Coding Rankings
ZICQ LLM rankings update daily across intelligence, coding, price, and context for selection and comparison.
Last updated: 19 min ago (2026-11-18 08:41)Sources and methodology
Ranked by OpenRouter benchmarks.coding_index (coding index) weighted with the overall Intelligence index. Ideal for code generation, refactoring, and code review.
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 5.1 Anthropic | Anthropic: Claude Fable 5.1 (batch) Anthropic | OpenAI: GPT-5.6 Sol OpenAI |
|---|---|---|---|
| Intelligence / Coding / Agentic | 50.0 / 80.7 / 57.2 | 50.0 / 80.7 / 57.2 | 0.0 / 78.3 / 47.4 |
| Context Window | 1M tokens | 1M tokens | 1.1M tokens |
| Input / Output Price (1M) | $10.00 / $50.00 | $5.00 / $25.00 | $4.00 / $20.00 |
| Est. Monthly Cost (30d) | Adjust inputs to calculate | Adjust inputs to calculate | Adjust inputs to calculate |
-
#101
Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...
Tools Reasoning StructuredIntelligence 0.0Coding 45.8Context 204K Output ≤ 131K$0.50/1M $2.00/1M out cache $0.10/1MStrong Coding -
#102
The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...
Tools Vision Video Reasoning StructuredIntelligence 0.0Coding 45.7Context 262K Output ≤ 65K$0.26/1M $2.08/1M outStrong Coding -
#103
LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic...
Tools ReasoningIntelligence 0.0Coding 45.3Context 1.0M Output ≤ 262K$0.30/1M $1.20/1M out cache $0.01/1MStrong Coding -
#104
GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...
Tools Reasoning StructuredIntelligence 0.0Coding 45.3Context 204K Output ≤ 131K$0.40/1M $1.75/1M out cache $0.08/1MStrong Coding -
#105
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 StructuredIntelligence 0.0Coding 44.2Context 163K Output ≤ 147K$0.26/1M $0.38/1M out cache $0.13/1MStrong Coding -
#106
Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...
Tools Vision Docs Reasoning StructuredIntelligence 7.4Coding 43.9Context 200K Output ≤ 64K$1.00/1M $5.00/1M out cache $0.10/1MStrong Coding -
#107
Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...
Tools Vision Docs Reasoning StructuredIntelligence 7.4Coding 43.9Context 200K Output ≤ 64K$0.50/1M $2.50/1M out cache $0.05/1MStrong Coding -
#108
DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...
Tools Reasoning StructuredIntelligence 0.0Coding 43.5Context 163K Output ≤ 147K$0.27/1M $1.00/1M outStrong Coding -
#109
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
Tools Vision Video Reasoning StructuredIntelligence 4.4Coding 43.4Context 262K Output ≤ 16K$0.20/1M $0.40/1M outStrong Coding -
#110
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
Tools Vision Video Reasoning StructuredIntelligence 4.4Coding 43.4Context 262K Output ≤ 32KFreeFree & Tunable -
#111
Grok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...
Tools Vision Docs Reasoning StructuredIntelligence 0.0Coding 42.2Context 1M Output ≤ 900K$1.25/1M $2.50/1M out cache $0.20/1MStrong Coding -
#112
Grok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...
Tools Vision Docs Reasoning StructuredIntelligence 0.0Coding 42.2Context 1M Output ≤ 900K$1.00/1M $2.00/1M out cache $0.16/1MStrong Coding -
#113
Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...
Tools Vision Video Reasoning StructuredIntelligence 0.0Coding 41.9Context 262K Output ≤ 235K$0.10/1M $0.90/1M out cache $0.02/1MStrong Coding -
#114
Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...
Tools Vision Video Reasoning StructuredIntelligence 0.0Coding 39.6Context 262K Output ≤ 230K$0.20/1M $1.15/1M out cache $0.04/1MStrong Coding -
#115
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
Tools Vision Video Reasoning StructuredIntelligence 0.0Coding 39.3Context 262K Output ≤ 235K$0.08/1M $0.26/1M out cache $0.04/1MStrong Coding -
#116
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
Tools Vision Video Reasoning StructuredIntelligence 0.0Coding 39.3Context 262K Output ≤ 32KFreeFree & Tunable -
#117
GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...
Tools Vision Docs Reasoning StructuredIntelligence 0.0Coding 37.8Context 400K Output ≤ 128K$1.25/1M $10.00/1M out cache $0.12/1MStrong Coding -
#118
GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...
Tools Vision Docs Reasoning StructuredIntelligence 0.0Coding 37.8Context 400K Output ≤ 128K$0.62/1M $5.00/1M out cache $0.06/1MStrong Coding -
#119
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...
Tools Reasoning StructuredIntelligence 0.0Coding 37.7Context 262K Output ≤ 16K$0.07/1M $0.40/1M outStrong Coding -
#120
The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...
Tools Vision Video Reasoning StructuredIntelligence 0.0Coding 37.0Context 262K Output ≤ 81K$0.14/1M $1.00/1M out cache $0.05/1MStrong Coding