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
merge-gateway Open weights
Ranked by Toolathlon-Verified
DeepSeek: DeepSeek V4 Pro 0813 T
Reasoning Tools JSON Open weights 74.1

DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes

deepseek/deepseek-v4-pro-0813 2026-08-13 1M context $0.132/M input $0.396/M output
42 providers
Zhipu AI: GLM-5.3 T
Reasoning Tools JSON Open weights 73.0

Flagship GLM model for long-horizon coding, agents, and complex project delivery

zhipuai/glm-5.3 2026-08-14 1M context $1.195/M input $4.183/M output
73 providers
Meta: Muse Spark Open T
Reasoning Tools Open weights 72.8

Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.

meta/muse-spark-open 2026-10-15 1.04858M context $1.25/M input $4.25/M output
14 providers
DeepSeek: DeepSeek V4 Flash 0731 T
Reasoning Tools JSON Open weights 70.3

Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding

deepseek/deepseek-v4-flash-0731 2026-07-31 1M context $0.035/M input $0.07/M output
54 providers