GPT-5.5vsClaude Mythos Preview

Across 6 shared benchmarks, Claude Mythos Preview leads overall: GPT-5.5 wins 1, Claude Mythos Preview wins 5, with 0 ties and an average score difference of -5.57.

OpenAI
GPT-5.5

OpenAI · 2026-04-23 · Reasoning model

Anthropic
Claude Mythos Preview

Anthropic · 2026-04-07 · Chat model

GPT-5.51 win(17%)(83%)5 winsClaude Mythos Preview

Benchmark scores

Grouped by capability, sorted by largest gap within each. 6 shared benchmarks.

AI Agent - Tool Usage

Even 2/2
BenchmarkGPT-5.5Claude Mythos PreviewDiff
OSWorld-Verified78.704 / 18Thinking High (With Tools)79.603 / 18Extended (with tools)-0.90
Terminal Bench 2.082.701 / 46Thinking High (With Tools)822 / 46Extended (with tools)+0.70

General Knowledge

Claude Mythos Preview 2/2
BenchmarkGPT-5.5Claude Mythos PreviewDiff
HLE52.2013 / 157Thinking High (With Tools)64.701 / 157Extended (with tools)-12.50
GPQA Diamond93.606 / 178Thinking High (No Tools)94.601 / 178Extended (no tools)-1

AI Agent - Information Search

Claude Mythos Preview 1/1
BenchmarkGPT-5.5Claude Mythos PreviewDiff
BrowseComp84.405 / 45Thinking High (With Tools + Internet)84.904 / 45Extended (with tools)-0.50

Coding and Software Engineer

Claude Mythos Preview 1/1
BenchmarkGPT-5.5Claude Mythos PreviewDiff
SWE-Bench Pro - Public58.607 / 43Thinking High (With Tools)77.802 / 43Extended (with tools)-19.20

Specs

FieldGPT-5.5Claude Mythos Preview
PublisherOpenAIAnthropic
Release date2026-04-232026-04-07
Model typeReasoning modelChat model
ArchitectureDenseDense
ParametersNot availableNot available
Context length1000KNot available
Max output128K8K

API pricing

Prices use DataLearner records when available; missing fields are not inferred.

ItemGPT-5.5Claude Mythos Preview
Text input$0.5 / 1M tokens$25 / 1M tokens
Text output$30 / 1M tokens$125 / 1M tokens
Cache read$0.5 / 1M tokensNot public
Cache write$6.25 / 1M tokensNot public

Summary

  • Claude Mythos Previewleads in:General Knowledge (2/2), AI Agent - Information Search (1/1), Coding and Software Engineer (1/1)
  • Tied in:AI Agent - Tool Usage

On average across the 6 shared benchmarks, Claude Mythos Preview scores 5.57 higher.

Largest single-benchmark gap: SWE-Bench Pro - Public — GPT-5.5 58.60 vs Claude Mythos Preview 77.80 (-19.20).

Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.