Benchmark Almanac

QwenWebBench

Qwen 3.6 Max (Preview) 1,532 leads since Apr 2026 Fading

Models generate front-end code for web apps, games, SVG, and other categories in English and Chinese. Multimodal judgments produce Elo ratings.

In-house Qwen benchmark, and the tasks are not released.

Made by Qwen Released Apr 2026 Web and app front ends Tasks kept private Last in a launch post Apr 2026 , dropped before it saturated Last model added Apr 2026
Level
University Undergraduates and entry-level professionals
Scored
Graded by a model A language model scores each response, usually against a rubric.
Answers
Open-ended Free-form text, documents, designs or media judged as a whole.
4
Models scored in lab cards
4
Launch posts list it, from 1 lab

Qwen 3.6 Max (Preview) leads with 1,532 among models released by Apr 2026

Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.

The newest model with a score here came out in Apr 2026, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

Bars start at 1,350.

  1. 1,532 Qwen 3.6 Max (Preview)
  2. 1,502 Qwen 3.6 Plus
  3. 1,487 Qwen3.6 27B
  4. 1,397 Qwen 3.6 35B-A3B

Bars start at 1,350.

  1. 1 Qwen 3.6 Max (Preview) 1,532
  2. 2 Qwen 3.6 Plus 1,502
  3. 3 Qwen3.6 27B 1,487
  4. 4 Qwen 3.6 35B-A3B 1,397
#ModelScoreSettingDateSource
1 Qwen 3.6 Max (Preview) 1,532 Apr 2026 Model card
2 Qwen 3.6 Plus 1,502 Apr 2026 Model card
3 Qwen3.6 27B 1,487 Apr 2026 Model card
4 Qwen 3.6 35B-A3B 1,397 Apr 2026 Model card

2 models have held number one since its release in Apr 2026

Lab claims count from the day the card came out, independent runs from the model’s release.

Qwen
Lab claims Not tested since Apr 2026
Qwen 3.6 Max (Preview) 1,532

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Reported by the lab in its model card
1,350 1,400 1,450 1,500 1,550 2026 1,350 1,400 1,450 1,500 1,550 2026

Labs headline it less often now, last in Apr 2026

Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.

Qwen
DateLaunch postScoreAs the post writes it
22 Apr 2026 Qwen3.6 27B 1487 QwenWebBench
20 Apr 2026 Qwen 3.6 Max (Preview) 1532 QwenWebBench (Elo Rating) Artifacts
15 Apr 2026 Qwen 3.6 35B-A3B 1397 QwenWebBench
2 Apr 2026 Qwen 3.6 Plus 1501.7 QwenWebBench

More in Coding

All 243 in Coding
  • SWE-bench Verified In use 500 human-validated GitHub issues from 12 Python repos. Agent writes a patch that must pass hidden tests. Claude Opus 4.7 83.5%
  • SWE-bench Multilingual In use 300 GitHub-issue tasks across nine programming languages in SWE-bench format. Patch graded by repository tests. Claude Opus 5.5 93.9%
  • LiveCodeBench v6 In use Competitive programming problems collected after model cutoffs from LeetCode, AtCoder, Codeforces. Scored pass@1 on hidden tests. DeepSeek-V4-Pro 93.5%
  • DeepSWE In use 113 original long-horizon engineering tasks across 91 repos and five languages, written from scratch. Hand-written verifiers accept alternative solutions. GPT-6 Astra 74.1%
  • SciCode In use Scientist-curated research coding problems split into subproblems across natural sciences. Code checked against test cases. Seed2.1 Pro 59.8%
  • Codeforces rating In use Model solves recent Codeforces contest problems. An Elo-style rating is computed from simulated contest performance. DeepSeek V4.1 Flash 3,471