Cursor CLIとGrok Build

Cursor CLIとGrok BuildをArtificial Analysis Coding Agent Indexのベンチマークスコア、コスト、実行時間、トークン使用量で比較します。

詳しい方法論は、方法論ページをご覧ください。

ほかの比較を見る
vs

ハイライト

Artificial Analysis Coding Agent Index v1.4 · Higher is better
Average agent wall time per task · Lower is better
Average API cost per task (USD) · Lower is better

比較

Cursor CLI と Grok Build の並列比較。

コーディングエージェント比較

指標
Cursor CLI
GPT-5.5 (medium)
Grok Build
Grok 4.5 (high)
分析
エージェントハーネス
Cursor CLI
Grok Build
代表モデル
GPT-5.5 (medium)
Grok 4.5 (high)
Coding Agent Index
47
64
Grok Build は Cursor CLI よりCoding Agent Indexが高いです
DeepSWE
37%
60%
Grok Build は Cursor CLI より DeepSWE のスコアが高いです
Terminal-Bench v2.1
76%
84%
Grok Build は Cursor CLI より Terminal-Bench v2.1 のスコアが高いです
SWE-Atlas-QnA
28%
48%
Grok Build は Cursor CLI より SWE-Atlas-QnA のスコアが高いです
タスクあたりのコスト
$2.00
$2.44
Cursor CLI は Grok Build よりタスクあたりのコストが低いです
タスクあたりの時間
6.4m
15.5m
Cursor CLI は Grok Build よりタスクあたりの時間が短いです
タスクあたりのターン数
77.8
60.7
Grok Build は Cursor CLI よりタスクあたりのターン数が少ないです
タスクあたりのトークン使用量
4M
3.6M
Grok Build は Cursor CLI よりタスクあたりのトークン使用量が少ないです
キャッシュヒット率
89%
92%
Grok Build は Cursor CLI よりキャッシュヒット率が高いです

モデルバリアント

Cursor CLI と Grok Build の評価済みモデルバリアント。

モデルバリアント

Cursor CLI
GPT-5.5 (medium)
47
37%
76%
28%
$2.00
6.4m
4M
Cursor CLI
Opus 4.7 (medium)
47
32%
75%
34%
$2.72
13.8m
5.7M
Cursor CLI
Composer 2.5
38
16%
68%
31%
$0.09
10.4m
3.7M
Cursor CLI
Composer 2.5 Fast
38
16%
68%
31%
$0.56
7.9m
4.3M
Grok Build
Grok 4.5 (high)
64
60%
84%
48%
$2.44
15.5m
3.6M

パフォーマンス

Artificial Analysis Coding Agent Indexにおけるパフォーマンス。

Artificial Analysis Coding Agent Index

Artificial Analysis Coding Agent Index v1.4 incorporates 3 benchmarks: DeepSWE, Terminal-Bench v2.1, and SWE-Atlas-QnA · Higher is better
Since benchmarking, we have observed a higher rate of content safety filtering on this endpoint.

The Artificial Analysis Coding Agent Index is a composite score built from DeepSWE, Terminal-Bench v2.1, and SWE-Atlas-QnA.

It is useful for quick comparison, but it should be read alongside the per-eval breakdowns. Two agents with similar index values can still have different strengths across repository tasks, terminal workflows, and rubric-based evaluations.

トークン使用量

Artificial Analysis Coding Agent Indexにおけるトークン消費量。

タスクあたりのトークン使用量

タスクあたりの入力・キャッシュ・出力トークンの平均
Prompt cache hit rates can vary significantly by provider routing, which can materially change effective cost.

Non-cached input tokens sent to the model, including prompts, instructions, tool context, and task context that were not served from prompt cache.

Artificial Analysis Coding Agent Index vs. 合計トークン

Artificial Analysis Coding Agent Index vs. タスクあたりの平均合計トークン
Most attractive quadrant

Each point represents a coding-agent variant. Farther left means lower average total token usage per task, while higher on the chart means higher benchmark performance. Agents toward the upper-left achieve stronger results with fewer tokens.

コスト

現在のトークン単位の価格に基づく、Artificial Analysis Coding Agent Indexのトークン従量課金APIコスト。

タスクあたりのコスト

Average pay-per-token API cost per task (USD) · Lower is better

This chart shows the average pay-per-token API cost per task across the Artificial Analysis Coding Agent Index, spanning DeepSWE, Terminal-Bench v2.1, and SWE-Atlas-QnA.

Where applicable, that cost model includes standard input pricing, discounted cached-input pricing, separate cache-write charges, and output pricing rather than treating all prompt tokens as if they were billed at the same uncached input rate.

It is intended to show pay-per-token API cost, not consumer plan pricing or the full operational cost of deploying the system in production. Infrastructure, engineering, and supervision costs are not the focus of this metric.

Artificial Analysis Coding Agent Index vs. タスクあたりのコスト

Artificial Analysis Coding Agent Index vs. タスクあたりの平均トークン従量課金APIコスト(USD)
Most attractive quadrant
Pareto line

Each point represents a coding-agent variant. Farther left means lower average cost per task, while higher on the chart means higher benchmark performance. The most efficient agents sit toward the upper-left: stronger results at lower cost.

実行時間

Artificial Analysis Coding Agent Indexにおけるエージェントの実稼働時間。

タスクあたりの時間

Average agent wall time per task · Lower is better

This chart uses agent wall time: how long the agent process was actively running on each task.

It does not include environment startup, verifier or judge time, or other harness overhead, so it is a cleaner comparison of how long the agent itself was working.

Artificial Analysis Coding Agent Index vs. 実行時間

Artificial Analysis Coding Agent Index vs. タスクあたりの平均エージェント稼働時間
Most attractive quadrant

Each point represents a coding-agent variant. Farther left means shorter average agent runtime per task, while higher on the chart means higher benchmark performance. Agents toward the upper-left deliver stronger results in less active agent time.