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
Reasoning empiriolabs
Ranked by SciCode
Sakana: Fugu Ultra T
Reasoning Tools JSON 58.7

Quality-first multi-agent model for hard research, analysis, and competitions

sakana/fugu-ultra 2026-06-15 1M context $5/M input $30/M output
11 providers
Alibaba Qwen: Qwen3.7 Max T
Reasoning Tools 53.5

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
31 providers
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
Alibaba Qwen: Qwen3 Max T
38.3

Flagship Qwen3 model for coding agents, complex reasoning, and tool use

alibaba/qwen3-max 2025-09-23 262.144K context $1.2/M input $6/M output
20 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