.7

Rank #60 Confirmed

Summary

  • They share 38 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 5 categories and Kimi K2.6 in 5 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Kimi K2.6 leads 57.0 to 32.5.
  • The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 24.6% for Gemini 2.5 Pro and 57.2% for Kimi K2.6.
  • Kimi K2.6 is cheaper at $0.95 / $4 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 262K.
  • Kimi K2.6 has downloadable open weights; the other is API-only.

Side by side

Gemini 2.5 ProKimi K2.6
ProviderGoogleMoonshot AI
Noometry Index45.047.7
Released2025-03-252026-04-20
WeightsProprietaryOpen
Context window1.05M262K
Max output66K262K
Input $ / M tokens$1.25$0.95
Output $ / M tokens$10$4
Results tracked7851

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

Category by category

Coding Kimi K2.6 leads

Gemini 2.5 Pro: 42.4 (#101), Kimi K2.6: 50.7 (#43)

BenchmarkGemini 2.5 ProKimi K2.6
SWE-bench Verified57.6%76.7%
LMArena WebDev12271509
SciCode42.8%53.5%
WeirdML54%55.9%
LMArena Coding14521488
ALE-Bench785.521,093
SWE-bench Verified (bash only)53.6%—
Aider Polyglot83.1%—
GSO3.9%—
LiveBench Coding85.9%—
CadEval64%—
AlgoTune1.51—

Agentic & Tool Use Gemini 2.5 Pro leads

Gemini 2.5 Pro: 29.2 (#88), Kimi K2.6: 21.9 (#137)

BenchmarkGemini 2.5 ProKimi K2.6
Vending-Bench 2573.646,205
Terminal-Bench32.6%—
OSWorld 2.0—4.6%
GDPval23.3%—
Remote Labor Index0.8%—
TheAgentCompany30.3%—
τ²-bench Banking13.7%—
DeepResearch Bench42.8%—
BALROG43.3%—
ExploitBench—18.4%
GBAEval—0.9%
GDP.pdf—12%
LMArena Search1142—
METR Time Horizons55.4%—

Reasoning Kimi K2.6 leads

Gemini 2.5 Pro: 28.8 (#99), Kimi K2.6: 40.5 (#55)

BenchmarkGemini 2.5 ProKimi K2.6
CritPt2%8%
Chess Puzzles20%26%
LMArena Hard Prompts14551470
DTBench82.4%90.9%
LMCA34.8%37.3%
Epoch Capabilities Index145.32151.05
ARC-AGI-24.9%—
SimpleBench62.4%—
Kagi LLM Benchmark70.3%—
NYT Connections (extended)—87.2%
ARC-AGI-141%—
EnigmaEval5.6%—
EBR-Bench—2.4%
LiveBench Reasoning89.8%—
Mystery Game Puzzles—18%
LiveBench Data Analysis79.9%—
ForecastBench61.3—
LiveBench82.3%—

Math Kimi K2.6 leads

Gemini 2.5 Pro: 32.5 (#213), Kimi K2.6: 57.0 (#41)

BenchmarkGemini 2.5 ProKimi K2.6
FrontierMath (Tiers 1-3)24.6%57.2%
FrontierMath Tier 40%25.6%
OTIS Mock AIME 2024-202584.7%96.1%
LMArena Math14501475
FrontierMath (Feb 2025 set)14.1%39%
FrontierMath Tier 4 (v1)4.2%14.6%
MathArena Final-Answer Competitions—72.9%
ProofBench—16%
Omni-MATH41.6%—
LiveBench Math90.2%—
MATH Level 595.9%—

Knowledge Gemini 2.5 Pro leads

Gemini 2.5 Pro: 56.0 (#46), Kimi K2.6: 54.0 (#54)

BenchmarkGemini 2.5 ProKimi K2.6
GPQA Diamond85.3%90.8%
Vectara Hallucination Rate7%10.8%
LMArena Expert14521491
Humanity's Last Exam21.6%—
SimpleQA Verified—34.9%
MMLU-Pro86.3%—
Confabulations10.6%—
GPQA (HELM)74.9%—

Multimodal Gemini 2.5 Pro leads

Gemini 2.5 Pro: 45.2 (#18), Kimi K2.6: 31.6 (#103)

BenchmarkGemini 2.5 ProKimi K2.6
LMArena Vision12631283
LMArena Document14211451
GeoBench86%—
VPCT48%—
Blueprint-Bench 2—3.9%
Furniture Assembly—21.7%
SpatialViz-Bench44.7%—

Multilingual Too close to call

Gemini 2.5 Pro: 55.3 (#31), Kimi K2.6: 54.9 (#37)

BenchmarkGemini 2.5 ProKimi K2.6
LMArena Non-English14511446
LMArena Chinese15071521
LMArena French14721471
LMArena German14871450
LMArena Japanese14611443
LMArena Korean14341427
LMArena Russian14611446
LMArena Spanish14731464

Instruction Following Kimi K2.6 leads

Gemini 2.5 Pro: 75.0 (#75), Kimi K2.6: 76.3 (#43)

BenchmarkGemini 2.5 ProKimi K2.6
LMArena Instruction Following14371451
LiveBench Instruction Following80.6%—
IFEval84%—

Long Context Gemini 2.5 Pro leads

Gemini 2.5 Pro: 59.8 (#5), Kimi K2.6: 44.9 (#52)

BenchmarkGemini 2.5 ProKimi K2.6
LMArena Longer Query14491468
Fiction.LiveBench91.7%—

Writing & Preference Kimi K2.6 leads

Gemini 2.5 Pro: 63.7 (#62), Kimi K2.6: 68.5 (#26)

BenchmarkGemini 2.5 ProKimi K2.6
LMArena Text14581455
LMArena Creative Writing14541434
EQ-Bench Creative Writing14211725
LMArena Multi-Turn14531453
Short-Story Creative Writing83.8%—
WildBench85.7%—
EQ-Bench 4—1202
LiveBench Language67.8%—

Frequently asked questions

Is Gemini 2.5 Pro better than Kimi K2.6?

Kimi K2.6 is the stronger model overall, scoring 47.7 to 45.0 on the Noometry Index.

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

Kimi K2.6 is cheaper. It lists at $0.95 per million input tokens and $4 per million output tokens; Gemini 2.5 Pro lists at $1.25 and $10.

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

Kimi K2.6 scores higher on coding benchmarks: 50.7 versus 42.4 in the Noometry coding category.

Which has the bigger context window?

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

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

38 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and Kimi K2.6 has 51.

Related comparisons

Go deeper