ModelBench
Model catalog

Models

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

Compare Export CSV
8 models
200K+ Open weights
Ranked by SciCode
StepFun: Step 3.5 Flash T
Open weights 40.4

StepFun flash lane for quick multimodal reasoning and coding assistance

stepfun/step-3.5-flash 2026-01-29 256K context $0.1/M input $0.3/M output
14 providers
StepFun: Step 3.7 Flash T
Reasoning Tools JSON Open weights 40.0

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
StepFun: Step 3.5 Flash 2603 T
Reasoning Open weights 38.5

StepFun flash model for efficient multimodal reasoning, coding, and tool use

stepfun/step-3.5-flash-2603 2026-04-02 256K context $0.1/M input $0.3/M output
6 providers
Zhipu AI: GLM-4.6 T
Reasoning Tools Open weights 38.4

Late GLM-4 workhorse for coding agents, reasoning, and structured tasks

zhipuai/glm-4.6 2025-09-30 204.8K context $0.6/M input $2.2/M output
18 providers
Mistral AI: Mistral Small 4 T
Reasoning Tools Open weights 38.0

Fast Mistral production model for chat, extraction, and cost-sensitive agents

mistral/mistral-small-2603 2026-03-16 256K context $0.15/M input $0.6/M output
12 providers
Mistral AI: Mistral Large 3 T
Open weights 36.2

Mistral's largest general model for enterprise agents, coding, and multilingual reasoning

mistral/mistral-large-2512 2024-11-01 262.144K context $0.5/M input $1.5/M output
12 providers
Mistral AI: Devstral 2 T
Tools Open weights 33.1

Mistral's coding-agent model for repository work, terminal tasks, and software fixes

mistral/devstral-2512 2025-12-09 262.144K context $0.4/M input $2/M output
13 providers
Alibaba Qwen: Qwen3-Coder 30B-A3B Instruct T
Tools Open weights 27.8

Smaller Qwen coder for efficient local agents and repo-level fixes

alibaba/qwen3-coder-30b-a3b-instruct 2025-04 262.144K context $0.45/M input $2.25/M output
13 providers