Benchmark Almanac

SuperCLUE-OnDevice

Gemini 3.6 Flash 93.6 leads since July 2026
Not in model cards

Phone-based models respond to requests in Chinese.

SuperCLUE reports scores in a public workbook.

Made by
SuperCLUE
Kind
Overall chat quality
Level
Everyday
Scored
Graded by people
Answers
Open-ended
Measures
Capability
Language
Chinese
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
A host
Strongest model tested
Qwen 3.8 Max #30 on the capability index
Last model added
August 2026
Scores refreshed
November 20th, 2026
10
Entries on its own leaderboard, 9 models we track

Gemini 3.6 Flash leads with 93.6 among models released by August 2026 Gemini 3.6 Flash leads with 93.6 among models released by August 2026

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.

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

  1. 1 Gemini 3.6 Flash 云端 93.6
  2. 2 Doubao Seed 2.1 Pro 云端 93.0
  3. 3 Qwen 3.8 Max 云端 92.3
  4. 4 BlueLM-3.5-Nano-3B 端侧 89.9
  5. 5 Qwen3.5-9B 端侧 87.8
  6. 6 GLM-5V-Turbo 云端 87.8
  7. 7 Qwen3.5-4B 端侧 85.2
  8. 8 GLM-4.6V-Flash 端侧 81.4
  9. 9 Gemma 4 E4B 端侧 73.0
  10. 10 Gemma 4 E2B 端侧 66.5

Source: Official SuperCLUE-OnDevice leaderboard

#EntryScoreSettingDateSource
1 Gemini 3.6 Flash 93.6 云端 Jul 2026 Official leaderboard
2 Doubao Seed 2.1 Pro 93.0 云端 Jun 2026 Official leaderboard
3 Qwen 3.8 Max 92.3 云端 Aug 2026 Official leaderboard
4 BlueLM-3.5-Nano-3B 89.9 端侧 Official leaderboard
5 Qwen3.5-9B 87.8 端侧 Feb 2026 Official leaderboard
6 GLM-5V-Turbo 87.8 云端 Apr 2026 Official leaderboard
7 Qwen3.5-4B 85.2 端侧 Feb 2026 Official leaderboard
8 GLM-4.6V-Flash 81.4 端侧 Dec 2025 Official leaderboard
9 Gemma 4 E4B 73.0 端侧 Mar 2026 Official leaderboard
10 Gemma 4 E2B 66.5 端侧 Mar 2026 Official leaderboard
#ModelScoreSettingDateSource
1 Gemini 3.6 Flash 93.6 云端 Jul 2026 Official leaderboard
2 Doubao Seed 2.1 Pro 93.0 云端 Jun 2026 Official leaderboard
3 Qwen 3.8 Max 92.3 云端 Aug 2026 Official leaderboard
4 Qwen3.5-9B 87.8 端侧 Feb 2026 Official leaderboard
5 GLM-5V-Turbo 87.8 云端 Apr 2026 Official leaderboard
6 Qwen3.5-4B 85.2 端侧 Feb 2026 Official leaderboard
7 GLM-4.6V-Flash 81.4 端侧 Dec 2025 Official leaderboard
8 Gemma 4 E4B 73.0 端侧 Mar 2026 Official leaderboard
9 Gemma 4 E2B 66.5 端侧 Mar 2026 Official leaderboard

Rankings by part

We read 15 parts from the benchmark’s own leaderboard in 3 groups: 文本理解, 图像理解 and 视频理解. Each ranks models on one part of the test. Doubao Seed 2.1 Pro leads 6 of them, and 2 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

分数

9 models we track have a score here.

  1. 1 Gemini 3.6 Flash 95.2
  2. 2 Qwen 3.8 Max ↑1 94.6
  3. 3 GLM-5V-Turbo ↑2 93.0
  4. 4 Doubao Seed 2.1 Pro ↓2 93.0
  5. 5 Qwen3.5-9B ↓1 90.0
  6. 6 Gemma 4 E4B ↑2 88.7
  7. 7 GLM-4.6V-Flash 87.7
  8. 8 Qwen3.5-4B ↓2 87.0
  9. 9 Gemma 4 E2B 81.6

4 models have held number one on the official leaderboard since 2023

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

Z.ai Qwen ByteDance Seed Google DeepMind
Own leaderboard Not tested since Aug 2026

Source: Official SuperCLUE-OnDevice leaderboard

Scores over time

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

Plot with other benchmarks
On the benchmark’s own leaderboard
60.0 70.0 80.0 90.0 100.0 2026 60.0 70.0 80.0 90.0 100.0 2026

Source: Official SuperCLUE-OnDevice leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Instructions and chat

All 144 in Instructions and chat
  • IFEval In use Models answer about 500 prompts containing verifiable instructions such as word limits or required keywords. Code checks each instruction for strict and loose accuracy. Gemma 4 31B IT 98.9%
  • IFBench In use 58 new out-of-domain verifiable output constraints. Scored by programmatic constraint checks (strict or loose). Flint 89.2%
  • MultiChallenge In use Multi-turn conversations testing instruction retention, inference memory, versioned editing and self-coherence. Graded by LLM judge with rubrics. GPT-6.1 Sol 82%
  • Multi-IF In use Models follow verifiable instructions over three-turn conversations in eight languages, extending IFEval. Scored by instruction accuracy at each turn. LFM3-1.7B 89.1%
  • AdvancedIF In use Models respond to over 1,600 prompts with complex, multi-turn, and system-level instructions. A judge model checks each response against expert-written rubrics. MAI-Thinking-1 85%
  • MM-IFEval In use Multimodal models follow image-grounded instructions with exact output constraints. Checks mix rule-based verification and a judge model. GPT-4o 64.6%

Data audit

8 of 9 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark

Catalog record 1 warning 1 pass
  • Warning Task access We don’t know whether the tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (10 entries).
  • Pass Models scored 9 models we track, plus 1 other entry on its leaderboard.
  • Pass Newest score The newest is from August 2026, for Qwen 3.8 Max.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Qwen 3.8 Max (#30).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on superclueai.com: 9 rows for models we track and 1 other entry at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check