Skip to main content
ZICQ

Agents & Tool Calling

ZICQ LLM rankings update daily across intelligence, coding, price, and context for selection and comparison.

Last updated: 19 min ago (2026-11-20 03:59)
Clear
Sources and methodology

Ranked by OpenRouter benchmarks.agentic_index (agent / tool-calling index) plus the supported_parameters.tools flag — a reference for agent framework builders.

📊 Evaluation Benchmarks & Methodology
1. Source:Model metadata and pricing are synced hourly from OpenRouter (openrouter.ai), covering commercial, open-weight, and preview/experimental versions.
2. Benchmarks:Intelligence, coding, and agentic indices are sourced directly from Artificial Analysis (artificialanalysis.ai) official benchmark indices.
3. Overall Score Weights:Overall Score = 60% × Intelligence Index + 25% × Coding Index + 15% × Agentic Index. Models without benchmark data are ranked at the end.
4. Referral links:"Try it" buttons marked "Referral" are referral links; ZICQ may earn a commission. Referral relationships never affect rankings or scores.
Statistics for this selection
Models tracked 479
Free & tunable 16
Vision 335
Tool calling 416
Reasoning 362
Max context xAI: Grok 4.20 Multi-Agent 2M tokens
Average known input price $1.56 / 1M USD / 1M tokens
Cheapest model inclusionAI: Ling 3.0 Tiny $0.015 / 1M
TOP by Agentic Anthropic: Claude Fable 5.2 0.0
⚡ Side-by-Side Model PK & Token Cost Calculator Click "+ Compare" on any model below to swap · Live monthly cost calculator · Shareable comparison URL
Metric Anthropic: Claude Fable 5.2 Anthropic Anthropic: Claude Fable 5.2 (batch) Anthropic OpenAI: GPT-6.2 Astra OpenAI
Intelligence / Coding / Agentic 64.6 / 0.0 / 0.0 64.6 / 0.0 / 0.0 62.1 / 0.0 / 0.0
Context Window 1M tokens 1M tokens 1.1M tokens
Input / Output Price (1M) $8.00 / $40.00 $4.00 / $20.00 $8.00 / $40.00
Est. Monthly Cost (30d) Adjust inputs to calculate Adjust inputs to calculate Adjust inputs to calculate
  1. #321
    OpenAI: GPT-5.2 (batch) OpenAI Doc & Vision

    GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...

    Tools Vision Docs Reasoning Structured
    Context 400K Output ≤ 128K
    $0.88/1M $7.00/1M out cache $0.09/1M
    Solid Tool Calling
  2. #322
    Mistral: Devstral 2 2512 Mistral AI General LLM

    Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...

    Tools Docs Structured
    Context 262K Output ≤ 209K
    $0.40/1M $2.00/1M out cache $0.04/1M
    Solid Tool Calling
  3. #323
    Relace: Relace Search Relace General LLM

    The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic...

    Tools Structured
    Context 256K Output ≤ 128K
    $1.00/1M $3.00/1M out
    Solid Tool Calling
  4. #324
    Z.ai: GLM 4.6V Zhipu 智谱 视觉多模态

    GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...

    Tools Vision Video Reasoning Structured
    Context 131K Output ≤ 32K
    $0.30/1M $0.90/1M out cache $0.05/1M
    Solid Tool Calling
  5. #325
    OpenAI: GPT-5.1-Codex-Max OpenAI 视觉多模态

    GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...

    Tools Vision Reasoning Structured
    Context 400K Output ≤ 128K
    $1.25/1M $10.00/1M out cache $0.12/1M
    Solid Tool Calling
  6. #326
    Amazon: Nova 2 Lite Amazon Doc & Vision

    Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing...

    Tools Vision Video Docs Reasoning
    Context 1M Output ≤ 65K
    $0.30/1M $2.50/1M out
    Solid Tool Calling
  7. #327
    Mistral: Ministral 3 14B 2512 Mistral AI 视觉多模态

    The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...

