Compare · ModelsLive · 3 picked · head to head
Claude Mythos Preview vs GPT-5 Chat vs Gemini 3.1 Pro Preview
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Claude Mythos Preview wins on 4/5 benchmarks
Claude Mythos Preview wins 4 of 5 shared benchmarks. Leads in knowledge · coding.
Category leads
arena·Gemini 3.1 Pro Previewknowledge·Claude Mythos Previewcoding·Claude Mythos Preview
Hype vs Reality
Attention vs performance
Claude Mythos Preview
#4 by perf·#2 by attention
GPT-5 Chat
#3 by perf·#1 by attention
Gemini 3.1 Pro Preview
#74 by perf·no signal
Best value
GPT-5 Chat
1.8x better value than Gemini 3.1 Pro Preview
Claude Mythos Preview
—
no price
GPT-5 Chat
14.6 pts/$
$5.63/M
Gemini 3.1 Pro Preview
8.1 pts/$
$7.00/M
Vendor risk
Who is behind the model
Anthropic
$380.0B·Tier 1
OpenAI
$840.0B·Tier 1
Google DeepMind
$4.00T·Tier 1
Head to head
5 benchmarks · 3 models
Claude Mythos PreviewGPT-5 ChatGemini 3.1 Pro Preview
Chatbot Arena Elo · Overall
Gemini 3.1 Pro Preview leads by +59.8
GPT-5 Chat
1426.6
Gemini 3.1 Pro Preview
1486.4
GPQA diamond
Claude Mythos Preview leads by +2.4
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
Gemini 3.1 Pro Preview
92.1
HLE
Claude Mythos Preview leads by +13.1
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%.
Claude Mythos Preview
56.8
Gemini 3.1 Pro Preview
43.7
SWE-Bench verified
Claude Mythos Preview leads by +18.3
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
Gemini 3.1 Pro Preview
75.6
Terminal Bench
Claude Mythos Preview leads by +1.8
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
Gemini 3.1 Pro Preview
80.2
Full benchmark table
| Benchmark | Claude Mythos Preview | GPT-5 Chat | Gemini 3.1 Pro Preview |
|---|---|---|---|
Chatbot Arena Elo · Overall | — | 1426.6 | 1486.4 |
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 | — | 92.1 |
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%. | 56.8 | — | 43.7 |
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 | — | 75.6 |
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 | — | 80.2 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| — | — | 1.0M tokens (~500 books) | — | |
| $1.25 | $10.00 | 128K tokens (~64 books) | $34.38 | |
| $2.00 | $12.00 | 1.0M tokens (~524 books) | $45.00 |