ModelBench
Model catalog

Models

Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.

Compare Export CSV
4 models
arcee 8K+
Ranked by Design Arena: website
Moonshot AI: Kimi K3 T
Reasoning Tools JSON Open weights 1334.0

Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work

moonshotai/kimi-k3 2026-07-16 1.04858M context $3/M input $15/M output
82 providers
DeepSeek: DeepSeek V4.1 Flash 1017 T
Reasoning Tools Open weights 1307.0

October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding

deepseek/deepseek-v4.1-flash-1017 2026-10-17 1M context $0.15/M input $0.6/M output
33 providers
DeepSeek: DeepSeek V4 Pro T
Reasoning Tools JSON Open weights 1233.0

Open MoE flagship with million-token context for coding and long agent runs

deepseek/deepseek-v4-pro 2026-04-24 1M context $0.66/M input $1.98/M output
71 providers
Arcee Ai: Trinity Large Thinking T
Reasoning Tools Open weights 1137.0

Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use

arcee-ai/trinity-large-thinking 2026-04-01 524.288K context $0.25/M input $0.9/M output
5 providers