- 每月造訪次數
- 72.8K
- 上升10.5%較上月2026 年 9 月
- 公開營收
- 未公開
- 暫無公開營收證據
- 入門價
- 免費
- 沒有月付訂閱價
- 首次發布
- 4 個月前
- 2026-07-15 · 估算
訪問
行銷動作
發布、搜尋與內容、引薦、促銷- BenchmarkList now tracks AI rankings across 52 arenas refreshed daily. Anthropic wins Coding OpenAI wins Image, Research Kimi wins Design Alibaba wins Video Cartesia wins Audio Suno wins Music
@davidtsong · 2026-08-28 · 17 贊 · 0 轉發 · 1,011 瀏覽
- GPT-6 Astra turned Animator vs. Animation (original) into a playable game.
@davidtsong · 2026-09-07 · 17 贊 · 1 轉發 · 1,464 瀏覽
- GPT-6 Astra runs roughly head to head with Fable 5.1 - excited to see more 3rd party / independent benchmark runs on these models over the next week!
@davidtsong · 2026-09-04 · 22 贊 · 0 轉發 · 1,663 瀏覽
BenchmarkList launched on Show HN（2 分）發布
Benchmarklist: track AI benchmarks (2.4k+), models, and capabilities — We’re launching BenchmarkList: one place to track AI benchmarks, models, and capabilities. It’s surprisingly hard to get a complete pictur…
7 月 15 日 · 4 個月前原文證據
第三方評測與案例拆解
客戶來源管道拆解、工程師評測與開源檔案- 創作者原帖摘錄：
- We’re launching BenchmarkList: one place to track AI benchmarks, models, and capabilities. It’s surprisingly hard to get a complete picture of what AI can and can’t do. Most of the attention goes to a handful of benchmarks focused on coding, math, and reasoning abilities. Meanwhile, researchers, companies, and domain experts are building incredible benchmark
流量來源
訪問構成
管道
- 自然搜尋49%
- 直接訪問41%
- 外部引薦5%
- 其他4%
國家/地區
- 美國16%
- 巴西6%
- 英國5%
- 印度5%
- 泰國5%
搜尋
站點權重 —網域名稱註冊 2025-02-13
| 關鍵字 | 月搜尋量 |
|---|---|
| gamedevbench | 760 |
| mai code 1.1 flash benchmark | 600 |
| mai code 1.1 flash benchmarks | 320 |
| oai draco | 300 |
| nl4cop | 200 |
流量資料：Vaneform
定價
官網未公開方案價格。
試用：未提供 · 觀察於 2026-11-03 · 來源頁面
頁面與變化
關鍵頁面
每週快照- 首頁benchmarklist.com/
- 功能benchmarklist.com/benchmarks/ 快照 2026-11-03
官方部落格與更新日誌
近期官方文章與版本動態Skip to content Benchmark List Search BenchmarkList ctrl k → Use w/ agent → Benchmarks 2,641 → Providers 1,611 → Models 24,117 → Arenas 52 → Research 7 → Ask ON THIS PAGE 01 Overview 02 Stay current → Feedback Email updates BENCHMARKLIST NE
Cognition's coding benchmark series measuring whether agent output is mergeable. FrontierCode 2.0 has 132 private tasks written by open-source maintainers from the repositories they maintain, spanning more repositories and categories t
is the long-horizon rebuild of the LiveBench contamination-free benchmark, sponsored by Abacus.AI. Models are given real work (decks, research reports, bug fixes, apps that run for hours) and graded on what they hand back. It reports seven
Tests AI coding agents on 100 software engineering tasks written by experienced engineers from Toptal's network: multi-file bug fixes and behavior-contract changes in 87 real open-source repositories across 11 languages, written as und
變化
開始記錄以來，定價、方案與定位都沒有變化。
問題與證據
- BenchmarkList 的網站造訪次數是多少？
- Vaneform 估算 2026-09 網站造訪次數為 72.8K。造訪次數包含重複訪問，付費客戶數與收入需分別查看對應證據。來源
同分類研究對象
這些產品屬於同一目錄分類。選型時請進一步核對客戶任務、功能與部署要求。