実際の利用状況に基づくコーディング向けの優れた AI モデルランキング

モデルランキングは に実際の利用データに基づいて更新されました。

この コーディング コレクションのモデルは、直近 7 日間に OpenRouter API を通じて処理されたプロンプトトークンと補完トークンの合計数で順位付けされています。 上位 10 個のモデルを表示しています。 ランキングは OpenRouter での使用状況を測定し、モデルの品質やベンチマーク性能ではなく、採用状況を反映しています。

以下では、コーディングに最適な AI モデルを、ベンチマークのスコアではなく、過去一週間に開発者が OpenRouter で実際に使用した量に基づいて順位付けしています。 現在のトップモデルは DeepSeek V4.1 Flash 1017、Hy4、DeepSeek V4.1 Flash です。 各掲載項目には、OpenRouter が情報を保有している場合、モデルのコンテキスト長と料金が表示されるため、選択前にコストと用途を比較できます。すべてのモデルを単一の OpenRouter APIキーで利用できるため、独自のコードベースでテストし、連携を書き直すことなく切り替えられます。

プログラミング モデルの LLM ランキング

1.
5.34T
24.8%
2.
1.69T
7.8%
3.
z-ai のファビコン
GLM 5.3 Flash
提供元: z-ai
1.51T
7.0%
4.
1.41T
6.6%
5.
1.01T
4.7%
6.
990B
4.6%
7.
openai のファビコン
GPT-6-Luna
提供元: openai
765B
3.6%
8.
tencent のファビコン
Hy4
提供元: tencent
721B
3.3%
9.
540B
2.5%
10.
7.56T
35.1%

OpenRouter の上位コーディングモデル

DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental V4 Flash Vision Exp.

It is suited for coding, terminal, and computer-use agents, along with long-horizon tasks that must run to completion across many steps and long-context analysis. Compressed KV caching cuts cache memory to roughly a quarter of the previous Flash generation, significantly reducing costs on agentic workloads. DeepSeek positions it as the cost-efficient tier of the V4.1 family and reports that it exceeds V4 Pro on performance, speed, and task completion time.

作成者: deepseek1.05M コンテキスト$0.02/M 入力 $0.108/M 出力
tencent のファビコン

Tencent: Hy4

18.2T トークン

The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity tasks. It also introduces visual understanding for the first time.

作成者: tencent1.05M コンテキスト$0.417/M 入力 $1.251/M 出力 50% off

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental V4 Flash Vision Exp.

It is suited for coding, terminal, and computer-use agents, along with long-horizon tasks that must run to completion across many steps and long-context analysis. Compressed KV caching cuts cache memory to roughly a quarter of the previous Flash generation, significantly reducing costs on agentic workloads. DeepSeek positions it as the cost-efficient tier of the V4.1 family and reports that it exceeds V4 Pro on performance, speed, and task completion time.

作成者: deepseek1.05M コンテキスト$0.051/M 入力 $0.567/M 出力
z-ai のファビコン

Z.ai: GLM 5.3 Flash

11.9T トークン

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 reducing compute overhead.

作成者: z-ai1.05M コンテキスト$0.0399/M 入力 $0.0784/M 出力
openai のファビコン

OpenAI: GPT-6 Luna

7.89T トークン

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 tasks, and at higher reasoning effort it can take on complex software engineering and computer-use tasks that previously called for a Sol-tier model. It shares the GPT-6 family's gains in factual reliability and its clearer, more concise communication style.

作成者: openai1.05M コンテキスト$0.10/M 入力 $0.50/M 出力
anthropic のファビコン

Anthropic: Claude Opus 5.5

7.02T トークン

Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code review and bug finding, financial and scientific analysis, and reading dense charts, diagrams, and screenshots, and it is more careful than its predecessor about only stating figures and citing sources it can back up.

The model completes comparable tasks in fewer steps and with fewer tokens than Opus 5, and reports on its work in plainer language, with clear updates on what it did, what it found, and what it needs from the user. Thinking is always adaptive, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings remain effective for latency-sensitive workloads.

作成者: anthropic1M コンテキスト$4/M 入力 $20/M 出力
stepfun のファビコン

StepFun: Step 5 Preview

6.41T トークン

Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional knowledge work, with particular strength in finance.

It is designed for extended tasks that span large codebases and documents, using tools and refining results over multiple steps.

作成者: stepfun1M コンテキスト$1/M 入力 $2.70/M 出力
xiaomi のファビコン

Xiaomi: MiMo-V2.6-Flash

4.25T トークン

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 greater computational efficiency. The model features a 1M-token context window and native multimodal capabilities. Optimized for agentic workflows, it delivers strong performance across coding, visual, general, and research scenarios, excelling at complex, long-horizon tasks with robust generalization across a diverse range of agent harnesses.

作成者: xiaomi1.05M コンテキスト$0.10/M 入力 $0.28/M 出力
z-ai のファビコン

Z.ai: GLM 5.3

3.78T トークン

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves on GLM-5.2 in coding and in the balance between performance and token efficiency.

Reasoning is always on and cannot be disabled. Reasoning efforts low, high, and max are supported; max is the default.

作成者: z-ai1.05M コンテキスト$0.0699/M 入力 $1.40/M 出力
openai のファビコン

OpenAI: GPT-6.1 Sol

3.72T トークン

GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional work, and multi-step business workflow automation, and approaches Astra-level results on these tasks at a much lower cost. Compared with GPT-6 Sol, it makes fewer factual errors and is more reliable at respecting explicit restrictions and user intent during agentic tasks.

作成者: openai1.05M コンテキスト$2/M 入力 $10/M 出力

その他のコレクションを見る