moonshotai

🇨🇳China

Top Model

Kimi K3.1 Pro

65.8

avg score

Compare moonshotai models All providers

Total Models

tracked on BenchGecko

Open Source

62% of models

$0.19

Cheapest Model

per 1M input tokens

53.5

Avg Benchmark

across 7 scored models

Model Categories

Multimodal8LLM5

Pricing Range · $/1M input tokens

$0.19

$0.53

$0.57

$0.60

$0.65

$0.70

$0.95

$2.00

$2.28

Low: $0.19Median: $0.60High: $2.28

Open Source Ratio

62%

8 open source5 proprietary

All moonshotai Models13 total

#▲	Model	Avg	ANLI?	APEX-Agents?	ARC AI2?	ARC-AGI?	ARC-AGI-2?	aider poly?	aider edit	aa critpt	aa gdpval	aa gpqa di	aa humanit	aa ifbench	aa long co	aa mmmu pr	aa scicode	aa termina	aa tau2 be	aa agentic?	aa coding ?	aa quality	seal audio	seal audio	seal audio	BBH?	hf bbh	Balrog?	C-Eval	CMMLU	CSQA2	CadEval?	charxiv re?	charxiv re?	arena elo	arena elo	chess puzz?	Cl Bench	cl bench l	Cybench?	deepresear?	Deepswe	Dtbench	Ebr Bench	EnigmaEval	Exploitbench	fiction li?	Fortress	frontierma?	frontierma?	frontierma	frontierma	Frontiercode	Frontierswe	furniture	GPQA	GPQA diamond?	GSM8K?	GSO-Bench?	Gdpval	GeoBench?	graphwalks?	HELM · GPQA	helm ifeva	helm mmlu	helm omni	helm wildb	HLE?	hle tools	HellaSwag?	seal human	seal human	IFEval	jp jcommon	JHumanEval	JMMLU	JNLI	JSQuAD	LAMBADA?	jp overall	lech mazur?	livebench	livebench	livebench	livebench	livebench	livebench	livebench	livebench	Lmca	MASK	MATH Level 5	MATH level 5?	MCP Atlas	MMLU?	MMLU-PRO	MMMLU	mmmlu ar	mmmlu bn	mmmlu zh	mmmlu fr	mmmlu de	mmmlu hi	mmmlu id	mmmlu it	mmmlu ja	mmmlu ko	mmmlu pt	mmmlu es	mmmlu sw	mmmlu yo	MUSR	metr time	Mirrorcode	seal multi	MultiNRC	mystery ga	OSWorld?	otis mock ?	OpenBookQA?	oc aime202	oc gpqa di	oc hle	oc ifeval	oc livecod	oc mmlu pr	Osworld 2 0	PIQA?	posttrainb	seal pro r	seal pro r	Proofbench	seal prope	remote lab	seal remot	seal swe a	seal swe a	seal swe b	seal swe b	swe bench ?	swe bench ?	swe bench	swe bench	swe bench	SciPredict	ScienceQA?	SimpleBench?	simpleqa v?	SpireClimb	surface ev	terminal b?	the agent ?	TriviaQA?	TutorBench	USAMO	VISTA	VPCT?	VideoMME?	seal visua	WeirdML?	WeirdML v3	Winogrande?	$/1M in	Context	Released
1	Kimi K3.1 Pro🇨🇳 moonshotai	70.0	-	65.5	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	42.1	-	-	-	-	-	88.9	-	-	-	-	-	-	-	65.8	82.4	-	-	36.9	-	96.1	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	67.8	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	36.1	-	100.0	-	-	-	-	-	-	-	-	-	-	-	-	91.0	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	62.2	-	-	-	-	-	-	-	-	-	-	-	-	21.0	-	$2.00	1.0M	Oct 2620d ago
2	Kimi K3🇨🇳 moonshotai	63.4	-	47.8	-	94.5	60.4	-	-	23.4	51.7	93.5	46.9	-	88.7	80.5	59.5	-	-	-	-	43.6	-	-	-	-	-	-	-	-	-	-	-	-	-	-	33.7	-	-	-	-	68.5	85.3	-	-	-	-	-	-	-	39.0	76.0	44.2	25.9	6.0	-	94.6	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	62.0	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	54.4	-	-	18.5	-	97.2	-	-	-	-	-	-	-	-	-	31.5	-	-	87.0	-	-	-	-	-	-	-	-	-	-	-	-	-	-	52.8	50.6	-	95.0	-	-	-	-	-	-	-	-	-	82.6	17.1	-	$0.19	1.0M	Jul 263mo ago
3	Kimi K2.7 Code🇨🇳 moonshotaiOpen	61.7	-	37.6	-	-	-	-	-	10.0	26.9	89.6	35.0	63.1	79.3	-	47.8	44.7	90.1	29.6	60.8	25.8	-	-	-	-	-	-	-	-	-	-	-	-	-	-	9.5	-	-	-	-	30.5	-	-	-	-	-	-	-	-	12.2	56.9	30.1	-	-	-	87.3	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	70.0	74.0	62.7	56.3	77.9	79.6	71.9	82.8	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	95.5	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	49.5	36.5	-	48.8	-	-	-	-	-	-	-	-	-	54.1	-	-	$0.60	262K	Jun 265mo ago
