ZIQI-Eval
Models answer multiple-choice questions about music history, performance, and theory. A second test asks them to choose the continuation of a melody.
The authors report 16 models. MuTheoryEval separately scored 15 configurations on a fixed sample of 500 comprehension questions.
- Made by
- Jiajia Li and collaborators
- Released
- February 2024
- Kind
- Exam questions
- Level
- University
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Capability
- Subject
- Arts
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
-
Qwen-14B #214 on the capability index
- Last model added
- September 2023
- Scores refreshed
- November 20th, 2026
GPT4 (gpt-4) tops the leaderboard with 67.3% chatglm2-6b leads with 26.1% among models released by September 2023
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. Every run is in the next chart. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is chatglm2-6b, at 26.1%. This view shows only models we track, each at its best.
The newest model with a score here came out in September 2023, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 67.3 GPT4 (gpt-4)
- 45.6 ChatGPT (gpt-3.5-turbo)
- 26.1 chatglm2-6b
- 24.6 ChatMusician-Base
- 23.7 Ziya-LLaMA-13B-v1.1
- 20.4
Qwen-7B
- 19.7 XVERSE-13B
- 18.9
Qwen-14B
- 15.8 XVERSE-7B
- 11.8
Baichuan 2-7B
- 11.5
Baichuan 1-13B
- 8.22 internlm-7b
- 8.06 internlm-20b
- 8.01
Baichuan2-13B
- 6.90
Baichuan1-7B
- 4.16 ChatMusician
- 0.0 educhat-base-002-13B
- 1 GPT4 (gpt-4) Five-shot 67.3%
- 2 ChatGPT (gpt-3.5-turbo) Five-shot 45.6%
- 3 chatglm2-6b Five-shot 26.1%
- 4 ChatMusician-Base Zero-shot 24.6%
- 5 Ziya-LLaMA-13B-v1.1 Zero-shot 23.7%
- 6
Qwen-7B Zero-shot 20.4%
- 7 XVERSE-13B Five-shot 19.7%
- 8
Qwen-14B Zero-shot 18.9%
- 9 XVERSE-7B Zero-shot 15.8%
- 10
Baichuan 2-7B Zero-shot 11.8%
- 11
Baichuan 1-13B Zero-shot 11.5%
- 12 internlm-7b Zero-shot 8.22%
- 13 internlm-20b Five-shot 8.06%
- 14
Baichuan2-13B Five-shot 8.01%
- 15
Baichuan1-7B Zero-shot 6.90%
- 16 ChatMusician Five-shot 4.16%
- 17 educhat-base-002-13B Zero-shot 0%
Source: Official ZIQI-Eval leaderboard
- 1 chatglm2-6b Five-shot 26.1%
- 2
Qwen-7B Zero-shot 20.4%
- 3
Qwen-14B Zero-shot 18.9%
- 4
Baichuan 2-7B Zero-shot 11.8%
- 5
Baichuan 1-13B Zero-shot 11.5%
- 6 internlm-7b Zero-shot 8.22%
- 7 internlm-20b Five-shot 8.06%
- 8
Baichuan2-13B Five-shot 8.01%
- 9
Baichuan1-7B Zero-shot 6.90%
Source: Official ZIQI-Eval leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT4 (gpt-4) | 67.3% | Five-shot | Official leaderboard | |
| 2 | ChatGPT (gpt-3.5-turbo) | 45.6% | Five-shot | Official leaderboard | |
| 3 | chatglm2-6b | 26.1% | Five-shot | Jun 2023 | Official leaderboard |
| 4 | ChatMusician-Base | 24.6% | Zero-shot | Official leaderboard | |
| 5 | Ziya-LLaMA-13B-v1.1 | 23.7% | Zero-shot | Official leaderboard | |
| 6 | | 20.4% | Zero-shot | Sep 2023 | Official leaderboard |
| 7 | XVERSE-13B | 19.7% | Five-shot | Official leaderboard | |
| 8 | | 18.9% | Zero-shot | Sep 2023 | Official leaderboard |
| 9 | XVERSE-7B | 15.8% | Zero-shot | Official leaderboard | |
| 10 | | 11.8% | Zero-shot | Sep 2023 | Official leaderboard |
| 11 | | 11.5% | Zero-shot | Jul 2023 | Official leaderboard |
| 12 | internlm-7b | 8.22% | Zero-shot | Jul 2023 | Official leaderboard |
| 13 | internlm-20b | 8.06% | Five-shot | Sep 2023 | Official leaderboard |
| 14 | | 8.01% | Five-shot | Sep 2023 | Official leaderboard |
| 15 | | 6.90% | Zero-shot | Jun 2023 | Official leaderboard |
| 16 | ChatMusician | 4.16% | Five-shot | Official leaderboard | |
| 17 | educhat-base-002-13B | 0% | Zero-shot | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | chatglm2-6b | 26.1% | Five-shot | Jun 2023 | Official leaderboard |
| 2 | | 20.4% | Zero-shot | Sep 2023 | Official leaderboard |
| 3 | | 18.9% | Zero-shot | Sep 2023 | Official leaderboard |
| 4 | | 11.8% | Zero-shot | Sep 2023 | Official leaderboard |
| 5 | | 11.5% | Zero-shot | Jul 2023 | Official leaderboard |
| 6 | internlm-7b | 8.22% | Zero-shot | Jul 2023 | Official leaderboard |
| 7 | internlm-20b | 8.06% | Five-shot | Sep 2023 | Official leaderboard |
| 8 | | 8.01% | Five-shot | Sep 2023 | Official leaderboard |
| 9 | | 6.90% | Zero-shot | Jun 2023 | Official leaderboard |
Rankings by part
We read 10 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as 作曲理论, 世界民族音乐 and 流行音乐. chatglm2-6b leads 8 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.
