ModelBench
Model catalog

Models

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

Compare Export CSV
6 models
cline-pass 1M+
Ranked by Design Arena: dataviz
Moonshot AI: Kimi K3 T
Reasoning Tools JSON Open weights 1352.0

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
Xiaomi: MiMo-V2.6-Pro T
Reasoning Tools Open weights 1337.0

Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution

xiaomi/mimo-v2.6-pro 2026-09-22 1.04858M context $0.435/M input $0.87/M output
23 providers
Xiaomi: MiMo-V2.5-Pro T
Reasoning Tools Open weights 1258.0

Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution

xiaomi/mimo-v2.5-pro 2026-04-22 1.04858M context $0.435/M input $0.87/M output
26 providers
Xiaomi: MiMo-V2.5 T
Reasoning Tools Open weights 1250.0

Open MiMo model for multimodal coding agents and long-context automation

xiaomi/mimo-v2.5 2026-04-22 1.04858M context $0.14/M input $0.28/M output
27 providers
DeepSeek: DeepSeek V4 Pro T
Reasoning Tools JSON Open weights 1203.0

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
DeepSeek: DeepSeek V4 Flash T
Reasoning Tools JSON Open weights 1127.0

Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work

deepseek/deepseek-v4-flash 2026-04-24 1M context $0.15/M input $0.6/M output
68 providers