Noometry

Model comparison

Gemini 2.5 Pro vs Kimi K2 (Jul 2025)

Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 41.2 on the Noometry Index. Kimi K2 (Jul 2025) costs 3.4× less per token, which makes it the better buy when Gemini 2.5 Pro's lead doesn't matter for your workload.

Last verified . 40 shared benchmarks.

Gemini 2.5 Pro Google

45.0

Rank #75 Confirmed

Kimi K2 (Jul 2025) Moonshot AI

41.2

Rank #140 Confirmed

Summary

  • They share 40 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 6 categories and Kimi K2 (Jul 2025) in 3 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Gemini 2.5 Pro leads 56.0 to 37.3.
  • The biggest single-benchmark swing is SimpleBench: 62.4% for Gemini 2.5 Pro and 26.3% for Kimi K2 (Jul 2025).
  • Kimi K2 (Jul 2025) is cheaper at $0.57 / $2.30 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 (Jul 2025) has downloadable open weights; the other is API-only.

Side by side

Gemini 2.5 ProKimi K2 (Jul 2025)
ProviderGoogleMoonshot AI
Noometry Index45.041.2
Released2025-03-252025-07-12
WeightsProprietaryOpen
Context window1.05M262K
Max output66K262K
Input $ / M tokens$1.25$0.57
Output $ / M tokens$10$2.30
Results tracked7842

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

Category by category

Coding Too close to call

Gemini 2.5 Pro: 42.4 (#101), Kimi K2 (Jul 2025): 42.4 (#102)

BenchmarkGemini 2.5 ProKimi K2 (Jul 2025)
SWE-bench Verified (bash only)53.6%63.4%
Aider Polyglot83.1%59.1%
GSO3.9%4.9%
WeirdML54%42.8%
LMArena Coding14521399
ALE-Bench785.52597.5
SWE-bench Verified57.6%—
LMArena WebDev1227—
SciCode42.8%—
LiveBench Coding85.9%—
CadEval64%—
AlgoTune1.51—

Agentic & Tool Use Kimi K2 (Jul 2025) leads

Gemini 2.5 Pro: 29.2 (#88), Kimi K2 (Jul 2025): 32.4 (#64)

BenchmarkGemini 2.5 ProKimi K2 (Jul 2025)
Terminal-Bench32.6%35.7%
METR Time Horizons55.4%59.2%
Berkeley Function Calling Leaderboard—59.1%
GDPval23.3%—
Remote Labor Index0.8%—
TheAgentCompany30.3%—
τ²-bench Banking13.7%—
DeepResearch Bench42.8%—
BALROG43.3%—
LMArena Search1142—
Vending-Bench 2573.64—

Reasoning Gemini 2.5 Pro leads

Gemini 2.5 Pro: 28.8 (#99), Kimi K2 (Jul 2025): 23.3 (#179)

BenchmarkGemini 2.5 ProKimi K2 (Jul 2025)
SimpleBench62.4%26.3%
Kagi LLM Benchmark70.3%64.4%
LMArena Hard Prompts14551384
Epoch Capabilities Index145.32146.01
ForecastBench61.360.2
ARC-AGI-24.9%—
ARC-AGI-141%—
CritPt2%—
Chess Puzzles20%—
EnigmaEval5.6%—
LiveBench Reasoning89.8%—
DTBench82.4%—
LiveBench Data Analysis79.9%—
LMCA34.8%—
LiveBench82.3%—

Math Kimi K2 (Jul 2025) leads

Gemini 2.5 Pro: 32.5 (#213), Kimi K2 (Jul 2025): 42.7 (#83)

BenchmarkGemini 2.5 ProKimi K2 (Jul 2025)
Omni-MATH41.6%65.4%
LMArena Math14501397
FrontierMath (Feb 2025 set)14.1%21.4%
FrontierMath Tier 4 (v1)4.2%0%
FrontierMath (Tiers 1-3)24.6%—
FrontierMath Tier 40%—
OTIS Mock AIME 2024-202584.7%—
LiveBench Math90.2%—
MATH Level 595.9%—

Knowledge Gemini 2.5 Pro leads

Gemini 2.5 Pro: 56.0 (#46), Kimi K2 (Jul 2025): 37.3 (#157)

BenchmarkGemini 2.5 ProKimi K2 (Jul 2025)
MMLU-Pro86.3%81.9%
Confabulations10.6%20.4%
Vectara Hallucination Rate7%17.9%
GPQA (HELM)74.9%65.3%
LMArena Expert14521365
GPQA Diamond85.3%—
Humanity's Last Exam21.6%—

Multimodal Not comparable

Gemini 2.5 Pro: 45.2 (#18), Kimi K2 (Jul 2025): —

BenchmarkGemini 2.5 ProKimi K2 (Jul 2025)
LMArena Vision1263—
GeoBench86%—
VPCT48%—
LMArena Document1421—
SpatialViz-Bench44.7%—

Multilingual Gemini 2.5 Pro leads

Gemini 2.5 Pro: 55.3 (#31), Kimi K2 (Jul 2025): 49.6 (#130)

BenchmarkGemini 2.5 ProKimi K2 (Jul 2025)
LMArena Non-English14511372
LMArena Chinese15071415
LMArena French14721379
LMArena German14871387
LMArena Japanese14611349
LMArena Korean14341325
LMArena Russian14611385
LMArena Spanish14731386

Instruction Following Gemini 2.5 Pro leads

Gemini 2.5 Pro: 75.0 (#75), Kimi K2 (Jul 2025): 71.1 (#156)

BenchmarkGemini 2.5 ProKimi K2 (Jul 2025)
IFEval84%85%
LMArena Instruction Following14371348
LiveBench Instruction Following80.6%—

Long Context Gemini 2.5 Pro leads

Gemini 2.5 Pro: 59.8 (#5), Kimi K2 (Jul 2025): 41.2 (#145)

BenchmarkGemini 2.5 ProKimi K2 (Jul 2025)
Fiction.LiveBench91.7%66.7%
LMArena Longer Query14491353
CL-bench—17.6%

Writing & Preference Gemini 2.5 Pro leads

Gemini 2.5 Pro: 63.7 (#62), Kimi K2 (Jul 2025): 62.3 (#78)

BenchmarkGemini 2.5 ProKimi K2 (Jul 2025)
LMArena Text14581380
LMArena Creative Writing14541350
Short-Story Creative Writing83.8%85.6%
EQ-Bench Creative Writing14211666
WildBench85.7%86.2%
LMArena Multi-Turn14531371
LiveBench Language67.8%—

Frequently asked questions

Is Gemini 2.5 Pro better than Kimi K2 (Jul 2025)?

Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 41.2 on the Noometry Index. Kimi K2 (Jul 2025) costs 3.4× less per token, which makes it the better buy when Gemini 2.5 Pro's lead doesn't matter for your workload.

Which is cheaper, Gemini 2.5 Pro or Kimi K2 (Jul 2025)?

Kimi K2 (Jul 2025) is cheaper. It lists at $0.57 per million input tokens and $2.30 per million output tokens; Gemini 2.5 Pro lists at $1.25 and $10.

Is Gemini 2.5 Pro or Kimi K2 (Jul 2025) better for coding?

They score almost the same on coding (42.4 vs 42.4); test both on your own repository before choosing.

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 (Jul 2025) share?

40 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and Kimi K2 (Jul 2025) has 42.

Related comparisons

Go deeper