Compare · ModelsLive · 2 picked · head to head
Claude Mythos Preview vs Claude Sonnet 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 · agentic · coding.
Category leads
knowledge·Claude Mythos Previewagentic·Claude Mythos Previewcoding·Claude Mythos Preview
Hype vs Reality
Attention vs performance
Claude Mythos Preview
#5 by perf·no signal
Claude Sonnet 4.6
#149 by perf·#10 by attention
Best value
Claude Sonnet 4.6
Claude Mythos Preview
n/a
no price
Claude Sonnet 4.6
5.1 pts/$
$9.00/M
Vendor risk
Who is behind the model
Anthropic
$965.0B·Tier 1
Anthropic
$965.0B·Tier 1
Head to head
4 benchmarks · 2 models
Claude Mythos PreviewClaude Sonnet 4.6
GPQA diamond
Claude Mythos Preview leads by +11.3
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 Sonnet 4.6
83.2
OSWorld
Claude Mythos Preview leads by +7.5
OSWorld · tests AI agents on real-world computer tasks across operating systems, including web browsing, file management, and application use.
Claude Mythos Preview
79.6
Claude Sonnet 4.6
72.1
SWE-Bench verified
Claude Mythos Preview leads by +18.7
SWE-bench Verified · 500 human-validated tasks from 12 real Python repositories (Django, Flask, scikit-learn, sympy, and others). Each task requires the model to produce a git patch that resolves a real GitHub issue and passes the test suite. The verified subset eliminates ambiguous tasks from the original SWE-bench. Claude Mythos Preview leads at 93.9%, crossing 90% for the first time in 2026. Opus 4.6 scores 80.8%. The benchmark remains the most-cited evaluation for code-generation capability.
Claude Mythos Preview
93.9
Claude Sonnet 4.6
75.2
Terminal Bench
Claude Mythos Preview leads by +28.6
Terminal-Bench 2.0 · evaluates AI agents on real terminal-based coding tasks · writing scripts, debugging, running tests, and managing projects entirely through command-line interaction. Tests both code quality and terminal fluency. Claude Opus 4.7 scores 69.4%, demonstrating significant agentic terminal competence.
Claude Mythos Preview
82.0
Claude Sonnet 4.6
53.4
Full benchmark table
| Benchmark | Claude Mythos Preview | Claude Sonnet 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 | 83.2 |
OSWorld OSWorld · tests AI agents on real-world computer tasks across operating systems, including web browsing, file management, and application use. | 79.6 | 72.1 |
SWE-Bench verified SWE-bench Verified · 500 human-validated tasks from 12 real Python repositories (Django, Flask, scikit-learn, sympy, and others). Each task requires the model to produce a git patch that resolves a real GitHub issue and passes the test suite. The verified subset eliminates ambiguous tasks from the original SWE-bench. Claude Mythos Preview leads at 93.9%, crossing 90% for the first time in 2026. Opus 4.6 scores 80.8%. The benchmark remains the most-cited evaluation for code-generation capability. | 93.9 | 75.2 |
Terminal Bench Terminal-Bench 2.0 · evaluates AI agents on real terminal-based coding tasks · writing scripts, debugging, running tests, and managing projects entirely through command-line interaction. Tests both code quality and terminal fluency. Claude Opus 4.7 scores 69.4%, demonstrating significant agentic terminal competence. | 82.0 | 53.4 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| — | — | 1.0M tokens (~500 books) | — | |
| $3.00 | $15.00 | 1.0M tokens (~500 books) | $60.00 |
People also compared