Nova Lite

+ contribute

Nova Lite is a closed-weights language model from Amazon, released December 2024.

Catalogue identity notes

Arena entry 'amazon-nova-lite-v1.0' (text, vision). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'amazon-nova-lite-v1.0' as 'Amazon Nova Lite 1.0' (Amazon, Proprietary), linking https://docs.aws.amazon.com/nova/latest/userguide/what-is-nova.html. Released 2024-12: Bedrock model card: 'Model launch date: Dec 05, 2024'. Bedrock model id amazon.nova-lite-v1:0, 'Model lifecycle: Active' (Bedrock model card). First-generation Nova Lite; distinct from nova-2-lite.

48.8±2.1#366 of 719 LLMsfrom 8 benchmark results across 4 sources

$ how it compares

The LLMs ranked either side of Nova Lite, out of 828 with a score, then more from Amazon.

#	model	score	where	RAM	released
435	speechless-codellama-34b-v2.0 uukuguy	49±1	local	~23GB	2023-10
436	Pixtral 12B (2409) Mistral	49±2	local	~9.6GB	2024-09
437	Nova Lite Amazon	49±2	api $0.10/M		2024-12
438	MegaBeam-Mistral-7B-512k AWS (aws-prototyping)	49±4	local	~6.1GB	2024-07
439	GPT-4o Audio Preview (2024-12-17) OpenAI	49±2	comparison only		2024-12
	more from Amazon
184	Nova 2 Pro (Preview) Amazon	64±2	api $3.78/M		2025-11
269	Nova 2 Lite Amazon	58±2	api $0.94/M		2025-10
339	Nova Premier Amazon	54±2	api $5.00/M		2025-04

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▃▆█▆▅▅▅▄▃▁ #230 of 300 · 31% of its score · 4 tests

Beats o3-mini, Ministral 3 14B Reasoning 2512, DeepSeek R1 0528 Qwen3 8B here, though they rank higher overall. Trails SmolLM3 3B, Phi-3.5-mini-instruct, Jamba 1.5 Mini here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
BFCL v3	55.9% ✎	▁▁▁▁▁▃▅█▅▄▁▁ beats 60/114	medium · avg 52%	▇▇▇ 8.6%	blunt · at its level
BFCL V4 (2025-11-03 archive, models absent from the December archive)	33.2% ✎	▃··▅▃▃·▅·▃·█ beats 1/10	hard · avg 34%	▇▇▇ 8.1%	at its level
Galileo Agent Leaderboard v1 (tool selection quality)	86.8% ✎	▃▃▃▃▆▅▆▅█▂▅▂ beats 16/31	easy · avg 79%	▇▇▇ 7.7%	blunt
Galileo Agent Leaderboard v2 (action completion)	16.0% ✎	▅▃·▃▃▅▅█▃█▅▅ beats 0/19	hard · avg 27%	▇▇ 6.2%	at its level

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #264 of 393 * · 39% of its score · 1 test

Beats Ministral 3 14B Reasoning 2512, Ministral 3 14B, Phi-4 14B here, though they rank higher overall. Trails Flan-T5 XXL, Granite 4.0 H 1B, Granite 4.0 1B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
LMArena (text)	1260.4 ✎	▁▁▁▂▃▃▃▆▆▇█▃ beats 96/379	avg 1268	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 39%	blunt

vision & documents▁▁▃▃▁▃▄▂▆▇█▄ #129 of 147 * · 27% of its score · 1 test

Trails Qwen2-VL 7B Instruct, InternVL2-26B, Qwen3.5 2B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Arena vision (style controlled)	1018.8 ✎	▁▁▂▃▂▂▄▅▅▆██ beats 15/145	avg 1068	▇▇▇▇▇▇▇▇▇▇▇ 27%	blunt

other tests2 not in a task · 2.5% of its score

test	result	vs the others in its run	difficulty	counts	why
Vectara hallucination leaderboard, 2025 dataset (HHEM-2.3, factual consistency rate)	98.2% ✎	▁▁▂▃▄▄█▆▃▃▂▁ beats 126/140	very easy · avg 94%	▇ 2.5%	blunt · maxed out · noisy
Vectara hallucination leaderboard (HHEM-2.3, factual consistency rate)	93.9% ✎	▁▂▁▂▅█▂▃▄▃▁▁ beats 77/98	very easy · avg 90%	▇ 0.0%	blunt

$ where to run it

Through an API

api · Amazon Bedrock · $0.10/M · $0.06 in / $0.24 out per 1M tokens · 300k context · docs.aws.amazon.com ↗ · price sourceUSD per 1M tokens, Standard tier, geo cross-Region inference and in-Region, US East (N. Virginia). Amazon Nova Lite (amazon.nova-lite-v1:0). Observed 2026-09-28 (page price data $0.00006/$0.00024 per 1K tokens).

$ how the score was worked out · LMArena leaderboard dataset 65%, Berkeley Function Calling Lea… 17%, Galileo Agent Leaderboard (v1… 14% and 1 more

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

source	results	share of the score	licence
LMArena leaderboard dataset	2	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 65%	CC BY 4.0
Berkeley Function Calling Leaderboard result archive	2	▇▇▇▇▇ 17%	Apache-2.0
Galileo Agent Leaderboard (v1 and v2 results)	2	▇▇▇▇ 14%	Apache-2.0
Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository)	2	▇ 2%	Apache-2.0
prior · pull toward the middle		▇ 2%
weighted average		= 48.8