Compare / Google vs Moonshot AI

AI labs compared · November 2026

Google vs Moonshot AI: which AI lab is ahead?

Each lab's best model on sale goes head to head on every kind of work we measure, from our own benchmarks and licensed sources. 28 models in all; a lab is only as good as the model you would actually pick from it.

20 models on sale with our resultsGoogle Best: Gemini 4 Argon · newest: Gemini 4 Neon
8 models on sale with our resultsMoonshot AI Best: Kimi K3.1 Pro · newest: Kimi K3.1 Pro
Google wins 7Moonshot AI wins 3

Kinds of work led by each lab's best model there, of the 10 both are measured on.

Results as of 19 November 2026 (catalogue release 2026-11-19-3608133e8331). Models on sale means listed on OpenRouter today.

Google or Moonshot AI? The short answer

Google is ahead: its best models beat Moonshot AI's in 7 of the 10 kinds of work both are measured on; Moonshot AI leads in 3.

  • Pick Google for product listings, user surveys, professional work, reasoning and knowledge, writing, sticking to the facts and speed under pressure.
  • Pick Moonshot AI for decks from an analysis, marketing planning and agents and tool use.
  • On our overall leaderboard, Gemini 4 Argon is #8 (70 of 100) and Kimi K3.1 Pro is #9 (67).
  • Prices start at $0.042 per million tokens for Google (Gemma 3 4B) and $1.00 for Moonshot AI (Kimi K2 (0711)).

Head to head

70Gemini 4 Argon
Best Spring Prompt overall score
67Kimi K3.1 Pro
52.6Gemini 4 Argon
Best Intelligence Index
43.6Kimi K3
$4.00Gemini 4 Argon
Flagship price, per million tokens
$3.81Kimi K3.1 Pro
$0.042Gemma 3 4B
Cheapest model, per million tokens
$1.00Kimi K2 (0711)
20
Models on sale with our results
8

Each line names the model behind the number. Prices are blended, three input tokens to one output, at the developer's list price where we have read it; see every model's price. Intelligence Index from Artificial Analysis; overall score from our leaderboard.

Which lab is better for what

For each kind of work, each lab's best model there and its rank among every model on sale. Further right is better; the better rank is in green.

Product listingsTurning a sparse product feed and photos into listings that can go live 6 of 35Gemini 4 Neon 24 of 35Kimi K3
Decks from an analysisTurning a finished analysis into a deck you could present as it is 21 of 35Gemini 4 Hydrogen 14 of 35Kimi K3.1 Pro
User surveysPlanning a user survey and reading its results without being misled 13 of 26Gemini 4 Hydrogen 23 of 26Kimi K3.1 Pro
Marketing planningPlanning a year of ad spend without overspending 13 of 35Gemini 3.8 Flash 5 of 35Kimi K3.1 Pro
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 5 of 159Gemini 4 Argon 1 of 159Kimi K3.1 Pro
Professional workReal tasks from banking, consulting and law, business documents and freelance projects 11 of 51Gemini 3.8 Flash 24 of 51Kimi K3
Reasoning and knowledgeHard questions across science, maths and general knowledge 4 of 187Gemini 4 Argon 9 of 187Kimi K3.1 Pro
WritingWhat people prefer in blind comparisons, and judged writing quality 1 of 169Gemini 4 Argon 12 of 169Kimi K3
Sticking to the factsSummarising without inventing things, and factual answers 1 of 139Gemini 4 Argon 27 of 139Kimi K3
Speed under pressureGood decisions against a real clock (fast chess) 2 of 38Gemini 3.5 Flash-Lite 29 of 38Kimi K3.1 Pro

Every model, by intelligence and price

Each dot is a model on sale with an Intelligence Index from Artificial Analysis. Up is smarter; left is cheaper. Hover or tap a dot for its name.

GoogleMoonshot AI

0204060 $0.01$0.1$1$10 Price per million tokens, blended (log scale) Intelligence Index Gemini 4 ArgonGemini 3.8 FlashGemini 3.7 FlashGemini 3.6 FlashGemini 3.5 FlashKimi K3

On our overall leaderboard

The 9 of their models we rank overall: one score out of 100 across everything we publish (how the score works). Only models with enough of our own results are ranked.

  1. #8Gemini 4 Argon70
  2. #9Kimi K3.1 Pro67
  3. #14Gemini 4 Neon60
  4. #14Gemini 4 Hydrogen60
  5. #18Gemini 3.8 Flash57
  6. #20Gemini 4 Carbon50
  7. #22Kimi K346
  8. #23Gemini 3.1 Pro Preview44
  9. #35Gemini 3.5 Flash-Lite24

Benchmark by benchmark

The headline result of every benchmark both labs have models on: each lab's best model and its rank among the models on sale. Green marks the better rank.

