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
Structured output deepinfra
Ranked by Terminal-Bench 2.0
Alibaba Qwen: Qwen3.7 Max T
Reasoning Tools 69.7

Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks

alibaba/qwen3.7-max 2026-05-21 1M context $2.5/M input $7.5/M output
34 providers
DeepSeek: DeepSeek V4 Pro T
Reasoning Tools JSON Open weights 67.9

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
Xiaomi: MiMo-V2.5 T
Reasoning Tools Open weights 65.8

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 Flash T
Reasoning Tools JSON Open weights 56.9

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