LSAT
Models take a simulated Law School Admission Test. Scored on the 120 to 180 scale.
OpenAI ran this as a simulated exam in the GPT-4 Technical Report.
- Made by
- LSAC
- Kind
- Language reasoning
- Level
- University
- Scored
- Checked automatically
- Answers
- Multiple choice
- Strongest model tested
- Claude 3 Opus #172 on the capability index
- Last in a system card
- November 2024
- Last model added
- November 2024
GPT-4 leads with 163.0 among models released by March 2024
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 March 2024, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- Claude Fable 5.2
-
Gemini 4 Carbon - GPT-6 Astra
- Claude Opus 5.5
- and 16 more
- 1 GPT-4 Mar 2023 163.0
- 2 Claude 3 Opus 161.0
- 3 Claude 3 Sonnet 158.3
- 4 Claude 3 Haiku 156.3
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4 Mar 2023 | 163.0 | Mar 2023 | Lab model card | |
| 2 | Claude 3 Opus | 161.0 | Mar 2024 | Lab model card | |
| 3 | Claude 3 Sonnet | 158.3 | Mar 2024 | Lab model card | |
| 4 | Claude 3 Haiku | 156.3 | Mar 2024 | Lab model card |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Labs’ model cards
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Labs’ model cards
Labs report it only in system cards
We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark. Some system cards do, below.
7 system cards report it, from 3 labs
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| Nov 23, 2024 |  Llama 3.1-8B technical report | 53.9 | LSAT, accuracy, Preptests 71, 73, 80 and 93 (Table 17) | Capabilities |
| Nov 23, 2024 | Llama 3.1-70B technical report | 74.2 | LSAT, accuracy, Preptests 71, 73, 80 and 93 (Table 17) | Capabilities |
| Nov 23, 2024 | Llama 3.1-405B technical report | 81.1 | LSAT, accuracy, Preptests 71, 73, 80 and 93 (Table 17) | Capabilities |
| Mar 4, 2024 | Claude 3 Sonnet model card | 158.3 | LSAT, 5-shot CoT, scaled score averaged over PT89, PT90 and PT91 (Table 2) | Capabilities |
| Mar 4, 2024 | Claude 3 Opus model card | 161 | LSAT, 5-shot CoT, scaled score averaged over PT89, PT90 and PT91 (Table 2) | Capabilities |
| Mar 4, 2024 | Claude 3 Haiku model card | 156.3 | LSAT, 5-shot CoT, scaled score averaged over PT89, PT90 and PT91 (Table 2) | Capabilities |
| Mar 14, 2023 | GPT-4 technical report | 163 | LSAT, 163 (~88th percentile) (Table 1, GPT-4 with vision) | Capabilities |
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% - 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%
- KMMLU-Pro In use Models answer multiple-choice questions taken from Korean National Professional Licensure exams. It tests professional knowledge used in Korean industry.
Solar Pro 4 79.2% - HLE-Verified In use Verified and revised version of Humanity's Last Exam (1,811 items) with uncertain items removed.
Seed2.0 Pro 73.6%