Noometry

Model comparison

Claude Sonnet 5.5 vs GPT-5-Codex

Claude Sonnet 5.5 is the stronger model overall, scoring 61.9 to 37.9 on the Noometry Index.

Last verified . 0 shared benchmarks.

Claude Sonnet 5.5 Anthropic

61.9

Rank #10 Confirmed

GPT-5-Codex OpenAI

37.9

Rank #192 Reported

Summary

  • The widest gap is in coding, where Claude Sonnet 5.5 leads 67.3 to 42.4.
  • GPT-5-Codex is cheaper at $1.25 / $10 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.5.
  • Claude Sonnet 5.5 accepts more context: 1M tokens versus 400K.

Side by side

Claude Sonnet 5.5GPT-5-Codex
ProviderAnthropicOpenAI
Noometry Index61.937.9
Released2026-09-282025-09-15
WeightsProprietaryProprietary
Context window1M400K
Max output128K128K
Input $ / M tokens$2$1.25
Output $ / M tokens$10$10
Results tracked323

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

Category by category

Coding Claude Sonnet 5.5 leads

Claude Sonnet 5.5: 67.3 (#6), GPT-5-Codex: 42.4 (#103)

BenchmarkClaude Sonnet 5.5GPT-5-Codex
FrontierCode52.1%—
CursorBench55.5%—
LMArena WebDev1774—
FrontierSWE61.9%—
SciCode61%—
WeirdML—54.5%
LMArena Coding1513—
ALE-Bench1,819—

Agentic & Tool Use Claude Sonnet 5.5 leads

Claude Sonnet 5.5: 45.0 (#16), GPT-5-Codex: 31.0 (#72)

BenchmarkClaude Sonnet 5.5GPT-5-Codex
Terminal-Bench—44.3%
APEX-Agents75.5%—

Reasoning Claude Sonnet 5.5 leads

Claude Sonnet 5.5: 54.0 (#28), GPT-5-Codex: 30.9 (#83)

BenchmarkClaude Sonnet 5.5GPT-5-Codex
Kagi LLM Benchmark—70.3%
NYT Connections (extended)80.5%—
CritPt31.4%—
LMArena Hard Prompts1495—
Mystery Game Puzzles65%—
Epoch Capabilities Index165.03—

Math Not comparable

Claude Sonnet 5.5: 87.9 (#6), GPT-5-Codex: —

BenchmarkClaude Sonnet 5.5GPT-5-Codex
FrontierMath (Tiers 1-3)88.8%—
FrontierMath Tier 480.5%—
OTIS Mock AIME 2024-2025100%—
ProofBench100%—
LMArena Math1510—
FrontierMath Erdős2.9%—

Knowledge Not comparable

Claude Sonnet 5.5: 66.0 (#12), GPT-5-Codex: —

BenchmarkClaude Sonnet 5.5GPT-5-Codex
GPQA Diamond95.6%—
SimpleQA Verified46.5%—
LMArena Expert1540—

Multimodal Not comparable

Claude Sonnet 5.5: 51.5 (#6), GPT-5-Codex: —

BenchmarkClaude Sonnet 5.5GPT-5-Codex
LMArena Vision1289—
Furniture Assembly75%—

Multilingual Not comparable

Claude Sonnet 5.5: 55.3 (#30), GPT-5-Codex: —

BenchmarkClaude Sonnet 5.5GPT-5-Codex
LMArena Non-English1452—
LMArena Chinese1522—
LMArena Russian1451—

Instruction Following Not comparable

Claude Sonnet 5.5: 78.3 (#11), GPT-5-Codex: —

BenchmarkClaude Sonnet 5.5GPT-5-Codex
LMArena Instruction Following1495—

Long Context Not comparable

Claude Sonnet 5.5: 45.9 (#28), GPT-5-Codex: —

BenchmarkClaude Sonnet 5.5GPT-5-Codex
LMArena Longer Query1498—

Writing & Preference Not comparable

Claude Sonnet 5.5: 66.0 (#40), GPT-5-Codex: —

BenchmarkClaude Sonnet 5.5GPT-5-Codex
LMArena Text1471—
LMArena Creative Writing1465—
LMArena Multi-Turn1474—

Frequently asked questions

Is Claude Sonnet 5.5 better than GPT-5-Codex?

Claude Sonnet 5.5 is the stronger model overall, scoring 61.9 to 37.9 on the Noometry Index.

Which is cheaper, Claude Sonnet 5.5 or GPT-5-Codex?

GPT-5-Codex is cheaper. It lists at $1.25 per million input tokens and $10 per million output tokens; Claude Sonnet 5.5 lists at $2 and $10.

Is Claude Sonnet 5.5 or GPT-5-Codex better for coding?

Claude Sonnet 5.5 scores higher on coding benchmarks: 67.3 versus 42.4 in the Noometry coding category.

Which has the bigger context window?

Claude Sonnet 5.5 does, with 1M tokens against 400K.

How many benchmarks do Claude Sonnet 5.5 and GPT-5-Codex share?

0 benchmarks have published results for both models. Claude Sonnet 5.5 has 32 scored results on Noometry and GPT-5-Codex has 3.

Related comparisons

Go deeper