Agents & Tool Calling
ZICQ LLM rankings update daily across intelligence, coding, price, and context for selection and comparison.
Last updated: 58 min ago (2026-11-20 00:59)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.
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
⚡ 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 |
-
#61
GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...
Tools Vision Docs Reasoning StructuredIntelligence 27.9Agentic 0.0Context 1.1M Output ≤ 128K$0.05/1M $0.25/1M out cache $0.01/1MSolid Tool Calling -
#62
GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...
Tools Vision Video Reasoning StructuredIntelligence 27.8Agentic 0.0Context 1.0M Output ≤ 943K$0.15/1M $0.50/1M out cache $0.03/1MSolid Tool Calling -
#63
GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...
Tools Vision Video Reasoning StructuredIntelligence 27.8Agentic 0.0Context 1.0M Output ≤ 943K$0.02/1M $0.07/1M out cache $0.01/1MSolid Tool Calling -
#64
MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...
Tools Vision Audio Video Reasoning StructuredIntelligence 26.7Agentic 0.0Context 1.1M Output ≤ 131K$0.14/1M $0.28/1M out cache $0.00/1MSolid Tool Calling -
#65
Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up...
Tools Vision Reasoning StructuredIntelligence 26.1Agentic 0.0Context 1.0M Output ≤ 262K$0.70/1M $2.10/1M out cache $0.07/1MSolid Tool Calling -
#66
Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers...
Tools Vision Audio Video Docs Reasoning StructuredIntelligence 24.9Agentic 0.0Context 1.0M Output ≤ 943K$1.25/1M $4.25/1M out cache $0.15/1MSolid Tool Calling -
#67
GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...
Tools Vision Docs Reasoning StructuredIntelligence 23.8Agentic 0.0Context 1.1M Output ≤ 128K$0.20/1M $1.20/1M out cache $0.02/1MSolid Tool Calling -
#68
GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...
Tools Vision Docs Reasoning StructuredIntelligence 23.8Agentic 0.0Context 1.1M Output ≤ 128K$0.10/1M $0.60/1M out cache $0.01/1MSolid Tool Calling -
#69
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
Tools Reasoning StructuredIntelligence 23.1Agentic 0.0Context 1.0M Output ≤ 943K$0.13/1M $5.50/1M out cache $0.11/1MSolid Tool Calling -
#70
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...
Tools Reasoning StructuredIntelligence 20.8Agentic 0.0Context 1.0M Output ≤ 393K$0.90/1M $1.50/1M out cache $0.25/1MSolid Tool Calling -
#71
Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...
Tools Vision Video Reasoning StructuredIntelligence 20.1Agentic 0.0Context 1.0M Output ≤ 235K$0.06/1M $2.20/1M out cache $0.06/1MSolid Tool Calling -
#72
Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...
Tools Vision Video Reasoning StructuredIntelligence 20.1Agentic 0.0Context 262K Output ≤ 235K$0.16/1M $2.00/1M out cache $0.04/1MSolid Tool Calling -
#73
MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...
Tools Vision Video Reasoning StructuredIntelligence 18.9Agentic 0.0Context 1.0M Output ≤ 512K$0.30/1M $1.20/1M out cache $0.06/1MSolid Tool Calling -
#74
MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...
Tools Vision Video Reasoning StructuredIntelligence 18.9Agentic 0.0Context 524K Output ≤ 512K$0.22/1M $0.88/1M out cache $0.04/1MSolid Tool Calling -
#75
Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...
Tools Reasoning StructuredIntelligence 17.7Agentic 0.0Context 1.0M Output ≤ 943K$0.30/1M $1.00/1M out cache $0.04/1MSolid Tool Calling -
#76
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...
Tools Vision Video Reasoning StructuredIntelligence 17.4Agentic 0.0Context 1.0M Output ≤ 943K$0.19/1M $16.00/1M out cache $0.18/1MSolid Tool Calling -
#77
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...
Tools Vision Video Reasoning StructuredIntelligence 17.4Agentic 0.0Context 1.0M Output ≤ 16K$2.28/1M $11.40/1M out cache $0.23/1MSolid Tool Calling -
#78
Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive...
Tools Reasoning StructuredIntelligence 14.2Agentic 0.0Context 524K Output ≤ 131K$0.15/1M $0.60/1M out cache $0.03/1MSolid Tool Calling -
#79
NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...
Tools Vision Video Reasoning StructuredIntelligence 13.6Agentic 0.0Context 1.0M Output ≤ 235K$0.15/1M $0.50/1M out cache $0.02/1MSolid Tool Calling -
#80
NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...
Tools Vision Video Reasoning StructuredIntelligence 13.6Agentic 0.0Context 1M Output ≤ 131KFreeFree & Tunable