Claude Mythos Preview vs GPT-5.5
15 SHARED BENCHMARKSAcross 15 shared benchmarks, Claude Mythos Preview scores higher on 14 and GPT-5.5 on 1. The widest gap is GraphWalks BFS 1M subset, where Claude Mythos Preview scores 74.3 against 45.4.
ANTHROPICVSOPENAI15 SHARED14–1 HEAD-TO-HEADNEWEST SCORE ADDED
At a glance
MakerAnthropicOpenAI
Released—
Price per 1M tokens input / output—$5.00 / $30.00
Cost of 1M in + 1M out—$35.00
Head-to-head of 15 shared benchmarks14 wins1 wins
Scores tracked independently verified25 0 ◆185 29 ◆
GPT-5.5's release date per Artificial Analysis. Prices: Artificial Analysis for GPT-5.5. ◆ = independently verified score.
Where each leadsby capability area · benchmark wins
Biggest gaps
Claude Mythos Preview pulls furthest ahead on
- Humanity's Last Exam64.7 vs 45.8
- SWE-bench Pro77.8 vs 58.6
GPT-5.5 pulls furthest ahead on
No ratified-area lead of 3 points or more.
Every shared benchmark15 · grouped by area
Reasoning 2
Coding 1
Agentic 2
Other shared benchmarks 10
Each score is the one the model's own page shows — the most authoritative tracked result for that benchmark, on the benchmark's standard methodology (source-attributed). ↓ marks lower-is-better metrics; ◆ an independently verified score. Open either model for its full surface, provenance and pricing.