Skip to main content
ZICQ

Reasoning Rankings

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

Last updated: 54 min ago (2026-11-21 05:34)
Clear
Sources and methodology

声明支持 reasoning 推理 effort 的模型,按 Intelligence 指数排序。

📊 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 476
Free & tunable 15
Vision 335
Tool calling 414
Reasoning 359
Max context SpaceXSI: Grok 4.20 Multi-Agent 2M tokens
Average known input price $1.57 / 1M USD / 1M tokens
Cheapest model inclusionAI: Ling 3.0 Tiny $0.015 / 1M
TOP by Intelligence Anthropic: Claude Fable 5.2 64.6
⚡ 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. #401
    Qwen: Qwen3 30B A3B Instruct 2507 Alibaba 通义 General LLM

    Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...

    Tools Structured
    Context 262K Output ≤ 235K
    $0.10/1M $0.30/1M out cache $0.10/1M
    Solid Reasoning
  2. #402
    Qwen: Qwen3 Coder 480B A35B Alibaba 通义 Coding & Programming

    Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...

    Tools Structured
    Context 262K Output ≤ 65K
    $0.30/1M $1.00/1M out cache $0.10/1M
    Solid Reasoning
  3. #403
    ByteDance: UI-TARS 7B Bytedance 视觉多模态

    UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...

    Vision Structured
    Context 128K Output ≤ 2K
    $0.10/1M $0.20/1M out cache $0.10/1M
    Solid Reasoning
  4. #404
    Qwen: Qwen3 235B A22B Instruct 2507 Alibaba 通义 General LLM

    Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...

    Tools Structured
    Context 262K Output ≤ 117K
    $0.14/1M $0.80/1M out cache $0.05/1M
    Solid Reasoning
  5. #405
    MoonshotAI: Kimi K2 0711 Moonshotai General LLM

    Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...

    Tools
    Context 131K Output ≤ 98K
    $0.57/1M $2.30/1M out
    Solid Reasoning
  6. #406
    Venice: Uncensored Cognitivecomputations General LLM

    Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...

    Structured
    Context 128K Output ≤ 8K
    $0.20/1M $0.90/1M out
    Solid Reasoning
  7. #407
    Morph: Morph V3 Large Morph General LLM

    Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code>...

    Structured
    Context 262K Output ≤ 131K
    $0.90/1M $1.90/1M out
    Solid Reasoning
  8. #408
    Morph: Morph V3 Large (batch) Morph General LLM

    Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code>...

    Structured
    Context 262K Output ≤ 131K
    $0.45/1M $0.95/1M out
    Solid Reasoning
  9. #409
    Morph: Morph V3 Fast Morph General LLM

    Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code> <update>{edit_snippet}</update>...

    Structured
    Context 262K Output ≤ 131K
    $0.80/1M $1.20/1M out
    Solid Reasoning
  10. #410
    Morph: Morph V3 Fast (batch) Morph General LLM

    Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code> <update>{edit_snippet}</update>...

    Context 81K Output ≤ 38K
    $0.40/1M $0.60/1M out
    Solid Reasoning
  11. #411
    Mistral: Mistral Small 3.2 24B Mistral AI 视觉多模态

    Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...

    Tools Vision Structured
    Context 256K Output ≤ 16K
    $0.07/1M $0.20/1M out
    Solid Reasoning
  12. #412
    Mistral: Mistral Medium 3 Mistral AI Doc & Vision

    Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...

    Tools Vision Docs Structured
    Context 131K Output ≤ 104K
    $0.44/1M $2.20/1M out cache $0.04/1M
    Solid Reasoning
  13. #413
    Meta: Llama Guard 4 12B Meta 视觉多模态

    Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...

    Vision
    Context 163K Output ≤ 16K
    $0.18/1M $0.18/1M out
    Solid Reasoning
  14. #414
    OpenAI: GPT-4.1 OpenAI Doc & Vision

    GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...

    Tools Vision Docs Structured
    Context 1.0M Output ≤ 32K
    $2.00/1M $8.00/1M out cache $0.50/1M
    Solid Reasoning
  15. #415
    OpenAI: GPT-4.1 (batch) OpenAI Doc & Vision

    GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...

    Tools Vision Docs Structured
    Context 1.0M Output ≤ 32K
    $1.00/1M $4.00/1M out cache $0.25/1M
    Solid Reasoning
  16. #416
    OpenAI: GPT-4.1 Mini OpenAI Doc & Vision

    GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...

    Tools Vision Docs Structured
    Context 1.0M Output ≤ 32K
    $0.40/1M $1.60/1M out cache $0.10/1M
    Solid Reasoning
  17. #417
    OpenAI: GPT-4.1 Mini (batch) OpenAI Doc & Vision

    GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...

    Tools Vision Docs Structured
    Context 1.0M Output ≤ 32K
    $0.20/1M $0.80/1M out cache $0.05/1M
    Solid Reasoning
  18. #418
    OpenAI: GPT-4.1 Nano OpenAI Doc & Vision

    For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...

    Tools Vision Docs Structured
    Context 1.0M Output ≤ 942K
    $0.10/1M $0.40/1M out cache $0.03/1M
    Solid Reasoning
  19. #419
    OpenAI: GPT-4.1 Nano (batch) OpenAI Doc & Vision

    For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...

    Tools Vision Docs Structured
    Context 1.0M Output ≤ 32K
    $0.05/1M $0.20/1M out cache $0.01/1M
    Solid Reasoning
  20. #420
    Meta: Llama 4 Maverick Meta 视觉多模态

    Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...

    Tools Vision Structured
    Context 524K Output ≤ 32K
    $0.35/1M $1.00/1M out cache $0.17/1M
    Solid Reasoning