Claude Mythos 5 vs GPT-5.5
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
| Specification |
by Anthropic
|
by OpenAI
|
|---|---|---|
| Overview | ||
| Status | Current flagship | Current flagship |
| Released | Jun 9, 2026 | Nov 15, 2025 |
| Pricing per million tokens | ||
| Input | $10.00/Mtok | $5.00/Mtok |
| Output | $50.00/Mtok | $30.00/Mtok |
| Blended avg | $20.00/Mtok | $11.25/Mtok |
| Cached input | $1.00/Mtok | $0.500/Mtok |
| Specifications | ||
| Context window | 1M tokens | 1M tokens |
| Parameters | Proprietary | Proprietary |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
textimage
|
textimageaudio
|
| Benchmarks source: Vellum LLM Leaderboard | ||
| Avg benchmark score | 87.5 | 75 |
| Perf / dollar | 4.4 | 6.7 |
| GPQA Diamond | 94.1 | 93.6 |
| Terminal-Bench 2.1 | 88 | 82.7 |
| Humanity's Last Exam | 64.5 | 41.4 |
| HumanEval | 95.5 | 58.6 |
| SWE-Bench Verified | 95.5 | — |
| MCP Atlas | — | 75.3 |
| BrowseComp | — | 84.4 |
| OSWorld-Verified | — | 78.7 |
| ARC-AGI 2 | — | 85 |
| AutoBench | — | 12.9 |
| Independent composite scores each on its own scale — not part of the average above | ||
| AA Intelligence Index | — | 56.3 |
| AA Agentic Index | — | 47.4 |
| AA-Omniscience Index (−100–100) | — | 20.5 |
| GDPval-AA v2 | — | 1491.1 ELO |
| LMSYS Chatbot Arena | — | 1476.7 ELO |
| Providers | ||
| Available from |
Anthropic — $10.00/$50.00/Mtok
|
OpenAI — $5.00/$30.00/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | Claude Mythos 5 | GPT-5.5 | Savings |
|---|---|---|---|
| 1M tokens | $20 | $11.25 | $8.75 (43.8%) |
| 10M tokens | $200 | $112.5 | $87.5 (43.8%) |
| 100M tokens | $2000 | $1125 | $875 (43.8%) |
| 1000M tokens | $20000 | $11250 | $8750 (43.8%) |
When to pick which
distilled from the pricing and spec data above- raw capability matters more than price: 87.5 vs 75 average benchmark score
- cost dominates: $11.25/Mtok blended vs $20.00 — 43.8% less on the same 50/50 token mix
The cheaper option here — GPT-5.5 costs $11.25/Mtok blended on OpenAI.
Summary
Claude Mythos 5 by Anthropic costs $10.00/Mtok input and $50.00/Mtok output, with a 1M-token context window. It supports text, image input.
GPT-5.5 by OpenAI costs $5.00/Mtok input and $30.00/Mtok output, with a 1M-token context window. It supports text, image, audio input.
On a blended cost basis, GPT-5.5 is 43.8% cheaper than Claude Mythos 5.It also has a larger context window.
On benchmarks, Claude Mythos 5 scores higher (87.5 vs 75) on average. In terms of value, GPT-5.5 has better performance per dollar (6.7 vs 4.4).
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.