Compare · ModelsLive · 2 picked · head to head
Claude Mythos Preview vs Claude Mythos Preview
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Claude Mythos Preview wins on 14/14 benchmarks
Claude Mythos Preview wins 14 of 14 shared benchmarks. Leads in reasoning · knowledge · agentic.
Category leads
reasoning·Claude Mythos Previewknowledge·Claude Mythos Previewagentic·Claude Mythos Previewcoding·Claude Mythos Previewmath·Claude Mythos Preview
Hype vs Reality
Attention vs performance
Claude Mythos Preview
#2 by perf·#2 by attention
Claude Mythos Preview
#2 by perf·#2 by attention
Best value
Pricing unknown
Claude Mythos Preview
—
no price
Claude Mythos Preview
—
no price
Vendor risk
Who is behind the model
Anthropic
$380.0B·Tier 1
Anthropic
$380.0B·Tier 1
Head to head
14 benchmarks · 2 models
Claude Mythos PreviewClaude Mythos Preview
CharXiv Reasoning
Claude Mythos Preview
86.1
Claude Mythos Preview
86.1
CharXiv Reasoning (with tools)
Claude Mythos Preview
93.2
Claude Mythos Preview
93.2
GPQA diamond
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 Mythos Preview
94.5
GraphWalks BFS 256K-1M
Claude Mythos Preview
80.0
Claude Mythos Preview
80.0
HLE
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 Mythos Preview
56.8
HLE (with tools)
Claude Mythos Preview
64.7
Claude Mythos Preview
64.7
MMMLU
Claude Mythos Preview
92.7
Claude Mythos Preview
92.7
OSWorld
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 Mythos Preview
79.6
SWE-bench Multilingual
Claude Mythos Preview
87.3
Claude Mythos Preview
87.3
SWE-bench Multimodal
Claude Mythos Preview
59.0
Claude Mythos Preview
59.0
SWE-bench Pro
Claude Mythos Preview
77.8
Claude Mythos Preview
77.8
SWE-Bench verified
Claude Mythos Preview
93.9
Claude Mythos Preview
93.9
Terminal Bench
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 Mythos Preview
82.0
USAMO
Claude Mythos Preview
97.6
Claude Mythos Preview
97.6
Full benchmark table
| Benchmark | Claude Mythos Preview | Claude Mythos Preview |
|---|---|---|
CharXiv Reasoning | 86.1 | 86.1 |
CharXiv Reasoning (with tools) | 93.2 | 93.2 |
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 | 94.5 |
GraphWalks BFS 256K-1M | 80.0 | 80.0 |
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 | 56.8 |
HLE (with tools) | 64.7 | 64.7 |
MMMLU | 92.7 | 92.7 |
OSWorld OSWorld · tests AI agents on real-world computer tasks across operating systems, including web browsing, file management, and application use. | 79.6 | 79.6 |
SWE-bench Multilingual | 87.3 | 87.3 |
SWE-bench Multimodal | 59.0 | 59.0 |
SWE-bench Pro | 77.8 | 77.8 |
SWE-Bench verified | 93.9 | 93.9 |
Terminal Bench Terminal Bench · tests the ability to accomplish real-world tasks using terminal commands, evaluating shell scripting and CLI tool proficiency. | 82.0 | 82.0 |
USAMO | 97.6 | 97.6 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| Claude Mythos Preview | — | — | 1.0M tokens (~500 books) | — |
| Claude Mythos Preview | — | — | 1.0M tokens (~500 books) | — |
People also compared
Claude Mythos Preview vs Claude Opus 4.6Claude Mythos Preview vs GPT-5.4Claude Mythos Preview vs Gemini 3.1 Pro PreviewClaude Mythos Preview vs o3 ProClaude Mythos Preview vs GPT-5 ChatClaude Mythos Preview vs Qwen3.5 397B A17BClaude Mythos Preview vs DeepSeek V3.2 SpecialeClaude Instant vs Claude Mythos Preview