Compare · ModelsLive · 2 picked · head to head
Claude Mythos Preview vs Claude Opus 4.6
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Claude Mythos Preview wins on 4/4 benchmarks
Claude Mythos Preview wins 4 of 4 shared benchmarks. Leads in knowledge · coding.
Category leads
knowledge·Claude Mythos Previewcoding·Claude Mythos Preview
Hype vs Reality
Attention vs performance
Claude Mythos Preview
#2 by perf·#2 by attention
Claude Opus 4.6
#54 by perf·#4 by attention
Best value
Claude Opus 4.6
Claude Mythos Preview
—
no price
Claude Opus 4.6
3.8 pts/$
$15.00/M
Vendor risk
Who is behind the model
Anthropic
$380.0B·Tier 1
Anthropic
$380.0B·Tier 1
Head to head
4 benchmarks · 2 models
Claude Mythos PreviewClaude Opus 4.6
GPQA diamond
Claude Mythos Preview leads by +7.1
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Claude Mythos Preview
94.5
Claude Opus 4.6
87.4
HLE
Claude Mythos Preview leads by +25.7
HLE (Humanity's Last Exam) · crowdsourced expert-level questions designed to be among the hardest possible challenges for AI systems across all domains.
Claude Mythos Preview
56.8
Claude Opus 4.6
31.1
SWE-Bench verified
Claude Mythos Preview leads by +15.2
Claude Mythos Preview
93.9
Claude Opus 4.6
78.7
Terminal Bench
Claude Mythos Preview leads by +7.3
Terminal Bench · tests the ability to accomplish real-world tasks using terminal commands, evaluating shell scripting and CLI tool proficiency.
Claude Mythos Preview
82.0
Claude Opus 4.6
74.7
Full benchmark table
| Benchmark | Claude Mythos Preview | Claude Opus 4.6 |
|---|---|---|
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 94.5 | 87.4 |
HLE HLE (Humanity's Last Exam) · crowdsourced expert-level questions designed to be among the hardest possible challenges for AI systems across all domains. | 56.8 | 31.1 |
SWE-Bench verified | 93.9 | 78.7 |
Terminal Bench Terminal Bench · tests the ability to accomplish real-world tasks using terminal commands, evaluating shell scripting and CLI tool proficiency. | 82.0 | 74.7 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| Claude Mythos Preview | — | — | 1.0M tokens (~500 books) | — |
| Claude Opus 4.6 | $5.00 | $25.00 | 1.0M tokens (~500 books) | $100.00 |