VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Refresh Models —Deals —Regulatory —Sources —

Claude Mythos 5.1 vs Claude Opus 5.5

13 SHARED BENCHMARKS

Across 13 shared benchmarks, Claude Mythos 5.1 scores higher on 0 and Claude Opus 5.5 on 13. The widest gap is OSWorld 2.0 (strict), where Claude Opus 5.5 scores 48.7 against 41.7. Claude Opus 5.5 is the cheaper of the two on tracked API pricing ($4.00 against $10.00 per million input tokens).

ANTHROPICVSANTHROPIC13 SHARED0–13 HEAD-TO-HEADNEWEST SCORE ADDED

At a glance

Claude Mythos 5.1Claude Opus 5.5
MakerAnthropicAnthropic
Released
Price per 1M tokens input / output$10.00 / $50.00$4.00 / $20.00
Cost of 1M in + 1M out$60.00$24.00 2.5× less
Head-to-head of 13 shared benchmarks0 wins13 wins
Scores tracked independently verified19 0 ◆37 1 ◆

Release dates per the vendor's own announcement. Prices: Anthropic's own price page for Claude Mythos 5.1; Artificial Analysis for Claude Opus 5.5. ◆ = independently verified score.

Where each leadsby capability area · benchmark wins

AreaClaude Mythos 5.1WINSClaude Opus 5.5
Reasoning01Claude Opus 5.5 leads 1 of 1 · widest: Humanity's Last Exam 60.9 vs 67.7
Coding02Claude Opus 5.5 leads 2 of 2 · widest: SWE-bench Pro 81.2 vs 89.9

Biggest gaps

Claude Mythos 5.1 pulls furthest ahead on

No ratified-area lead of 3 points or more.

Claude Opus 5.5 pulls furthest ahead on

  1. Humanity's Last Exam67.7 vs 60.9
  2. SWE-bench Pro89.9 vs 81.2
  3. SWE-bench Multilingual93.9 vs 89.1

Every shared benchmark13 · grouped by area

Other shared benchmarks 10

BenchmarkClaude Mythos 5.1MARGINClaude Opus 5.5
AECI168.1169.4
CoBench 2.153.455.8
DeepSWE 1.167.474.2
HealthBench Professional62.165.6
OSWorld 2.0 (partial)77.981.8
OSWorld 2.0 (strict)41.748.7
Program Bench87.691.2
SWE-bench Multimodal54.761.4
Terminal-Bench 4.060.966.4
Terminal-Bench-Science 0.152.658.7

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. Quoted rates are the price-setter row we currently track for each model — its direct or vendor-official listing where one exists (anthropic-official, direct), otherwise the lowest tracked offer.