Compare · ModelsLive · 2 picked · head to head
GPT-5.4 vs Claude Mythos Preview
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
GPT-5.4
#61 by perf·no signal
Claude Mythos Preview
#4 by perf·#2 by attention
Vendor risk
Who is behind the model
OpenAI
$840.0B·Tier 1
Anthropic
$380.0B·Tier 1
Head to head
4 benchmarks · 2 models
GPT-5.4Claude Mythos Preview
GPQA diamond
Claude Mythos Preview leads by +3.4
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
GPT-5.4
91.1
Claude Mythos Preview
94.5
HLE
Claude Mythos Preview leads by +23.8
HLE (Humanity's Last Exam) · a reasoning benchmark designed to be the hardest public evaluation of AI. Questions span mathematics, physics, philosophy, and logic · curated to be at or beyond the frontier of human expert capability. Tested with and without tool augmentation. Claude Opus 4.7 scores 46.9% without tools and 54.7% with tools · making it one of the few benchmarks where the top score is below 60%.
GPT-5.4
33.0
Claude Mythos Preview
56.8
SWE-Bench verified
Claude Mythos Preview leads by +17.0
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.
GPT-5.4
76.9
Claude Mythos Preview
93.9
Terminal Bench
Claude Mythos Preview leads by +0.2
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.
GPT-5.4
81.8
Claude Mythos Preview
82.0
Full benchmark table
| Benchmark | GPT-5.4 | Claude Mythos Preview |
|---|---|---|
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 91.1 | 94.5 |
HLE HLE (Humanity's Last Exam) · a reasoning benchmark designed to be the hardest public evaluation of AI. Questions span mathematics, physics, philosophy, and logic · curated to be at or beyond the frontier of human expert capability. Tested with and without tool augmentation. Claude Opus 4.7 scores 46.9% without tools and 54.7% with tools · making it one of the few benchmarks where the top score is below 60%. | 33.0 | 56.8 |
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. | 76.9 | 93.9 |
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. | 81.8 | 82.0 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $2.50 | $15.00 | 1.1M tokens (~525 books) | $56.25 | |
| — | — | 1.0M tokens (~500 books) | — |