Gemini 3.7 Flash vs Kimi K3

At a glance

• Capability index

  • Gemini 3.7 Flash157.3
  • Kimi K3157.4

  Kimi K3 is 0.2 points higher.

• Price per 1M tokens

  • Gemini 3.7 Flash$1.50
  • Kimi K3$6.00

  Gemini 3.7 Flash is 4 times cheaper.

• Context window

  • Gemini 3.7 Flash1M tokens
  • Kimi K31M tokens

  They take in about the same.

• Released

  • Gemini 3.7 FlashAug 13, 2026
  • Kimi K3Jul 16, 2026

  Gemini 3.7 Flash is 28 days newer.

Where each scores higher

On the 22 tests both have taken, each on its own scale. A gap of a point or two can sit within a test’s margin of error.

Level on Arena text, Mock AIME 2024–2025, LiveBench language.

Everything side by side

Comparison of Gemini 3.7 Flash vs Kimi K3

Measure	Gemini 3.7 FlashGoogle	Kimi K3Moonshot AI
Model
Maker	Google	Moonshot AI
Sold here by	Google	Moonshot AI
API model ID	gemini-3.7-flash	kimi-k3
Released	Aug 13, 2026	Jul 16, 2026
Knowledge cutoff	Mar 2026	Not reported
Weights	Closed: hosted access only	Open: downloadable
Developer’s country	United States	China
Hosts selling it	29including Google directly	84including Moonshot AI directly
Training compute	Not published	2.0 × 10²⁵ FLOPEpoch AI estimate
Test results
Capability index	157.3#16 of 274	157.4 (best of these models)#15 of 274
LiveBench overall	78.8%#16 of 66	79.2% (best of these models)#15 of 66
Arena text	1488#17 of 413	1488#16 of 413
LiveBench coding	78.9%#29 of 66	81.5% (best of these models)#15 of 66
Arena WebDev	1592#27 of 138	1658 (best of these models)#13 of 138
Arena coding	1518#41 of 408	1541 (best of these models)#9 of 408
LiveBench mathematics	93.5% (best of these models)#20 of 66	84.4%#53 of 66
Mock AIME 2024–2025	97.2%#31 of 297	97.2%#31 of 297
FrontierMath Tiers 1–3	71.6%#23 of 114	72.2% (best of these models)#22 of 114
FrontierMath Tier 4	36.6%#30 of 70	39.0% (best of these models)#29 of 70
Arena math	1503 (best of these models)#12 of 396	1501#16 of 396
SimpleQA Verified	69.2% (best of these models)#9 of 86	50.6%#24 of 86
LiveBench agentic coding	58.3%#19 of 66	62.2% (best of these models)#10 of 66
DeepSWE	65.5%#25 of 69	68.5% (best of these models)#19 of 69
LiveBench language	85.5%#13 of 66	85.5%#11 of 66
LiveBench instructions	79.9% (best of these models)#2 of 66	71.4%#23 of 66
Arena creative writing	1493 (best of these models)#5 of 411	1460#26 of 411
Arena instruction following	1485#17 of 413	1488 (best of these models)#14 of 413
LiveBench data analysis	68.0%#55 of 66	78.7% (best of these models)#21 of 66
LiveBench reasoning	87.8%#25 of 66	90.7% (best of these models)#9 of 66
GPQA Diamond	94.8% (best of these models)#5 of 319	93.1%#20 of 319
Chess puzzles	47.0% (best of these models)#14 of 227	39.0%#31 of 227
Arena hard prompts	1508#19 of 413	1517 (best of these models)#9 of 413
Price per million tokens
Input	$0.75 (best of these models)	$3.00
Output	$3.75 (best of these models)	$15.00
Blended, 3 input to 1 output	$1.50 (best of these models)	$6.00
Cached input	$0.075 (best of these models)	$0.30
Audio input	$0.75	Not reported
The maker’s own price	This listing	This listing
Limits
Context window	1M tokens	1M tokens
Max input	936K tokens	1M tokens (best of these models)
Max output	65.5K tokens	1M tokens (best of these models)
Features
Reads	audio, images, PDFs, text and video	images, text and video
Produces	text	text
Reasoning	Yeseffort low, medium, high	Yeseffort low, high, max; can be switched off; thinking budget can be set
Tool calling	Yes	Yes
Structured output	Yes, such as JSON	Yes, such as JSON
File attachments	Yes	Yes
Temperature setting	Supported	Fixed by the provider

Bold marks the better value in each row. Prices are each model’s own list price, or the middle price across hosts when the maker does not sell it, blended as three input tokens for every output token. Test results as published by LiveBench (Apache-2.0), Epoch AI (CC BY 4.0), Datacurve DeepSWE, compiled by Epoch AI (CC BY 4.0), Arena (CC BY 4.0); model details and prices from models.dev (MIT). Confirm pricing with the provider before use.