Noometry

Model comparison

Claude 3 Opus vs GPT-5.3 Codex

GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 29.5 on the Noometry Index.

Last verified . 3 shared benchmarks.

Claude 3 Opus Anthropic

29.5

Rank #310 Confirmed

GPT-5.3 Codex OpenAI

45.8

Rank #69 Reported

Summary

  • They share 3 benchmarks with published results for both. Claude 3 Opus scores higher in 0 categories and GPT-5.3 Codex in 2 categories; 2 gaps are clear of the uncertainty.
  • The widest gap is in agentic & tool use, where GPT-5.3 Codex leads 48.0 to 24.6.
  • The biggest single-benchmark swing is WeirdML: 19.2% for Claude 3 Opus and 79.3% for GPT-5.3 Codex.

Side by side

Claude 3 OpusGPT-5.3 Codex
ProviderAnthropicOpenAI
Noometry Index29.545.8
Released2024-02-292026-02-05
WeightsProprietaryProprietary
Context window—400K
Max output—128K
Input $ / M tokens—$1.75
Output $ / M tokens—$14
Results tracked468

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

Category by category

Coding GPT-5.3 Codex leads

Claude 3 Opus: 32.9 (#267), GPT-5.3 Codex: 48.6 (#56)

BenchmarkClaude 3 OpusGPT-5.3 Codex
WeirdML19.2%79.3%
SWE-bench Verified—74.8%
LMArena WebDev—1409
BigCodeBench Instruct45.5%—
LiveBench Coding38.6%—
LMArena Coding1264—
BigCodeBench Complete57.4%—
ALE-Bench—1,655
HumanEval+77.4%—
MBPP+73.3%—

Agentic & Tool Use GPT-5.3 Codex leads

Claude 3 Opus: 24.6 (#116), GPT-5.3 Codex: 48.0 (#9)

BenchmarkClaude 3 OpusGPT-5.3 Codex
METR Time Horizons29.5%74.5%
Terminal-Bench—78.4%
Cybench10%—
Vending-Bench 2—5,940

Reasoning Not comparable

Claude 3 Opus: 14.6 (#324), GPT-5.3 Codex: —

BenchmarkClaude 3 OpusGPT-5.3 Codex
Epoch Capabilities Index126.91156.77
SimpleBench23.5%—
Chess Puzzles5%—
EnigmaEval0.8%—
LiveBench Reasoning40.6%—
LMArena Hard Prompts1245—
DTBench61.6%—
LiveBench Data Analysis57.9%—
LMCA17%—
ForecastBench58.4—
LiveBench49.2%—
WinoGrande88.5%—

Math Not comparable

Claude 3 Opus: 14.8 (#299), GPT-5.3 Codex: —

BenchmarkClaude 3 OpusGPT-5.3 Codex
OTIS Mock AIME 2024-20254.7%—
LiveBench Math43.6%—
LMArena Math1273—
MATH Level 537.5%—

Knowledge Not comparable

Claude 3 Opus: 24.5 (#267), GPT-5.3 Codex: —

BenchmarkClaude 3 OpusGPT-5.3 Codex
GPQA Diamond47.2%—
SimpleQA Verified12.6%—
Confabulations22.7%—
LMArena Expert1223—
MMLU84.6%—

Multimodal Not comparable

Claude 3 Opus: 27.1 (#116), GPT-5.3 Codex: —

BenchmarkClaude 3 OpusGPT-5.3 Codex
LMArena Vision1023—

Multilingual Not comparable

Claude 3 Opus: 41.4 (#207), GPT-5.3 Codex: —

BenchmarkClaude 3 OpusGPT-5.3 Codex
LMArena Non-English1258—
LMArena Chinese1248—
LMArena French1275—
LMArena German1258—
LMArena Japanese1204—
LMArena Korean1187—
LMArena Russian1280—
LMArena Spanish1246—

Instruction Following Not comparable

Claude 3 Opus: 64.1 (#228), GPT-5.3 Codex: —

BenchmarkClaude 3 OpusGPT-5.3 Codex
LiveBench Instruction Following63.9%—
LMArena Instruction Following1248—

Long Context Not comparable

Claude 3 Opus: 38.2 (#202), GPT-5.3 Codex: —

BenchmarkClaude 3 OpusGPT-5.3 Codex
LMArena Longer Query1259—

Writing & Preference Not comparable

Claude 3 Opus: 47.2 (#213), GPT-5.3 Codex: —

BenchmarkClaude 3 OpusGPT-5.3 Codex
LMArena Text1262—
LMArena Creative Writing1235—
LMArena Multi-Turn1275—
LiveBench Language50.4%—

Frequently asked questions

Is Claude 3 Opus better than GPT-5.3 Codex?

GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 29.5 on the Noometry Index.

Is Claude 3 Opus or GPT-5.3 Codex better for coding?

GPT-5.3 Codex scores higher on coding benchmarks: 48.6 versus 32.9 in the Noometry coding category.

How many benchmarks do Claude 3 Opus and GPT-5.3 Codex share?

3 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and GPT-5.3 Codex has 8.

Related comparisons

Go deeper