Comparing 2 models

Gemini 3.5 Flash vs Kimi K3

Benchmarks through

Verdict

Gemini 3.5 Flash places higher on 3 of the 3 tasks where both are ranked. Kimi K3 costs 7.8x less per input token. Only Kimi K3 has open weights for self-hosting.

  • Choose Gemini 3.5 Flash for Translation (#7), Literary Translation (#7), Everyday Translation (#7).
  • 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 3.5 Flash
Model 2Kimi K3
Best for
Business Writing (#5)
JSON & Schema Output (#2)
Provider
google
moonshotai
Context
1.0MBest
1.0MBest
Input / 1M
$1.50
$0.19Best
Output / 1M
$9Best
$16
Tool use
yesBest
yesBest
Vision
yesBest
yesBest
Reasoning
yesBest
yesBest
Open-weight
—
yesBest
Released
May 19, 2026
Jul 16, 2026

Measured head to head

Benchmarks both models were run on

EvaluationGemini 3.5 FlashKimi K3Source
Design Arena Coding1256 Elo1352 Elosource · 2026-11-15
Design Arena Full-stack Agent1170 Elo1289 Elosource · 2026-11-15
Design Arena UI1265 Elo1342 Elosource · 2026-11-15
Design Arena Web-app Agent1177 Elo1273 Elosource · 2026-11-15
Design Arena Website1260 Elo1336 Elosource · 2026-11-15
FrontierMath Tiers 1-3 (Epoch AI)62.8% ± 2.972.2% ± 2.7source · 2026-06-10
GPQA Diamond (Epoch AI)88.9% ± 2.293.1% ± 1.5source · 2026-08-06
GPQA Diamond (Epoch AI)86.4% ± 2.493.1% ± 1.5source · 2026-07-15
GPQA Diamond (Epoch AI)92.8% ± 1.693.1% ± 1.5source · 2026-05-22
LiveBench Agentic Coding49.0%62.2%source · 2026-10-18
LiveBench Coding78.2%81.5%source · 2026-10-18
LiveBench Data Analysis64.9%78.7%source · 2026-10-18
LiveBench Instruction Following75.6%71.4%source · 2026-10-18
LiveBench Language84.6%85.5%source · 2026-10-18
LiveBench Math88.2%84.4%source · 2026-10-18
LiveBench Reasoning82%90.7%source · 2026-10-18
LMArena Creative Writing1469 Elo1453 Elosource · 2026-11-11
LMArena Instruction Following1467 Elo1484 Elosource · 2026-11-11
LMArena Long Query1484 Elo1490 Elosource · 2026-11-11
LMArena Math1504 Elo1496 Elosource · 2026-11-11
LMArena Text1478 Elo1487 Elosource · 2026-11-11
LMArena Text Factuality1478 Elo1471 Elosource · 2026-11-11
LMArena WebDev1500 Elo1658 Elosource · 2026-11-11
LMArena WebDev Image-to-Web1500 Elo1586 Elosource · 2026-11-10
OTIS Mock AIME (Epoch AI)88.9% ± 4.797.2% ± 1.1source · 2026-08-06
OTIS Mock AIME (Epoch AI)80% ± 697.2% ± 1.1source · 2026-07-15
OTIS Mock AIME (Epoch AI)95.6% ± 2.797.2% ± 1.1source · 2026-05-25
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.