MeasureGoogleMoonshot AI
Agents and tool use
Berkeley Function Calling Leaderboard (BFCL) V4 · Overall accuracy · BFCL% correct, higher is better 56.2%Gemini 2.5 Flash · 8 of 3659.1%Kimi K2 (0711) · 6 of 36
OpenHands Index · Average% resolved, higher is better 62.6%Gemini 3.5 Flash · 7 of 3157.1%Kimi K2.6 · 14 of 31
Artificial Analysis · Terminal-Bench 4.0% of tasks, higher is better 57.1%Gemini 4 Argon · 5 of 10767.2%Kimi K3.1 Pro · 1 of 107
Artificial Analysis · Terminal-Bench 2.1% of tasks, higher is better 87.6%Gemini 3.8 Flash · 8 of 10785.0%Kimi K3 · 11 of 107
Artificial Analysis · τ-bench banking% of tasks, higher is better 45.8%Gemini 3.8 Flash · 10 of 10446.0%Kimi K3 · 9 of 104
Vending-Bench 2 · Money after a yearUS dollars, higher is better $5,396Gemini 3.5 Flash · 22 of 53$6,205Kimi K2.6 · 15 of 53
Decks from an analysis
DeckBench · Deck ratingrating, higher is better 1,079Gemini 4 Hydrogen · 21 of 351,223Kimi K3.1 Pro · 14 of 35
Marketing planning
ROASBench · Overall scorescore out of 100, higher is better 51.4Gemini 3.8 Flash · 13 of 3555.1Kimi K3.1 Pro · 5 of 35
Product listings
CatalogBench · Reliably publish-ready% of products, higher is better 78.6%Gemini 4 Neon · 1 of 3541.1%Kimi K3 · 20 of 35
CatalogBench · Reliably publish-ready · sales brief% of products, higher is better 32.1%Gemini 4 Neon · 13 of 351.8%Kimi K3 · 28 of 35
Professional work
APEX-Agents · Tasks passed% of tasks, higher is better 67.8%Gemini 3.7 Flash · 4 of 3750.6%Kimi K3 · 21 of 37
GDP.pdf · Professional document tasks% of rubric, higher is better 23.8%Gemini 3.7 Flash · 11 of 3119.0%Kimi K3 · 17 of 31
Reasoning and knowledge
Artificial Analysis · Artificial Analysis Intelligence Indexindex score, higher is better 52.6Gemini 4 Argon · 5 of 18543.6Kimi K3 · 19 of 185
Artificial Analysis · Humanity's Last Exam% of questions, higher is better 57.1%Gemini 4 Argon · 3 of 18652.5%Kimi K3.1 Pro · 9 of 186
Artificial Analysis · GPQA Diamond% of questions, higher is better 95.3%Gemini 3.8 Flash · 2 of 16893.5%Kimi K3 · 10 of 168
Speed under pressure
BulletBench · Ladder Elo · Bullet 60sladder Elo, higher is better 1,068Gemini 3.8 Flash · 1 of 36147Kimi K3.1 Pro · 28 of 36
Sticking to the facts
Vectara Hallucination Leaderboard · Hallucination rate · Vectara% of summaries, lower is better 3.3%Gemini 2.5 Flash-Lite · 2 of 7110.8%Kimi K2.6 · 48 of 71
Arena (formerly LMArena) · Overall · Text factualityArena rating, higher is better 1,511Gemini 4 Argon · 1 of 1091,472Kimi K3 · 17 of 109
SimpleQA Verified (Epoch AI) · Correct answers% of questions, higher is better 73.5%Gemini 3.1 Pro Preview · 3 of 6850.6%Kimi K3 · 22 of 68
User surveys
SurveyBench · Analysis ratingrating, higher is better 1,096Gemini 4 Hydrogen · 13 of 26605Kimi K3.1 Pro · 23 of 26
Writing
Arena (formerly LMArena) · Overall · TextArena rating, higher is better 1,525Gemini 4 Argon · 1 of 1531,488Kimi K3 · 12 of 153
UGI Leaderboard · Writing score · UGIscore out of 100, higher is better 78.6Gemini 3.8 Flash · 1 of 12464.4Kimi K2.6 · 25 of 124

Their models, one against one

Quick answers

Is Google or Moonshot AI better?

Google is ahead: its best models beat Moonshot AI's in 7 of the 10 kinds of work both are measured on; Moonshot AI leads in 3.

What is Google's best model?

Gemini 4 Argon: #8 on the Spring Prompt overall leaderboard and 52.6 on the Artificial Analysis Intelligence Index.

What is Moonshot AI's best model?

Kimi K3.1 Pro: #9 on the Spring Prompt overall leaderboard.

Which is better for agents and tool use, Google or Moonshot AI?

Moonshot AI: its best model there, Kimi K3.1 Pro, ranks 1 of 159 models on sale, against 5 for Google's Gemini 4 Argon.

Which is better for reasoning and knowledge, Google or Moonshot AI?

Google: its best model there, Gemini 4 Argon, ranks 4 of 187 models on sale, against 9 for Moonshot AI's Kimi K3.1 Pro.

Which is better for writing, Google or Moonshot AI?

Google: its best model there, Gemini 4 Argon, ranks 1 of 169 models on sale, against 12 for Moonshot AI's Kimi K3.

Which is cheaper, Google or Moonshot AI?

Google's cheapest model with results, Gemma 3 4B, costs $0.042 per million tokens (three input to one output), against $1.00 for Kimi K2 (0711) from Moonshot AI.

Other labs compared

Which model is best for your product?

Benchmarks aren't your task. Run models from Google, Moonshot AI and the rest on your own prompt, and see the cheapest one that passes.