4	Kimi K2 0711🇨🇳 moonshotaiOpen	57.1	-	-	-	-	-	59.1	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	61.1	-	-	-	-	-	-	-	-	-	-	-	4.9	-	-	-	65.2	85.0	81.9	65.4	86.2	-	-	-	-	-	-	-	-	-	-	-	-	-	85.6	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	11.6	-	-	-	27.8	-	-	-	-	-	-	-	-	39.4	-	-	$0.57	131K	Jul 251y ago
5	Kimi K2.5🇨🇳 moonshotaiOpen	57.1	-	14.4	-	65.3	11.8	-	-	-	-	-	-	-	-	-	-	-	-	58.9	39.5	46.8	-	-	-	-	-	-	-	-	-	-	-	-	-	-	12.0	19.3	13.2	-	-	-	-	-	-	-	86.1	-	27.9	7.0	-	-	-	-	-	-	86.9	-	-	-	-	-	-	-	-	-	-	20.6	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	63.3	92.2	-	91.9	88.1	28.6	93.9	80.6	86.2	-	-	10.3	-	-	-	-	-	-	-	-	-	-	-	73.8	-	-	-	-	-	36.2	34.3	-	-	43.2	-	-	54.6	-	-	-	-	-	45.6	-	-	$0.53	262K	Jan 269mo ago
6	Kimi K2 Thinking🇨🇳 moonshotaiOpen	56.7	-	4.0	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	20.0	17.6	-	-	-	-	-	-	-	-	-	-	21.4	0.0	-	-	-	-	-	-	79.0	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	38.3	67.4	52.3	62.0	66.5	81.1	61.6	63.5	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	59.2	-	-	-	-	-	83.0	-	94.1	82.7	21.3	92.4	77.1	84.3	-	-	7.3	-	-	-	-	-	-	-	-	-	-	63.4	-	-	-	-	-	-	27.5	31.6	-	-	35.7	-	-	-	-	-	-	-	-	42.8	-	-	$0.60	262K	Nov 251y ago
7	Kimi K2.6🇨🇳 moonshotaiOpen	41.6	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	30.3	56.0	42.8	-	-	-	-	-	-	-	-	-	-	-	-	1508.7	1461.0	15.8	-	-	-	-	-	84.9	2.4	-	18.4	-	-	39.0	14.6	25.6	60.2	-	-	0.0	-	91.4	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	43.8	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	9.7	-	96.1	-	-	-	-	-	-	-	4.6	-	-	-	-	16.0	-	-	-	-	-	-	-	-	76.7	-	-	-	-	-	-	34.9	-	-	-	-	-	-	-	-	-	-	-	55.9	-	-	$0.65	262K	Apr 266mo ago

90+ Gold 80-89 70-79 60-69 <60Scores in % unless noted. Avg = unweighted mean across tested benchmarks.

About moonshotai

Quick answers · sourced from our data

How many models does moonshotai have?

BenchGecko tracks 13 models from moonshotai, of which 8 (62%) are open source. Every entry is updated daily from live provider feeds.

What is the best model from moonshotai?

Kimi K3.1 Pro is currently the highest scoring moonshotai model we track, with an average benchmark score of 65.8. Scores are computed across every public benchmark we have data for.

What is the cheapest moonshotai model?

The cheapest moonshotai model on BenchGecko starts at $0.19 per 1M input tokens. Pricing is pulled from OpenRouter and cross-checked against official provider rate cards.

How does moonshotai compare on benchmarks?

moonshotai models average 53.5 across the benchmarks we track · see the All Providers page for the full ranking by model count, open source ratio, and average score.

Where is moonshotai based?

moonshotai is headquartered in China. BenchGecko groups providers by region to make it easy to compare US, EU, China, and Rest of World markets.

Is moonshotai open source?

8 of 13 moonshotai models are open source (62%). The rest are proprietary · closed weights served via API.

All Providers 🇨🇳 View by Country moonshotai · Economy →Pricing →Compare →Full Leaderboard →