Cookie-Bench: Continuous On-screen Key Interaction Evaluation for Web Generation (Cookie-Bench)
We show this table for reference; we do not rank on it.
A 1,000-query web development benchmark that judges generated front-end apps by deploying them and letting an evaluator agent use them, scoring functionality and aesthetics without reference implementations or test suites.
Benchmark score on Cookie-Bench — November 13, 2026
We compile the Cookie-Bench rows from provider self-reports. Claude Opus 5.5 leads the table at 91.5%, followed by GPT-6.1 Sol (89.7%) and Hy4 (88.8%). We do not use these results to rank models overall.
Claude Opus 5.5
Anthropic
Lab-reported, from another publisher’s documentGPT-6.1 Sol
OpenAI
Lab-reported, from another publisher’s documentHy4
Tencent
Lab-reported, from another publisher’s document7 modelsCodingCurrentDisplay onlyUpdated November 13, 2026
Benchmark score table (7 models)
None of the 7 results on this page has a documented run by the benchmark or an independent evaluator: 1 reported by the lab that built the model and 6 reported in another publisher’s document.
| Rank | Model / configuration | Score | Who ran it | Parameters (B) | Open / closed |
|---|---|---|---|---|---|
| 1 | Claude Opus 5.5AnthropicLab-reported, from another publisher’s document | 91.5% | Lab-reported, from another publisher’s document | Not reported | Closed |
| 2 | GPT-6.1 SolOpenAILab-reported, from another publisher’s document | 89.7% | Lab-reported, from another publisher’s document | Not reported | Closed |
| 3 | Hy4TencentLab-reported, from another publisher’s document | 88.8% | Lab-reported, from another publisher’s document | Not reported | Pending |
| 4 | ERNIE 5.5 Flash PreviewBaiduReported by Baidu | 88.2% | Reported by Baidu | Not reported | Pending |
| 5 | DeepSeek V4.1 Flash 1017DeepSeekLab-reported, from another publisher’s document | 87.9% | Lab-reported, from another publisher’s document | Not reported | Open |
| 6 | GLM-5.3Z.AILab-reported, from another publisher’s document | 80.4% | Lab-reported, from another publisher’s document | Not reported | Open |
| 7 | GLM-5.3-FlashZ.AILab-reported, from another publisher’s document | 76.9% | Lab-reported, from another publisher’s document | Not reported | Open |
- Lab-reported
- Benchmark-run
- Independent
How to read this leaderboard
Operator receipt: 7 sourced rows are currently displayable on this page; the leading published row is Claude Opus 5.5 at 91.5%.
Honest limit: Scores come from an LLM-driven evaluator and a chosen judge model, and every current row is a run by Baidu, which also built the benchmark.
Among the reported Cookie-Bench rows, Claude Opus 5.5 is first at 91.5%. The third row is 2.7 points behind. The broader top-10 range is 14.6 points, so the table still separates the published systems.
7 models have been evaluated on Cookie-Bench. The benchmark falls in the Coding category. We keep these results separate from the weighted global scoring system, so they remain source-specific evidence. Cookie-Bench is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About Cookie-Bench
Year
2026
Tasks
1,000 web development queries (React setting)
Format
Benchmark score (0-100)
Difficulty
Interactive web apps and static pages across three tiers
Baidu researchers released Cookie-Bench in May 2026 with Cookie, its evaluator: 1,000 queries across 11 domains and 54 leaf categories, covering static pages and interactive applications, balanced across three difficulty tiers and three target-language groups, with briefs rewritten to resist recall. Cookie forms a first impression from the rendered page, then drives the app with a computer-using agent while recording screenshots, screen video and audio, and only then scores functionality and aesthetics. Baidu reports ERNIE 5.5 Flash Preview at 88.2 on the React setting in its November 2026 launch, next to its own runs of Claude Opus 5.5 (91.5), GPT-6.1 Sol (89.7), Hy4 (88.8), DeepSeek V4.1 Flash 1017 (87.9), GLM-5.3 (80.4) and GLM-5.3-Flash (76.9), all judged by Qwen3.8-Max. BenchLM stores these Baidu-run rows as display-only.
Freshness and provenance
Version
Cookie-Bench 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does Cookie-Bench measure?
A 1,000-query web development benchmark that judges generated front-end apps by deploying them and letting an evaluator agent use them, scoring functionality and aesthetics without reference implementations or test suites.
Which model scores highest on Cookie-Bench?
Claude Opus 5.5 by Anthropic currently leads with a score of 91.5% on Cookie-Bench.
How many models are evaluated on Cookie-Bench?
7 AI models have published results on Cookie-Bench in the BenchLM catalog.
Compare top models on Cookie-Bench
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 7,000+ subscribers.
One email each week. Unsubscribe anytime.