Noometry

Model comparison

Claude 3.5 Haiku vs Nova Premier 1.0

Nova Premier 1.0 is the stronger model overall, scoring 37.7 to 28.9 on the Noometry Index.

Last verified . 5 shared benchmarks.

Claude 3.5 Haiku Anthropic

28.9

Rank #309 Confirmed

Nova Premier 1.0 Amazon

37.7

Rank #185 Confirmed

Summary

  • They share 5 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 0 categories and Nova Premier 1.0 in 5 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in math, where Nova Premier 1.0 leads 31.5 to 13.7.
  • The biggest single-benchmark swing is GPQA (HELM): 36.3% for Claude 3.5 Haiku and 51.8% for Nova Premier 1.0.

Side by side

Claude 3.5 HaikuNova Premier 1.0
ProviderAnthropicAmazon
Noometry Index28.937.7
Released2024-10-222025-04-30
WeightsProprietaryProprietary
Context window—1M
Max output—10K
Input $ / M tokens—$2.50
Output $ / M tokens—$12.50
Results tracked496

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

Category by category

Coding Not comparable

Claude 3.5 Haiku: 32.6 (#258), Nova Premier 1.0: —

BenchmarkClaude 3.5 HaikuNova Premier 1.0
Aider Polyglot28%—
SciCode27.4%—
WeirdML30.7%—
BigCodeBench Instruct46.1%—
LiveBench Coding51.4%—
LMArena Coding1287—
BigCodeBench Complete59%—
CadEval32%—

Agentic & Tool Use Not comparable

Claude 3.5 Haiku: 27.7 (#90), Nova Premier 1.0: —

BenchmarkClaude 3.5 HaikuNova Premier 1.0
BALROG19.3%—

Reasoning Nova Premier 1.0 leads

Claude 3.5 Haiku: 17.1 (#286), Nova Premier 1.0: 22.3 (#182)

BenchmarkClaude 3.5 HaikuNova Premier 1.0
Kagi LLM Benchmark—44.8%
CritPt0%—
LiveBench Reasoning28.1%—
LMArena Hard Prompts1251—
DTBench56.7%—
LiveBench Data Analysis48.5%—
Epoch Capabilities Index127.15—
LiveBench43.5%—

Math Nova Premier 1.0 leads

Claude 3.5 Haiku: 13.7 (#294), Nova Premier 1.0: 31.5 (#194)

BenchmarkClaude 3.5 HaikuNova Premier 1.0
Omni-MATH22.4%35%
OTIS Mock AIME 2024-20254.3%—
LiveBench Math35.5%—
LMArena Math1244—
MATH Level 546.4%—
FrontierMath (Feb 2025 set)0.3%—

Knowledge Nova Premier 1.0 leads

Claude 3.5 Haiku: 18.7 (#276), Nova Premier 1.0: 35.4 (#176)

BenchmarkClaude 3.5 HaikuNova Premier 1.0
MMLU-Pro60.5%72.6%
GPQA (HELM)36.3%51.8%
GPQA Diamond38.1%—
Confabulations36.7%—
LMArena Expert1208—
MMLU74.3%—

Multimodal Not comparable

Claude 3.5 Haiku: 26.3 (#113), Nova Premier 1.0: —

BenchmarkClaude 3.5 HaikuNova Premier 1.0
LMArena Vision1092—
GeoBench34%—

Multilingual Not comparable

Claude 3.5 Haiku: 40.2 (#213), Nova Premier 1.0: —

BenchmarkClaude 3.5 HaikuNova Premier 1.0
LMArena Non-English1238—
LMArena Chinese1229—
LMArena French1262—
LMArena German1237—
LMArena Japanese1175—
LMArena Korean1172—
LMArena Russian1253—
LMArena Spanish1261—

Instruction Following Nova Premier 1.0 leads

Claude 3.5 Haiku: 63.1 (#229), Nova Premier 1.0: 66.9 (#201)

BenchmarkClaude 3.5 HaikuNova Premier 1.0
IFEval79.2%80.3%
LiveBench Instruction Following61.9%—
LMArena Instruction Following1241—

Long Context Not comparable

Claude 3.5 Haiku: 38.3 (#195), Nova Premier 1.0: —

BenchmarkClaude 3.5 HaikuNova Premier 1.0
LMArena Longer Query1261—

Writing & Preference Nova Premier 1.0 leads

Claude 3.5 Haiku: 42.9 (#228), Nova Premier 1.0: 51.0 (#174)

BenchmarkClaude 3.5 HaikuNova Premier 1.0
WildBench76%78.8%
LMArena Text1255—
LMArena Creative Writing1233—
Short-Story Creative Writing73.5%—
EQ-Bench Creative Writing1146—
LMArena Multi-Turn1265—
LiveBench Language35.4%—

Frequently asked questions

Is Claude 3.5 Haiku better than Nova Premier 1.0?

Nova Premier 1.0 is the stronger model overall, scoring 37.7 to 28.9 on the Noometry Index.

How many benchmarks do Claude 3.5 Haiku and Nova Premier 1.0 share?

5 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Nova Premier 1.0 has 6.

Related comparisons

Go deeper