Comparing 2 models

Gemini 3.6 Flash vs Kimi K3

Benchmarks through

Verdict

Gemini 3.6 Flash and Kimi K3 are not yet ranked on the same task, so compare the specifications below. Kimi K3 costs 3.9x less per input token. Only Kimi K3 has open weights for self-hosting.

  • Choose Kimi K3 for you need to self-host.

Built from the published task rankings below; ranks come from each task's own weighted benchmarks, so a win on one task says nothing about another.

metric
Model 1Gemini 3.6 Flash
Model 2Kimi K3
Best for
Business Writing (#7)
JSON & Schema Output (#2)
Provider
google
moonshotai
Context
1.0MBest
1.0MBest
Input / 1M
$0.75
$0.19Best
Output / 1M
$3.75Best
$16
Tool use
yesBest
yesBest
Vision
yesBest
yesBest
Reasoning
yesBest
yesBest
Open-weight
—
yesBest
Released
Jul 21, 2026
Jul 16, 2026

Measured head to head

Benchmarks both models were run on

EvaluationGemini 3.6 FlashKimi K3Source
Design Arena Coding1279 Elo1352 Elosource · 2026-11-15
Design Arena Full-stack Agent1154 Elo1289 Elosource · 2026-11-15
Design Arena UI1289 Elo1342 Elosource · 2026-11-15
Design Arena Web-app Agent1174 Elo1273 Elosource · 2026-11-15
Design Arena Website1292 Elo1336 Elosource · 2026-11-15
FrontierMath Tiers 1-3 (Epoch AI)58.9% ± 2.972.2% ± 2.7source · 2026-08-02
GPQA Diamond (Epoch AI)85.9% ± 2.593.1% ± 1.5source · 2026-08-07
GPQA Diamond (Epoch AI)86.4% ± 2.493.1% ± 1.5source · 2026-08-06
GPQA Diamond (Epoch AI)94.1% ± 1.493.1% ± 1.5source · 2026-08-02
LiveBench Agentic Coding43.4%62.2%source · 2026-10-18
LiveBench Coding77.9%81.5%source · 2026-10-18
LiveBench Data Analysis63%78.7%source · 2026-10-18
LiveBench Instruction Following75.4%71.4%source · 2026-10-18
LiveBench Language83.9%85.5%source · 2026-10-18
LiveBench Math86.4%84.4%source · 2026-10-18
LiveBench Reasoning85.2%90.7%source · 2026-10-18
LMArena Agent Bash Recovery-18.24.4source · 2026-10-08
LMArena Creative Writing1466 Elo1453 Elosource · 2026-11-11
LMArena Instruction Following1467 Elo1484 Elosource · 2026-11-11
LMArena Long Query1475 Elo1490 Elosource · 2026-11-11
LMArena Math1505 Elo1496 Elosource · 2026-11-11
LMArena Text Factuality1472 Elo1471 Elosource · 2026-11-11
LMArena WebDev Image-to-Web1545 Elo1586 Elosource · 2026-11-10
OTIS Mock AIME (Epoch AI)82.2% ± 5.897.2% ± 1.1source · 2026-08-07
OTIS Mock AIME (Epoch AI)94.2% ± 3.197.2% ± 1.1source · 2026-08-02
SimpleQA Verified (Epoch AI)66.2% ± 1.550.6% ± 1.6source · 2026-08-27

Values are as published by each evaluator, in its own units; rows from different evaluators are not on a common scale.