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
nano-gpt Open weights
Ranked by CharXiv Reasoning
Moonshot AI: Kimi K3 T
Reasoning Tools JSON Open weights 91.3

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
Alibaba Qwen: Qwen3.8 27B T
Reasoning Tools JSON Open weights 90.2

Dense 27B vision-language model for coding, agent tasks, and image and video understanding

alibaba/qwen3.8-27b 2026-08-14 262.144K context $0.04/M input $1.35/M output
44 providers
Xiaomi: MiMo-V2.5 T
Reasoning Tools JSON Open weights 81.0

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
Meta: Muse Glimmer 30B T
Reasoning Tools Open weights 78.8

Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.

meta/muse-glimmer-30b 2026-08-10 131.072K context $0.2/M input $0.8/M output
12 providers