Noometry

Model comparison

Claude Opus 5.5 vs GPT-5.4

Claude Opus 5.5 is the stronger model overall, scoring 68.6 to 59.4 on the Noometry Index.

Last verified . 39 shared benchmarks.

Claude Opus 5.5 Anthropic

68.6

Rank #3 Confirmed

GPT-5.4 OpenAI

59.4

Rank #16 Confirmed

Summary

  • They share 39 benchmarks with published results for both. Claude Opus 5.5 scores higher in 8 categories and GPT-5.4 in 2 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Claude Opus 5.5 leads 71.9 to 52.6.
  • The biggest single-benchmark swing is MirrorCode: 77.4% for Claude Opus 5.5 and 15.6% for GPT-5.4.
  • GPT-5.4 is cheaper at $2.50 / $15 per million input/output tokens, against $4 / $20 for Claude Opus 5.5.
  • GPT-5.4 accepts more context: 1.05M tokens versus 1M.

Side by side

Claude Opus 5.5GPT-5.4
ProviderAnthropicOpenAI
Noometry Index68.659.4
Released2026-09-222026-03-05
WeightsProprietaryProprietary
Context window1M1.05M
Max output128K128K
Input $ / M tokens$4$2.50
Output $ / M tokens$20$15
Results tracked4468

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

Category by category

Coding Claude Opus 5.5 leads

Claude Opus 5.5: 71.9 (#3), GPT-5.4: 52.6 (#33)

BenchmarkClaude Opus 5.5GPT-5.4
LMArena WebDev18131465
SciCode66.9%56.6%
LMArena Coding15471497
MirrorCode77.4%15.6%
ALE-Bench2,1471,607
SWE-bench Verified—76.9%
DeepSWE—51.8%
FrontierCode54.6%—
CursorBench57.8%—
FrontierSWE62.3%—
GSO—31.4%
WeirdML—77.7%
AlgoTune—1.85

Agentic & Tool Use GPT-5.4 leads

Claude Opus 5.5: 45.3 (#15), GPT-5.4: 46.5 (#13)

BenchmarkClaude Opus 5.5GPT-5.4
APEX-Agents73.5%52.4%
Vending-Bench 29,2356,144
Terminal-Bench—81.8%
τ²-bench Banking—39.4%
DeepResearch Bench—35.1%
PostTrainBench—19%
GBAEval—45.1%
GDP.pdf30.6%—
LMArena Search—1197
METR Time Horizons—74.3%

Reasoning Claude Opus 5.5 leads

Claude Opus 5.5: 80.2 (#3), GPT-5.4: 61.8 (#19)

BenchmarkClaude Opus 5.5GPT-5.4
ARC-AGI-293.3%74%
NYT Connections (extended)88.5%91.3%
ARC-AGI-198.5%93.7%
CritPt31.7%23.4%
EBR-Bench71.4%25.4%
LMArena Hard Prompts15351485
Mystery Game Puzzles71%37%
DTBench98.9%94.4%
LMCA68.2%52%
Epoch Capabilities Index167.33156.81
Kagi LLM Benchmark—63.8%
Chess Puzzles—44%
EnigmaEval—16%
Thematic Generalization—80%
ForecastBench—59.5

Math Claude Opus 5.5 leads

Claude Opus 5.5: 91.8 (#3), GPT-5.4: 73.5 (#19)

BenchmarkClaude Opus 5.5GPT-5.4
FrontierMath (Tiers 1-3)91.2%78.6%
FrontierMath Tier 495%49%
OTIS Mock AIME 2024-2025100%97.8%
ProofBench100%56%
LMArena Math15061488
MathArena Final-Answer Competitions—83.1%
FrontierMath (Feb 2025 set)—47.6%
FrontierMath Erdős2.9%—
FrontierMath Tier 4 (v1)—27.1%

Knowledge Claude Opus 5.5 leads

Claude Opus 5.5: 66.4 (#10), GPT-5.4: 65.3 (#14)

BenchmarkClaude Opus 5.5GPT-5.4
GPQA Diamond90.6%93.3%
SimpleQA Verified72.2%45.1%
LMArena Expert15471507
Humanity's Last Exam—36.2%
Vectara Hallucination Rate—7%

Multimodal Claude Opus 5.5 leads

Claude Opus 5.5: 57.8 (#1), GPT-5.4: 43.7 (#20)

BenchmarkClaude Opus 5.5GPT-5.4
LMArena Vision13211303
Blueprint-Bench 251.2%27.1%
Furniture Assembly83.3%37.5%
LMArena Document—1471

Multilingual Claude Opus 5.5 leads

Claude Opus 5.5: 59.1 (#2), GPT-5.4: 56.2 (#23)

BenchmarkClaude Opus 5.5GPT-5.4
LMArena Non-English15071465
LMArena Chinese15881519
LMArena French15141493
LMArena Russian15201480
LMArena Spanish15071454
LMArena German—1472
LMArena Japanese—1485
LMArena Korean—1448

Instruction Following Claude Opus 5.5 leads

Claude Opus 5.5: 80.0 (#3), GPT-5.4: 77.1 (#27)

BenchmarkClaude Opus 5.5GPT-5.4
LMArena Instruction Following15371469

Long Context GPT-5.4 leads

Claude Opus 5.5: 47.1 (#19), GPT-5.4: 50.3 (#8)

BenchmarkClaude Opus 5.5GPT-5.4
LMArena Longer Query15321473
CL-bench—27.9%
CL-bench Life—21.7%

Writing & Preference Claude Opus 5.5 leads

Claude Opus 5.5: 78.2 (#3), GPT-5.4: 71.9 (#17)

BenchmarkClaude Opus 5.5GPT-5.4
LMArena Text15151469
LMArena Creative Writing15331439
EQ-Bench Creative Writing20501840
LMArena Multi-Turn14991482
EQ-Bench 4—1272

Frequently asked questions

Is Claude Opus 5.5 better than GPT-5.4?

Claude Opus 5.5 is the stronger model overall, scoring 68.6 to 59.4 on the Noometry Index.

Which is cheaper, Claude Opus 5.5 or GPT-5.4?

GPT-5.4 is cheaper. It lists at $2.50 per million input tokens and $15 per million output tokens; Claude Opus 5.5 lists at $4 and $20.

Is Claude Opus 5.5 or GPT-5.4 better for coding?

Claude Opus 5.5 scores higher on coding benchmarks: 71.9 versus 52.6 in the Noometry coding category.

Which has the bigger context window?

GPT-5.4 does, with 1.05M tokens against 1M.

How many benchmarks do Claude Opus 5.5 and GPT-5.4 share?

39 benchmarks have published results for both models. Claude Opus 5.5 has 44 scored results on Noometry and GPT-5.4 has 68.

Related comparisons

Go deeper