Noometry

Model comparison

Gemini 1.5 Flash 8B vs Kimi K2.5

Kimi K2.5 is the stronger model overall, scoring 48.1 to 29.9 on the Noometry Index.

Last verified . 20 shared benchmarks.

Gemini 1.5 Flash 8B Google

29.9

Rank #301 Confirmed

Kimi K2.5 Moonshot AI

48.1

Rank #57 Confirmed

Summary

  • They share 20 benchmarks with published results for both. Gemini 1.5 Flash 8B scores higher in 0 categories and Kimi K2.5 in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Kimi K2.5 leads 51.8 to 14.2.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.6% for Gemini 1.5 Flash 8B and 92.2% for Kimi K2.5.
  • Kimi K2.5 has downloadable open weights; the other is API-only.

Side by side

Gemini 1.5 Flash 8BKimi K2.5
ProviderGoogleMoonshot AI
Noometry Index29.948.1
Released2024-10-032026-01-27
WeightsProprietaryOpen
Context window—262K
Max output—262K
Input $ / M tokens—$0.45
Output $ / M tokens—$2.25
Results tracked2151

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

Category by category

Coding Kimi K2.5 leads

Gemini 1.5 Flash 8B: 35.5 (#225), Kimi K2.5: 48.8 (#53)

BenchmarkGemini 1.5 Flash 8BKimi K2.5
LMArena Coding12181474
SWE-bench Verified—73.8%
SWE-bench Verified (bash only)—70.8%
LMArena WebDev—1437
SWE-bench Multilingual—67.3%
SciCode—49%
WeirdML—45.6%
ALE-Bench—821.65

Agentic & Tool Use Not comparable

Gemini 1.5 Flash 8B: —, Kimi K2.5: 34.2 (#48)

BenchmarkGemini 1.5 Flash 8BKimi K2.5
Terminal-Bench—43.2%
OSWorld—63.3%
Vending-Bench 2—1,198

Reasoning Kimi K2.5 leads

Gemini 1.5 Flash 8B: 20.0 (#244), Kimi K2.5: 31.2 (#80)

BenchmarkGemini 1.5 Flash 8BKimi K2.5
LMArena Hard Prompts12091453
ARC-AGI-2—11.8%
SimpleBench—46.8%
Kagi LLM Benchmark—78.5%
NYT Connections (extended)—69.9%
ARC-AGI-1—65.3%
CritPt—3.1%
Chess Puzzles—12%
EnigmaEval—3.4%
Thematic Generalization—69.4%
DTBench50%—
Epoch Capabilities Index—148.03

Math Kimi K2.5 leads

Gemini 1.5 Flash 8B: 14.2 (#302), Kimi K2.5: 51.8 (#53)

BenchmarkGemini 1.5 Flash 8BKimi K2.5
OTIS Mock AIME 2024-20254.6%92.2%
LMArena Math12071470
MathArena Final-Answer Competitions—62.3%
FrontierMath (Feb 2025 set)—27.9%
FrontierMath Tier 4 (v1)—4.2%

Knowledge Kimi K2.5 leads

Gemini 1.5 Flash 8B: 16.0 (#289), Kimi K2.5: 53.6 (#56)

BenchmarkGemini 1.5 Flash 8BKimi K2.5
GPQA Diamond33%87.6%
LMArena Expert11851466
Humanity's Last Exam—24.4%
SimpleQA Verified—34.3%
Vectara Hallucination Rate—14.2%

Multimodal Kimi K2.5 leads

Gemini 1.5 Flash 8B: 28.2 (#115), Kimi K2.5: 41.1 (#39)

BenchmarkGemini 1.5 Flash 8BKimi K2.5
LMArena Vision10441269
LMArena Document—1430

Multilingual Kimi K2.5 leads

Gemini 1.5 Flash 8B: 38.5 (#229), Kimi K2.5: 53.9 (#53)

BenchmarkGemini 1.5 Flash 8BKimi K2.5
LMArena Non-English12151433
LMArena Chinese12311495
LMArena French12341454
LMArena German12061441
LMArena Japanese11501421
LMArena Korean11401410
LMArena Russian12361435
LMArena Spanish12121450

Instruction Following Kimi K2.5 leads

Gemini 1.5 Flash 8B: 62.8 (#236), Kimi K2.5: 75.3 (#64)

BenchmarkGemini 1.5 Flash 8BKimi K2.5
LMArena Instruction Following11991431

Long Context Kimi K2.5 leads

Gemini 1.5 Flash 8B: 37.0 (#225), Kimi K2.5: 52.1 (#7)

BenchmarkGemini 1.5 Flash 8BKimi K2.5
LMArena Longer Query12191445
Fiction.LiveBench—86.1%
CL-bench—19.3%
CL-bench Life—13.2%

Writing & Preference Kimi K2.5 leads

Gemini 1.5 Flash 8B: 42.8 (#232), Kimi K2.5: 65.1 (#53)

BenchmarkGemini 1.5 Flash 8BKimi K2.5
LMArena Text12261445
LMArena Creative Writing12181423
LMArena Multi-Turn11851444
EQ-Bench Creative Writing—1579

Frequently asked questions

Is Gemini 1.5 Flash 8B better than Kimi K2.5?

Kimi K2.5 is the stronger model overall, scoring 48.1 to 29.9 on the Noometry Index.

Is Gemini 1.5 Flash 8B or Kimi K2.5 better for coding?

Kimi K2.5 scores higher on coding benchmarks: 48.8 versus 35.5 in the Noometry coding category.

How many benchmarks do Gemini 1.5 Flash 8B and Kimi K2.5 share?

20 benchmarks have published results for both models. Gemini 1.5 Flash 8B has 21 scored results on Noometry and Kimi K2.5 has 51.

Related comparisons

Go deeper