    Tools Vision Structured
    Context 262K Output ≤ 209K
    $0.20/1M $0.20/1M out cache $0.02/1M
    Solid Tool Calling
  8. #328
    Mistral: Ministral 3 8B 2512 Mistral AI 视觉多模态

    A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.

    Tools Vision Structured
    Context 262K Output ≤ 209K
    $0.15/1M $0.15/1M out cache $0.01/1M
    Solid Tool Calling
  9. #329
    Mistral: Ministral 3 3B 2512 Mistral AI 视觉多模态

    The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.

    Tools Vision Structured
    Context 131K Output ≤ 104K
    $0.10/1M $0.10/1M out cache $0.01/1M
    Solid Tool Calling
  10. #330
    Mistral: Mistral Large 3 2512 Mistral AI Doc & Vision

    Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.

    Tools Vision Docs Structured
    Context 262K Output ≤ 209K
    $0.50/1M $1.50/1M out cache $0.05/1M
    Solid Tool Calling
  11. #331
    DeepSeek: DeepSeek V3.2 DeepSeek General LLM

    DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

    Tools Reasoning Structured
    Context 163K Output ≤ 147K
    $0.26/1M $0.38/1M out cache $0.13/1M
    Solid Tool Calling
  12. #332
    Anthropic: Claude Opus 4.5 Anthropic Doc & Vision

    Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...

    Tools Vision Docs Reasoning Structured
    Context 200K Output ≤ 64K
    $5.00/1M $25.00/1M out cache $0.50/1M
    Solid Tool Calling
  13. #333
    Anthropic: Claude Opus 4.5 (batch) Anthropic Doc & Vision

    Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...

    Tools Vision Docs Reasoning Structured
    Context 200K Output ≤ 64K
    $2.50/1M $12.50/1M out cache $0.25/1M
    Solid Tool Calling
  14. #334
    Google: Nano Banana Pro (Gemini 3 Pro Image Preview) Google DeepMind Image Generation

    Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...

    Vision Reasoning Structured Image gen
    Context 65K Output ≤ 32K
    $2.00/1M $12.00/1M out cache $0.20/1M
    Solid Tool Calling
  15. #335
    OpenAI: GPT-5.1 OpenAI Doc & Vision

    GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...

    Tools Vision Docs Reasoning Structured
    Context 400K Output ≤ 128K
    $1.25/1M $10.00/1M out cache $0.12/1M
    Solid Tool Calling
  16. #336
    OpenAI: GPT-5.1 (batch) OpenAI Doc & Vision

    GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...

    Tools Vision Docs Reasoning Structured
    Context 400K Output ≤ 128K
    $0.62/1M $5.00/1M out cache $0.06/1M
    Solid Tool Calling
  17. #337
    OpenAI: GPT-5.1-Codex OpenAI 视觉多模态

    GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....

    Tools Vision Reasoning Structured
    Context 400K Output ≤ 128K
    $1.25/1M $10.00/1M out cache $0.13/1M
    Solid Tool Calling
  18. #338
    OpenAI: GPT-5.1-Codex-Mini OpenAI 视觉多模态

    GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex

    Tools Vision Reasoning Structured
    Context 400K Output ≤ 128K
    $0.25/1M $2.00/1M out cache $0.03/1M
    Solid Tool Calling
  19. #339
    MoonshotAI: Kimi K2 Thinking Moonshotai General LLM

    Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...

    Tools Reasoning Structured
    Context 262K Output ≤ 98K
    $0.60/1M $2.50/1M out cache $0.15/1M
    Solid Tool Calling
  20. #340
    Amazon: Nova Premier 1.0 Amazon 视觉多模态

    Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.

    Tools Vision
    Context 1M Output ≤ 32K
    $2.50/1M $12.50/1M out cache $0.62/1M
    Solid Tool Calling