Compare · ModelsLive · 2 picked · head to head
Claude 3.7 Sonnet 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 · agentic · coding.
Category leads
knowledge·Claude Mythos Previewagentic·Claude Mythos Previewcoding·Claude Mythos Preview
Hype vs Reality
Attention vs performance
Claude 3.7 Sonnet
#101 by perf·no signal
Claude Mythos Preview
#2 by perf·#2 by attention
Best value
Claude 3.7 Sonnet
Claude 3.7 Sonnet
5.3 pts/$
$9.00/M
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
4 benchmarks · 2 models
Claude 3.7 SonnetClaude Mythos Preview
GPQA diamond
Claude Mythos Preview leads by +21.5
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Claude 3.7 Sonnet
73.0
Claude Mythos Preview
94.5
HLE
Claude Mythos Preview leads by +53.4
HLE (Humanity's Last Exam) · crowdsourced expert-level questions designed to be among the hardest possible challenges for AI systems across all domains.
Claude 3.7 Sonnet
3.4
Claude Mythos Preview
56.8
OSWorld
Claude Mythos Preview leads by +43.8
OSWorld · tests AI agents on real-world computer tasks across operating systems, including web browsing, file management, and application use.
Claude 3.7 Sonnet
35.8
Claude Mythos Preview
79.6
SWE-Bench verified
Claude Mythos Preview leads by +33.0
Claude 3.7 Sonnet
61.0
Claude Mythos Preview
93.9
Full benchmark table
| Benchmark | Claude 3.7 Sonnet | 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. | 73.0 | 94.5 |
HLE HLE (Humanity's Last Exam) · crowdsourced expert-level questions designed to be among the hardest possible challenges for AI systems across all domains. | 3.4 | 56.8 |
OSWorld OSWorld · tests AI agents on real-world computer tasks across operating systems, including web browsing, file management, and application use. | 35.8 | 79.6 |
SWE-Bench verified | 61.0 | 93.9 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| Claude 3.7 Sonnet | $3.00 | $15.00 | 200K tokens (~100 books) | $60.00 |
| 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 3.7 Sonnet vs GPT-4oClaude Mythos Preview vs GPT-5 ChatClaude Mythos Preview vs Qwen3.5 397B A17BClaude Mythos Preview vs DeepSeek V3.2 Speciale