See key specs and per-benchmark scores for each model/mode. Scroll horizontally for all columns. 当前对比 2 个模型的评测数据与核心参数。
GPT-5.5
OpenAI
Best overall
Claude Mythos Preview · 81.40
Best single
Claude Mythos Preview · GPQA Diamond 94.60
Modality coverage
GPT-5.5 · 2 modalities
Head to head
3
Benchmarks
0
Wins
3
Losses
-8.27
Average diff
Compare benchmark results across thinking modes and tool usage.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
Complete scores for each model/mode across selected benchmarks.
3 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | GPT-5.5 | Claude Mythos Preview |
|---|---|---|
GPQA Diamond 综合评估 | 93.60Thinking Level · High | 94.60Extended Thinking |
HLE 综合评估 | 41.40Thinking Level · High | 64.70Extended Thinking ｜ Tools |
BrowseComp AI Agent - 信息收集 | 84.40Thinking Level · High ｜ Tools | 84.90Extended Thinking ｜ Tools |
Side-by-side input/output token pricing
Licensing, MoE architecture, and multi-modality support.
| Features & specs | GPT-5.5OpenAI | Claude Mythos PreviewAnthropic |
|---|---|---|
Core specsRelease | 2026-04-23 | 2026-04-07 |
Context length | 1000K | — |
Max output | 131072 | 8192 |
MoE | No | No |
LicenseCode Open Source | Not provided | Not provided |
Weights Open Source | Not provided | Not provided |
Commercial use | 不开源 | 不开源 |
Modality supportText Input/Output | / | / |
Image Input/Output | / | / |
ResourcesPaper / report | Introducing GPT‑5.5 | Introducing Claude Mythos Preview and Project Glasswing |
DataLearner blog | OpenAI 发布 GPT-5.5：代号 | Claude Mythos 是什么？Anthropic最强模型评测、安全能力与Project Glasswing详解 |
Claude Mythos Preview
Anthropic
