ModelBench
Model catalog

Models

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

Compare Export CSV
14 models
Image Has benchmarks
Ranked by Terminal-Bench 4.0
Anthropic: Claude Sonnet 5.5 T
Reasoning Tools JSON 70.6

Fast Claude model for everyday coding, agents, and knowledge work

anthropic/claude-sonnet-5-5 2026-09-28 1M context $2/M input $10/M output
33 providers
Anthropic: Claude Opus 5.5 T
Reasoning Tools 66.4

Claude model for long-running agentic coding and knowledge work

anthropic/claude-opus-5-5 2026-09-22 1M context $4/M input $20/M output
35 providers
OpenAI: GPT-6 Astra T
Reasoning Tools JSON 57.9

GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.

openai/gpt-6-astra 2026-09-04 1.05M context $10/M input $50/M output
35 providers
Meta: Muse Wonder Full T
57.1

Muse Wonder Full is the most capable model in Meta's Muse Wonder series, built for long-running professional agents and ultra-long-horizon software engineering. It shares Muse Wonder's Active Memory and Active Focus capabilities and generally scores higher on Meta's agentic and coding evaluations.

meta/muse-wonder-full 2026-10-12 1.04858M context Input not listed Output not listed
Anthropic: Claude Fable 5.1 T
Reasoning Tools 55.8

Claude model for demanding reasoning and long-horizon agentic work

anthropic/claude-fable-5-1 2026-09-01 1M context $10/M input $50/M output
36 providers
Meta: Muse Wonder T
Reasoning Tools JSON 52.0

Muse Wonder is a frontier multimodal reasoning model from Meta for personal and professional agents, long-horizon coding, and computer use. It combines Active Memory, which carries relevant context across conversations, with Active Focus, which keeps it working through blockers toward a goal.

meta/muse-wonder-1.0 2026-10-12 1.04858M context $4/M input $20/M output
11 providers
DeepSeek: DeepSeek V4.1 Flash 1017 T
Reasoning Tools JSON Open weights 42.3

October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding

deepseek/deepseek-v4.1-flash-1017 2026-10-17 1M context $0.15/M input $0.6/M output
32 providers
Anthropic: Claude Haiku 5.5 T
Reasoning Tools JSON 39.2

Fast Claude model for responsive assistance, classification, and lightweight agents

anthropic/claude-haiku-5-5 2026-10-07 1M context $0.1/M input $0.5/M output
33 providers
xAI: Grok 4.7 T
Reasoning Tools JSON 37.6

xAI's frontier model for long-running agents, coding, knowledge work, and visual projects

xai/grok-4.7 2026-09-21 500K context $2/M input $6/M output
27 providers
Xiaomi: MiMo-V2.6-Pro T
Reasoning Tools Open weights 34.9

Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution

xiaomi/mimo-v2.6-pro 2026-09-22 1.04858M context $0.435/M input $0.87/M output
23 providers
DeepSeek: DeepSeek V4.1 Flash T
Reasoning Tools JSON Open weights 31.2

DeepSeek V4.1 Flash model for reasoning and agentic coding

deepseek/deepseek-v4.1-flash 2026-09-10 1M context $0.02/M input $1/M output
70 providers
Xiaomi: MiMo-V2.6-Flash T
Reasoning Tools Open weights 28.8

MiMo Flash model for multimodal coding agents and long-context automation

xiaomi/mimo-v2.6-flash 2026-09-22 1.04858M context $0.14/M input $0.28/M output
24 providers
xAI: Grok 4.6 T
Reasoning Tools JSON 20.3

xAI's frontier model for long-running agents, coding, knowledge work, and visual projects

xai/grok-4.6 2026-08-12 500K context $2/M input $6/M output
34 providers
Google: Gemini 3.8 Flash T
Reasoning Tools JSON 19.1

Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows

google/gemini-3.8-flash 2026-09-02 1.04858M context $0.75/M input $3.75/M output
32 providers