作曲理论
9 models we track have a score here.
- 1
Qwen-7B ↑1 19%
- 2 chatglm2-6b ↓1 18.1%
- 3
Qwen-14B 15.3%
- 4
Baichuan 1-13B ↑1 9.70%
- 5
Baichuan 2-7B ↓1 9.36%
- 6 internlm-7b 8.67%
- 7
Baichuan1-7B ↑2 7.64%
- 8 internlm-20b ↓1 6.78%
- 9
Baichuan2-13B ↓1 6.44%
世界民族音乐
9 models we track have a score here.
- 1 chatglm2-6b 24.8%
- 2
Qwen-14B ↑1 24%
- 3
Qwen-7B ↓1 19.6%
- 4 internlm-20b ↑3 12.6%
- 5
Baichuan 2-7B ↓1 11.4%
- 6
Baichuan 1-13B ↓1 11.3%
- 7 internlm-7b ↓1 8.09%
- 8
Baichuan2-13B 6.87%
- 9
Baichuan1-7B 6.15%
流行音乐
9 models we track have a score here.
- 1 chatglm2-6b 32.4%
- 2
Qwen-14B ↑1 25.8%
- 3
Qwen-7B ↓1 24.7%
- 4
Baichuan 1-13B ↑1 15.7%
- 5
Baichuan 2-7B ↓1 13.6%
- 6 internlm-20b ↑1 12.9%
- 7
Baichuan2-13B ↑1 12.4%
- 8 internlm-7b ↓2 11.9%
- 9
Baichuan1-7B 10.5%
西方音乐史
9 models we track have a score here.
- 1 chatglm2-6b 30%
- 2
Qwen-7B 19.3%
- 3
Qwen-14B 17.8%
- 4
Baichuan 2-7B 12.8%
- 5 internlm-7b ↑1 10.3%
- 6
Baichuan 1-13B ↓1 10.3%
- 7 internlm-20b 9.19%
- 8
Baichuan2-13B 7.79%
- 9
Baichuan1-7B 7.02%
中国音乐史
9 models we track have a score here.
- 1
Qwen-14B ↑2 24.7%
- 2 chatglm2-6b ↓1 24.6%
- 3
Qwen-7B ↓1 19.8%
- 4
Baichuan 1-13B ↑1 12.4%
- 5
Baichuan 2-7B ↓1 11.6%
- 6
Baichuan2-13B ↑2 9.80%
- 7 internlm-7b ↓1 6.53%
- 8
Baichuan1-7B ↑1 6.31%
- 9 internlm-20b ↓2 5.47%
中国传统音乐
9 models we track have a score here.
- 1 chatglm2-6b 28.4%
- 2
Qwen-7B 19.5%
- 3
Qwen-14B 19.3%
- 4
Baichuan 2-7B 11.3%
- 5
Baichuan 1-13B 10.6%
- 6 internlm-20b ↑1 9.34%
- 7 internlm-7b ↓1 7.44%
- 8
Baichuan1-7B ↑1 6.86%
- 9
Baichuan2-13B ↓1 6.59%
音乐美学
9 models we track have a score here.
- 1 chatglm2-6b 36.4%
- 2
Qwen-14B ↑1 18.4%
- 3
Qwen-7B ↓1 17.8%
- 4
Baichuan 2-7B 11.7%
- 5
Baichuan 1-13B 9.27%
- 6 internlm-7b 9.12%
- 7 internlm-20b 7.45%
- 8
Baichuan2-13B 6.69%
- 9
Baichuan1-7B 6.23%
音乐教育
9 models we track have a score here.
