Noometry

Model comparison

Claude 3.5 Haiku vs Nova 2 Lite

Nova 2 Lite is the stronger model overall, scoring 39.7 to 29.2 on the Noometry Index.

Last verified . 17 shared benchmarks.

Claude 3.5 Haiku Anthropic

29.2

Rank #315 Confirmed

Nova 2 Lite Amazon

39.7

Rank #161 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 1 category and Nova 2 Lite in 8 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Nova 2 Lite leads 43.0 to 18.7.

Side by side

Claude 3.5 HaikuNova 2 Lite
ProviderAnthropicAmazon
Noometry Index29.239.7
Released2024-10-222025-12-01
WeightsProprietaryProprietary
Context window—1M
Max output—64K
Input $ / M tokens—$0.30
Output $ / M tokens—$2.50
Results tracked4919

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

Category by category

Coding Nova 2 Lite leads

Claude 3.5 Haiku: 32.9 (#265), Nova 2 Lite: 40.7 (#134)

BenchmarkClaude 3.5 HaikuNova 2 Lite
LMArena Coding12861385
Aider Polyglot28%—
SciCode27.4%—
WeirdML30.7%—
BigCodeBench Instruct46.1%—
LiveBench Coding51.4%—
BigCodeBench Complete59%—
CadEval32%—

Agentic & Tool Use Claude 3.5 Haiku leads

Claude 3.5 Haiku: 28.0 (#95), Nova 2 Lite: 24.1 (#121)

BenchmarkClaude 3.5 HaikuNova 2 Lite
Berkeley Function Calling Leaderboard—27.1%
BALROG19.3%—

Reasoning Nova 2 Lite leads

Claude 3.5 Haiku: 17.7 (#290), Nova 2 Lite: 27.5 (#118)

BenchmarkClaude 3.5 HaikuNova 2 Lite
LMArena Hard Prompts12511364
CritPt0%—
LiveBench Reasoning28.1%—
DTBench56.7%—
LiveBench Data Analysis48.5%—
Epoch Capabilities Index127.15—
LiveBench43.5%—

Math Nova 2 Lite leads

Claude 3.5 Haiku: 14.7 (#300), Nova 2 Lite: 37.5 (#156)

BenchmarkClaude 3.5 HaikuNova 2 Lite
LMArena Math12441359
OTIS Mock AIME 2024-20254.3%—
Omni-MATH22.4%—
LiveBench Math35.5%—
MATH Level 546.4%—
FrontierMath (Feb 2025 set)0.3%—

Knowledge Nova 2 Lite leads

Claude 3.5 Haiku: 18.7 (#281), Nova 2 Lite: 43.0 (#94)

BenchmarkClaude 3.5 HaikuNova 2 Lite
LMArena Expert12081358
GPQA Diamond38.1%—
MMLU-Pro60.5%—
Confabulations36.7%—
Vectara Hallucination Rate—5.1%
GPQA (HELM)36.3%—
MMLU74.3%—

Multimodal Not comparable

Claude 3.5 Haiku: 26.8 (#117), Nova 2 Lite: —

BenchmarkClaude 3.5 HaikuNova 2 Lite
LMArena Vision1092—
GeoBench34%—

Multilingual Nova 2 Lite leads

Claude 3.5 Haiku: 40.0 (#218), Nova 2 Lite: 47.1 (#153)

BenchmarkClaude 3.5 HaikuNova 2 Lite
LMArena Non-English12381337
LMArena Chinese12291364
LMArena French12641381
LMArena German12371343
LMArena Japanese11751271
LMArena Korean11731284
LMArena Russian12531343
LMArena Spanish12611373

Instruction Following Nova 2 Lite leads

Claude 3.5 Haiku: 62.9 (#234), Nova 2 Lite: 70.5 (#161)

BenchmarkClaude 3.5 HaikuNova 2 Lite
LMArena Instruction Following12411335
LiveBench Instruction Following61.9%—
IFEval79.2%—

Long Context Nova 2 Lite leads

Claude 3.5 Haiku: 38.3 (#200), Nova 2 Lite: 40.6 (#150)

BenchmarkClaude 3.5 HaikuNova 2 Lite
LMArena Longer Query12611335

Writing & Preference Nova 2 Lite leads

Claude 3.5 Haiku: 42.7 (#234), Nova 2 Lite: 53.9 (#154)

BenchmarkClaude 3.5 HaikuNova 2 Lite
LMArena Text12551362
LMArena Creative Writing12331291
LMArena Multi-Turn12651338
Short-Story Creative Writing73.5%—
EQ-Bench Creative Writing1146—
WildBench76%—
LiveBench Language35.4%—

Frequently asked questions

Is Claude 3.5 Haiku better than Nova 2 Lite?

Nova 2 Lite is the stronger model overall, scoring 39.7 to 29.2 on the Noometry Index.

Is Claude 3.5 Haiku or Nova 2 Lite better for coding?

Nova 2 Lite scores higher on coding benchmarks: 40.7 versus 32.9 in the Noometry coding category.

How many benchmarks do Claude 3.5 Haiku and Nova 2 Lite share?

17 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Nova 2 Lite has 19.

Related comparisons

Go deeper