ASAG2024
Models grade short answers from seven English datasets on a common zero to one scale. The authors weight errors to account for rare grades.
The authors evaluated GPT-4o, GPT-3.5 Turbo, and Llama 3. An independent study fitted its scoring method on the training split and evaluated the test split.
- Released
- June 2024
- Kind
- Other professions
- Level
- University
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- All public
- Measures
- Capability
- Subject
- Education
- Language
- English
- Interaction
- Single turn
- Items from
- Another benchmark
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
- GPT-4o May 2024 #162 on the capability index
- Last model added
- May 2024
- Scores refreshed
- November 20th, 2026
GPT-4o leads with 0.27 among models released by May 2024 GPT-4o leads with 0.27 among models released by May 2024
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. 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 May 2024, 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
- 1 GPT-4o May 2024 0.27
- 2 GPT-3.5 Turbo Jan 2024 0.30
- 3 Nomic-embed-text 0.34
- 4
Llama 3-8B 0.39
- 5 PrometheusII-7B 0.43
- 6 BART-SAF 0.48
Source: The ASAG2024 paper
- 1 GPT-4o May 2024 0.27
- 2 GPT-3.5 Turbo Jan 2024 0.30
- 3
Llama 3-8B 0.39
Source: The ASAG2024 paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4o May 2024 | 0.27 | May 2024 | Official leaderboard | |
| 2 | GPT-3.5 Turbo Jan 2024 | 0.30 | Jan 2024 | Official leaderboard | |
| 3 | Nomic-embed-text | 0.34 | Official leaderboard | ||
| 4 | | 0.39 | Apr 2024 | Official leaderboard | |
| 5 | PrometheusII-7B | 0.43 | Official leaderboard | ||
| 6 | BART-SAF | 0.48 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4o May 2024 | 0.27 | May 2024 | Official leaderboard | |
| 2 | GPT-3.5 Turbo Jan 2024 | 0.30 | Jan 2024 | Official leaderboard | |
| 3 | | 0.39 | Apr 2024 | Official leaderboard |
Rankings by part
We read 7 parts from the benchmark’s paper, each ranking models on one part of the test, such as Beetle, CU-NLP and DigiKlausur. GPT-4o leads 6 of them, and GPT-3.5 Turbo leads the other one. Arrows show how far a model moved from its overall rank among the models we track.
Beetle
3 models we track have a score here.
- 1 GPT-4o May 2024 0.32
- 2 GPT-3.5 Turbo Jan 2024 0.33
- 3
Llama 3-8B 0.37
CU-NLP
3 models we track have a score here.
- 1 GPT-3.5 Turbo Jan 2024 ↑1 0.31
- 2 GPT-4o May 2024 ↓1 0.34
- 3
Llama 3-8B 0.43
DigiKlausur
3 models we track have a score here.
- 1 GPT-4o May 2024 0.27
- 2 GPT-3.5 Turbo Jan 2024 0.33
- 3
Llama 3-8B 0.42
Mohler
3 models we track have a score here.
- 1 GPT-4o May 2024 0.22
- 2 GPT-3.5 Turbo Jan 2024 0.25
- 3
Llama 3-8B 0.27
SAF
3 models we track have a score here.
- 1 GPT-4o May 2024 0.24
- 2 GPT-3.5 Turbo Jan 2024 0.28
- 3
Llama 3-8B 0.46
SciEntsBank
3 models we track have a score here.
- 1 GPT-4o May 2024 0.31
- 2 GPT-3.5 Turbo Jan 2024 0.33
- 3
Llama 3-8B 0.38
Stita
3 models we track have a score here.
- 1 GPT-4o May 2024 0.22
- 2 GPT-3.5 Turbo Jan 2024 0.28
- 3
Llama 3-8B 0.38
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The ASAG2024 paper
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official ASAG2024 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 Law, finance and medicine
- MedXpertQA-MM In use Models answer expert-level medical exam questions that combine images with clinical records and test results. Scoring is accuracy.
Qwen 3.8 Max 80.4%
- HealthBench Professional In use 525 physician-authored tasks from real clinician chats (care consult, documentation, research) with physician-adjudicated rubrics. Claude Sonnet 5.5 69.2%
- HealthBench In use 5,000 realistic health conversations graded against physician-written rubrics. A length-adjusted variant penalizes verbosity. GPT-5 67.2%
- FinSearchComp In use Agents search the web to fetch live financial data, look up history, and run multi-step investigations, across 635 expert-written questions. Scored by answer accuracy.
Ling-3.1-flash 81.7%
- KorMedMCQA In use Models answer 7,469 multiple-choice questions from Korean licensing exams for doctors, nurses, pharmacists and dentists, held from 2012 to 2024. o1-preview 92.7%
- Harvey LAB-AA v1.1 In use Artificial Analysis's run of Harvey's Legal Agent Benchmark on Harvey's newer private set of 120 tasks across 24 practice areas. A deliverable with a material hallucination scores zero, and the headline is the share of judges who find every rubric criterion passed. GPT-6.2 Astra 15%
Data audit
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 2 years ago, in May 2024, for GPT-4o. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the benchmark’s paper (6 entries).
- Pass Models scored 3 models we track, plus 3 other entries on its leaderboard.
- Warning Newest score The newest came 2 years ago, in May 2024, for GPT-4o.
- Note Frontier models None of the top 10 has a score. The strongest tested is GPT-4o (#162).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 3 rows for models we track and 3 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.