- 1 chatglm2-6b 31.4%
- 2
Qwen-7B 21.7%
- 3
Qwen-14B 20.3%
- 4
Baichuan 1-13B ↑1 14.4%
- 5
Baichuan 2-7B ↓1 12.5%
- 6 internlm-7b 9.57%
- 7
Baichuan2-13B ↑1 7.87%
- 8
Baichuan1-7B ↑1 6.18%
- 9 internlm-20b ↓2 4.91%
音乐表演
9 models we track have a score here.
- 1 chatglm2-6b 28.1%
- 2
Qwen-7B 22.4%
- 3 internlm-20b ↑4 19.3%
- 4
Qwen-14B ↓1 18.3%
- 5
Baichuan 2-7B ↓1 13.4%
- 6 internlm-7b 9.20%
- 7
Baichuan 1-13B ↓2 8.84%
- 8
Baichuan2-13B 8.23%
- 9
Baichuan1-7B 7.02%
女性音乐
9 models we track have a score here.
- 1 chatglm2-6b 33.3%
- 2
Qwen-7B 24.5%
- 3
Qwen-14B 20.9%
- 4 internlm-20b ↑3 16.4%
- 5
Baichuan 1-13B 11.9%
- 6
Baichuan 2-7B ↓2 10.2%
- 7
Baichuan2-13B ↑1 8.96%
- 8 internlm-7b ↓2 8.06%
- 9
Baichuan1-7B 7.46%
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: Official ZIQI-Eval leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| chatglm2-6b | Five-shot | 26.1% | |||
| chatglm2-6b | Zero-shot | 24.1% | |||
| Zero-shot | 20.4% | ||||
| Zero-shot | 18.9% | ||||
| Five-shot | 17.7% | ||||
| Zero-shot | 11.8% | ||||
| Zero-shot | 11.5% | ||||
| Five-shot | 9.48% | ||||
| internlm-7b | Zero-shot | 8.22% | |||
| internlm-20b | Five-shot | 8.06% | |||
| Five-shot | 8.01% | ||||
| internlm-20b | Zero-shot | 7.43% | |||
| internlm-7b | Five-shot | 7.22% | |||
| Zero-shot | 6.90% | ||||
| Five-shot | 5.84% | ||||
| Five-shot | 5.60% | ||||
| Five-shot | 5.48% | ||||
| Zero-shot | 5.23% |
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: Official ZIQI-Eval leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| chatglm2-6b | Five-shot | 26.1% | |||
| chatglm2-6b | Zero-shot | 24.1% | |||
| Zero-shot | 20.4% | ||||
| Zero-shot | 18.9% | ||||
| Five-shot | 17.7% | ||||
| Zero-shot | 11.8% | ||||
| Zero-shot | 11.5% | ||||
| Five-shot | 9.48% | ||||
| internlm-7b | Zero-shot | 8.22% | |||
| internlm-20b | Five-shot | 8.06% | |||
| Five-shot | 8.01% | ||||
| internlm-20b | Zero-shot | 7.43% | |||
| internlm-7b | Five-shot | 7.22% | |||
| Zero-shot | 6.90% | ||||
| Five-shot | 5.84% | ||||
| Five-shot | 5.60% | ||||
| Five-shot | 5.48% | ||||
| Zero-shot | 5.23% |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official ZIQI-Eval leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official ZIQI-Eval 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 Knowledge
- MMLU-Pro In use Harder 10-option version of MMLU with reasoning-focused questions across 14 subjects.
Intern-S2-397B 89.8%
- MMLU In use 57-subject multiple-choice exam questions from elementary to professional level. Scored by accuracy.
Seed1.8 92.3%
- SuperGPQA In use 26,529 graduate-level multiple-choice questions across 285 disciplines. Accuracy.
Qwen 3.6 Max (Preview) 73.9%
- WideSearch In use 200 bilingual broad info-seeking tasks: agent collects many atomic facts into a table. Scored by success rate and row/item F1.
Tencent Hy4 preview 83.9%
- BBEH micro average In use Models solve harder replacements for each of the 23 BIG-Bench Hard tasks, 4,520 examples in total. The score is the share of all examples answered correctly.
Gemma 4 31B IT 74.4%
- HLE-Diamond In use Models answer 1,000 cleaned expert questions from Humanity's Last Exam, 500 on reasoning and 500 on knowledge, closed book. Graded on exact answers. Claude Fable 5.2 77.9%
Data audit
9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 3 years ago, in September 2023, for Qwen-7B. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
- Pass Independent runs Scores from the official leaderboard (17 entries).
- Pass Models scored 9 models we track, plus 8 other entries on its leaderboard.
- Warning Newest score The newest came 3 years ago, in September 2023, for Qwen-7B.
- Note Frontier models None of the top 10 has a score. The strongest tested is Qwen-14B (#214).
- Pass Headroom The best is 26.1%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on github.com: 18 rows for models we track and 8 other entries 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.