Noometry

Amazon, proprietary

Nova 2 Lite

Nova 2 Lite by Amazon ranks 161st of 354 ranked models on the Noometry Index as of October 2026, with a score of 39.7. Its strongest category is knowledge, where it ranks 94th. API pricing starts at $0.30 per million input tokens and $2.50 per million output tokens, with a 1M-token context window.

Last verified

Noometry rank
#161 of 354
Index score
39.7
Evidence
Confirmed 19 results
Provider
Amazon
Released
December 1, 2025
Weights
Proprietary
Reasoning
Yes
Context window
1M
Max output
64K
Input price
$0.30 / M
Output price
$2.50 / M
Blended price
$0.85 / M
Output speed
Not measured
Value
#99 of 219
Knowledge cutoff
October 2025
Input
text, image, video, pdf

Category scores

Each category score combines every public result we have in that category.

  1. Coding 40.7
  2. Agentic & Tool Use 24.1
  3. Reasoning 27.5
  4. Math 37.5
  5. Knowledge 43.0
  6. Multilingual 47.1
  7. Instruction Following 70.5
  8. Long Context 40.6
  9. Writing & Preference 53.9
CategoryScoreRankResults
Coding40.7#1341
Agentic & Tool Use24.1#1211
Reasoning27.5#1181
Math37.5#1561
Knowledge43.0#942
Multilingual47.1#1531
Instruction Following70.5#1611
Long Context40.6#1501
Writing & Preference53.9#1543

Strengths and weaknesses

Categories where Nova 2 Lite places highest and lowest among the models ranked in each, with its score against that category's median.

Strongest categories

CategoryScorevs medianRank
Knowledge43.0+5.7#94 of 314, top 30%
Reasoning27.5+3.9#118 of 350, top 34%
Coding40.7+2.0#134 of 340, top 40%

Weakest categories

CategoryScorevs medianRank
Agentic & Tool Use24.1−6.2#121 of 154, top 79%
Instruction Following70.5−0.8#161 of 305, top 53%
Multilingual47.1−0.3#153 of 297, top 52%

Closest competitors

The models ranked just above and below Nova 2 Lite. When scores are this close, price and speed are often the better way to choose.

ModelRankScoreBlended $/MSpeed
Grok 3#15739.9—42Compare
GLM-4.5V#15839.8$0.9034Compare
QwQ-32B#15939.8——Compare
Step 1o Turbo 202506#16039.7——Compare
DeepSeek-V3.2-Speciale#16239.7$0.85—Compare
Hunyuan Turbo 0110#16339.6——Compare
Claude 3.7 Sonnet#16439.5——Compare
Claude Haiku 4.5#16539.5$2—Compare

Sponsored placements are available on pages like this one. Advertise on Noometry

Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

Coding

BenchmarkScorePositionSettingSourceDate
LMArena Coding1385#145 of 294, top 50%LMArena2026-10-08

Agentic & Tool Use

BenchmarkScorePositionSettingSourceDate
Berkeley Function Calling Leaderboard27.1%#40 of 49, top 82%fcBerkeley Function Calling Leaderboard

Reasoning

BenchmarkScorePositionSettingSourceDate
LMArena Hard Prompts1364#152 of 297, top 52%LMArena2026-10-08

Math

BenchmarkScorePositionSettingSourceDate
LMArena Math1359#158 of 285, top 56%LMArena2026-10-08

Knowledge

BenchmarkScorePositionSettingSourceDate
Vectara Hallucination Rate (lower is better)5.1%#10 of 96, top 11%Vectara Hallucination Leaderboard
LMArena Expert1358#150 of 273, top 55%LMArena2026-10-08

Multilingual

BenchmarkScorePositionSettingSourceDate
LMArena Non-English1337#153 of 297, top 52%LMArena2026-10-08
LMArena Chinese1364#159 of 285, top 56%LMArena2026-10-08
LMArena French1381#131 of 223, top 59%LMArena2026-10-08
LMArena German1343#134 of 231, top 59%LMArena2026-10-08
LMArena Japanese1271#133 of 211, top 64%LMArena2026-10-08
LMArena Korean1284#136 of 213, top 64%LMArena2026-10-08
LMArena Russian1343#150 of 283, top 54%LMArena2026-10-08
LMArena Spanish1373#130 of 226, top 58%LMArena2026-10-08

Instruction Following

BenchmarkScorePositionSettingSourceDate
LMArena Instruction Following1335#154 of 298, top 52%LMArena2026-10-08

Long Context

BenchmarkScorePositionSettingSourceDate
LMArena Longer Query1335#159 of 291, top 55%LMArena2026-10-08

Writing & Preference

BenchmarkScorePositionSettingSourceDate
LMArena Text1362#149 of 297, top 51%LMArena2026-10-08
LMArena Creative Writing1291#174 of 295, top 59%LMArena2026-10-08
LMArena Multi-Turn1338#166 of 295, top 57%LMArena2026-10-08

API pricing by provider

RouteInput $/MOutput $/MCached input $/MChecked
bedrock$0.33$2.75$0.08252026-10-10
openrouter$0.30$2.50—2026-10-10

All Amazon API prices → Estimate your cost →

Compare Nova 2 Lite

Other Amazon models

Frequently asked questions

How good is Nova 2 Lite?

Nova 2 Lite by Amazon ranks 161st of 354 ranked models on the Noometry Index as of October 2026, with a score of 39.7. Its strongest category is knowledge, where it ranks 94th. API pricing starts at $0.30 per million input tokens and $2.50 per million output tokens, with a 1M-token context window.

How much does Nova 2 Lite cost?

Nova 2 Lite costs $0.30 per million input tokens and $2.50 per million output tokens on openrouter.

What is Nova 2 Lite's context window?

Nova 2 Lite accepts up to 1M tokens of input and can write up to 64K tokens in one response.

Is Nova 2 Lite open source?

No. Nova 2 Lite is proprietary and available only through Amazon's API and partner platforms.

What are Nova 2 Lite's strengths and weaknesses?

Relative to other ranked models, Nova 2 Lite places best in knowledge, reasoning, coding and lowest in agentic & tool use, instruction following, multilingual.

What is Nova 2 Lite best at?

Its best category is knowledge, where it ranks 94th on Noometry.