最先端AIモデルの統合ディレクトリ。プロファイル、ベンチマーク、多面的な性能比較に加え、新たなトレンドのインサイトも掲載しています。
Muse Spark 1.3 (max) is amongst the leading models in intelligence and well priced when comparing to other models of similar price. The model supports text, image, and video input, outputs text, and has a 1M tokens conte…
Claude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback) is amongst the leading models in intelligence, but somewhat expensive when comparing to other models of similar price. It's also faster than average, how…
Claude Opus 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback) is amongst the leading models in intelligence, but somewhat expensive when comparing to other models of similar price. It's also faster than average, h…
Claude Sonnet 5.5 (Adaptive Reasoning, Max Effort, Default Fallback) is amongst the leading models in intelligence and reasonably priced when comparing to other models of similar price. It's also notably fast, however ve…
Claude Opus 5.5 (Adaptive Reasoning, High Effort, Default Fallback) is amongst the leading models in intelligence, but somewhat expensive when comparing to other models of similar price. It's also faster than average and…
Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) is amongst the leading models in intelligence, but particularly expensive when comparing to other models of similar price. It's also slower than average…
GPT-6 Astra (max) is amongst the leading models in intelligence, but particularly expensive when comparing to other models of similar price. It's also slower than average, however fairly concise.
Gemini 4 Argon (High) is amongst the leading models in intelligence and reasonably priced when comparing to other models of similar price. The model supports text and image input, outputs text, and has a 1M tokens contex…
Claude Sonnet 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback) is amongst the leading models in intelligence and reasonably priced when comparing to other models of similar price. It's also notably fast, however …
GPT-6.1 Sol (Max) is amongst the leading models in intelligence and reasonably priced when comparing to other models of similar price. It's also slower than average, however fairly concise.
Claude Opus 5.5 (Adaptive Reasoning, Medium Effort, Default Fallback) is amongst the leading models in intelligence, but somewhat expensive when comparing to other models of similar price. It's also faster than average a…
GPT-6.1 Sol (Xhigh) is amongst the leading models in intelligence and reasonably priced when comparing to other models of similar price. It's also slower than average, however highly concise.
Claude Opus 5 (Adaptive Reasoning, Max Effort) is amongst the leading models in intelligence, but particularly expensive when comparing to other models of similar price. It's also slower than average and somewhat verbose…
GPT-6.1 Sol (High) is amongst the leading models in intelligence and reasonably priced when comparing to other models of similar price. It's also slower than average, however highly concise.
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) is amongst the leading models in intelligence, but particularly expensive when comparing to other models of similar price. It's also slower than average …
GPT-6.1 Sol (Medium) is amongst the leading models in intelligence and reasonably priced when comparing to other models of similar price. It's also slower than average, however highly concise.
GPT-6 Sol (Max) is amongst the leading models in intelligence and reasonably priced when comparing to other models of similar price. It's also faster than average and fairly concise.
GPT-5.6 Sol (max) is amongst the leading models in intelligence, but particularly expensive when comparing to other models of similar price. It's also notably slow and somewhat verbose.
Claude Sonnet 5.5 (Adaptive Reasoning, High Effort, Default Fallback) is amongst the leading models in intelligence and reasonably priced when comparing to other models of similar price. It's also faster than average and…
Grok 4.7 (Xhigh) is amongst the leading models in intelligence and reasonably priced when comparing to other models of similar price. It's also faster than average, however very verbose.
Grok 4.7 (High) is amongst the leading models in intelligence and reasonably priced when comparing to other models of similar price. It's also faster than average, however very verbose.
MiMo-V2.6-Pro is amongst the leading models in intelligence and reasonably priced when comparing to other open weight models of similar size. It's also notably slow and somewhat verbose.
Qwen3.8 Max (0902) is amongst the leading models in intelligence and reasonably priced when comparing to other models of similar price. It's also notably slow and very verbose.
GLM-5.3 (max) is amongst the leading models in intelligence, but particularly expensive when comparing to other open weight models of similar size. It's also slower than average and very verbose.
Grok 4.6 (high) is amongst the leading models in intelligence and reasonably priced when comparing to other models of similar price. It's also slower than average and somewhat verbose.
GPT-6 Sol (Xhigh) is amongst the leading models in intelligence and reasonably priced when comparing to other models of similar price. It's also slower than average, however fairly concise.
GPT-5.6 Sol (xhigh) is amongst the leading models in intelligence, but particularly expensive when comparing to other models of similar price. It's also notably slow, however fairly concise.
Step 5 Preview is amongst the leading models in intelligence and well priced when comparing to other models of similar price. It's also faster than average, however very verbose.
Kimi K3 is amongst the leading models in intelligence, but somewhat expensive when comparing to other models of similar price. It's also slower than average and very verbose.
GPT-6 Sol (High) is amongst the leading models in intelligence and reasonably priced when comparing to other models of similar price. It's also slower than average, however highly concise.