ModelBench
Model catalog

Models

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

Compare Export CSV
7 models
Image empiriolabs
Ranked by SWE-Bench Verified
Moonshot AI: Kimi K2.6 T
Reasoning Tools JSON Open weights 80.2

Multimodal Kimi workhorse for agent loops, coding tasks, and visual context

moonshotai/kimi-k2.6 2026-04-21 262.144K context $0.95/M input $4/M output
64 providers
Alibaba Qwen: Qwen3.6 27B T
Tools Open weights 77.2

Qwen vision-language model for visual reasoning, documents, and agent tasks

alibaba/qwen3.6-27b 2026-04-22 262.144K context $0.6/M input $3.6/M output
24 providers
StepFun: Step 3.7 Flash T
Reasoning Tools JSON Open weights 76.5

Newer StepFun flash model for faster agents, coding, and multimodal prompts

stepfun/step-3.7-flash 2026-05-29 256K context $0.185/M input $1.11/M output
17 providers
Alibaba Qwen: Qwen3.5 397B-A17B T
Reasoning Tools JSON Open weights 76.4

Large open Qwen multimodal MoE for visual agents and long technical tasks

alibaba/qwen3.5-397b-a17b 2026-02-15 262.144K context $0.6/M input $3.6/M output
18 providers
Meta: Muse Glimmer 30B T
Reasoning Tools JSON Open weights 76.0

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
9 providers
Alibaba Qwen: Qwen3.5 27B T
Tools Open weights 72.4

Qwen vision-language model for visual reasoning, documents, and agent tasks

alibaba/qwen3.5-27b 2026-02-23 262.144K context $0.3/M input $2.4/M output
14 providers
Alibaba Qwen: Qwen3.5 122B-A10B T
Reasoning Tools JSON Open weights 72.0

Qwen vision-language model for visual reasoning, documents, and agent tasks

alibaba/qwen3.5-122b-a10b 2026-02-23 262.144K context $0.4/M input $3.2/M output
16 providers