Noometry

Model comparison

Claude Sonnet 5.5 vs Nova Premier 1.0

Claude Sonnet 5.5 is the stronger model overall, scoring 61.9 to 38.3 on the Noometry Index.

Last verified . 0 shared benchmarks.

Claude Sonnet 5.5 Anthropic

61.9

Rank #10 Confirmed

Nova Premier 1.0 Amazon

38.3

Rank #189 Confirmed

Summary

  • The widest gap is in math, where Claude Sonnet 5.5 leads 87.9 to 33.8.
  • Claude Sonnet 5.5 is cheaper at $2 / $10 per million input/output tokens, against $2.50 / $12.50 for Nova Premier 1.0.

Side by side

Claude Sonnet 5.5Nova Premier 1.0
ProviderAnthropicAmazon
Noometry Index61.938.3
Released2026-09-282025-04-30
WeightsProprietaryProprietary
Context window1M1M
Max output128K10K
Input $ / M tokens$2$2.50
Output $ / M tokens$10$12.50
Results tracked326

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

Category by category

Coding Not comparable

Claude Sonnet 5.5: 67.3 (#6), Nova Premier 1.0: —

BenchmarkClaude Sonnet 5.5Nova Premier 1.0
FrontierCode52.1%—
CursorBench55.5%—
LMArena WebDev1774—
FrontierSWE61.9%—
SciCode61%—
LMArena Coding1513—
ALE-Bench1,819—

Agentic & Tool Use Not comparable

Claude Sonnet 5.5: 45.0 (#16), Nova Premier 1.0: —

BenchmarkClaude Sonnet 5.5Nova Premier 1.0
APEX-Agents75.5%—

Reasoning Claude Sonnet 5.5 leads

Claude Sonnet 5.5: 54.0 (#28), Nova Premier 1.0: 23.0 (#185)

BenchmarkClaude Sonnet 5.5Nova Premier 1.0
Kagi LLM Benchmark—44.8%
NYT Connections (extended)80.5%—
CritPt31.4%—
LMArena Hard Prompts1495—
Mystery Game Puzzles65%—
Epoch Capabilities Index165.03—

Math Claude Sonnet 5.5 leads

Claude Sonnet 5.5: 87.9 (#6), Nova Premier 1.0: 33.8 (#199)

BenchmarkClaude Sonnet 5.5Nova Premier 1.0
FrontierMath (Tiers 1-3)88.8%—
FrontierMath Tier 480.5%—
OTIS Mock AIME 2024-2025100%—
ProofBench100%—
Omni-MATH—35%
LMArena Math1510—
FrontierMath Erdős2.9%—

Knowledge Claude Sonnet 5.5 leads

Claude Sonnet 5.5: 66.0 (#12), Nova Premier 1.0: 35.8 (#180)

BenchmarkClaude Sonnet 5.5Nova Premier 1.0
GPQA Diamond95.6%—
SimpleQA Verified46.5%—
MMLU-Pro—72.6%
GPQA (HELM)—51.8%
LMArena Expert1540—

Multimodal Not comparable

Claude Sonnet 5.5: 51.5 (#6), Nova Premier 1.0: —

BenchmarkClaude Sonnet 5.5Nova Premier 1.0
LMArena Vision1289—
Furniture Assembly75%—

Multilingual Not comparable

Claude Sonnet 5.5: 55.3 (#30), Nova Premier 1.0: —

BenchmarkClaude Sonnet 5.5Nova Premier 1.0
LMArena Non-English1452—
LMArena Chinese1522—
LMArena Russian1451—

Instruction Following Claude Sonnet 5.5 leads

Claude Sonnet 5.5: 78.3 (#11), Nova Premier 1.0: 66.8 (#204)

BenchmarkClaude Sonnet 5.5Nova Premier 1.0
IFEval—80.3%
LMArena Instruction Following1495—

Long Context Not comparable

Claude Sonnet 5.5: 45.9 (#28), Nova Premier 1.0: —

BenchmarkClaude Sonnet 5.5Nova Premier 1.0
LMArena Longer Query1498—

Writing & Preference Claude Sonnet 5.5 leads

Claude Sonnet 5.5: 66.0 (#40), Nova Premier 1.0: 51.0 (#178)

BenchmarkClaude Sonnet 5.5Nova Premier 1.0
LMArena Text1471—
LMArena Creative Writing1465—
WildBench—78.8%
LMArena Multi-Turn1474—

Frequently asked questions

Is Claude Sonnet 5.5 better than Nova Premier 1.0?

Claude Sonnet 5.5 is the stronger model overall, scoring 61.9 to 38.3 on the Noometry Index.

Which is cheaper, Claude Sonnet 5.5 or Nova Premier 1.0?

Claude Sonnet 5.5 is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; Nova Premier 1.0 lists at $2.50 and $12.50.

Which has the bigger context window?

Both accept 1M tokens.

How many benchmarks do Claude Sonnet 5.5 and Nova Premier 1.0 share?

0 benchmarks have published results for both models. Claude Sonnet 5.5 has 32 scored results on Noometry and Nova Premier 1.0 has 6.

Related comparisons

Go deeper