# Logical Reasoning and Reading Comprehension on LSAT Official (test N=77)

Source: [Logical Reasoning and Reading Comprehension on LSAT Official (test N=77)](<https://www.sota2.com/research/sota/logical-reasoning-and-reading-comprehension-on-lsat-official-test-n-77>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-14T07:51:31.003Z

Evaluation of model performance on the official test split (N=77) of the LSAT dataset, covering Logical Reasoning and Reading Comprehension tasks.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Logical Reasoning and Reading Comprehension |
| Dataset (including any stated split) | LSAT Official (test N=77) |
| Metric | LR Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [LR Accuracy](<https://www.sota2.com/research/sota/logical-reasoning-and-reading-comprehension-on-lsat-official-test-n-77.md?metric=LR%20Accuracy>): Higher is better; unit: PERCENT.

- [RC Accuracy](<https://www.sota2.com/research/sota/logical-reasoning-and-reading-comprehension-on-lsat-official-test-n-77.md?metric=RC%20Accuracy>): Higher is better; unit: PERCENT.

- [Overall Accuracy](<https://www.sota2.com/research/sota/logical-reasoning-and-reading-comprehension-on-lsat-official-test-n-77.md?metric=Overall%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | LR Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| DeepSeek-R1 | 100 | Not recorded | 69ddc9ee7d0172140ec79863 |
| Kimi K2 Thinking | 100 | Not recorded | 69ddc9ee7d0172140ec79863 |
| GPT-5 | 98 | Not recorded | 69ddc9ee7d0172140ec79863 |
| Claude Opus 4 | 98 | Not recorded | 69ddc9ee7d0172140ec79863 |
| Gemini 2.5 Pro | 94 | Not recorded | 69ddc9ee7d0172140ec79863 |
| QwQ-32B | 92 | Not recorded | 69ddc9ee7d0172140ec79863 |
| DeepSeek-R1 Distill 7B | 54 | Not recorded | 69ddc9ee7d0172140ec79863 |
| DeepSeek-R1 Distill Llama 8B | 46 | Not recorded | 69ddc9ee7d0172140ec79863 |

### DeepSeek-R1

LR Accuracy: 100. Result ID: 69ddf1e747f34ce924c523e9.

[Reporting paper](<https://www.sota2.com/research/paper/69ddc9ee7d0172140ec79863.md>)

Recorded evaluation configuration: {"system prompt":"none","answer reordering":"none","sampling":"single sample"}. This record does not assert independent reproduction.

### Kimi K2 Thinking

LR Accuracy: 100. Result ID: 69ddf1e747f34ce924c523ea.

[Reporting paper](<https://www.sota2.com/research/paper/69ddc9ee7d0172140ec79863.md>)

Recorded evaluation configuration: {"system prompt":"none","answer reordering":"none","sampling":"single sample"}. This record does not assert independent reproduction.

### GPT-5

LR Accuracy: 98. Result ID: 69ddf1e747f34ce924c523e6.

[Reporting paper](<https://www.sota2.com/research/paper/69ddc9ee7d0172140ec79863.md>)

Recorded evaluation configuration: {"system prompt":"none","answer reordering":"none","sampling":"single sample"}. This record does not assert independent reproduction.

### Claude Opus 4

LR Accuracy: 98. Result ID: 69ddf1e747f34ce924c523e7.

[Reporting paper](<https://www.sota2.com/research/paper/69ddc9ee7d0172140ec79863.md>)

Recorded evaluation configuration: {"system prompt":"none","answer reordering":"none","sampling":"single sample"}. This record does not assert independent reproduction.

### Gemini 2.5 Pro

LR Accuracy: 94. Result ID: 69ddf1e747f34ce924c523e8.

[Reporting paper](<https://www.sota2.com/research/paper/69ddc9ee7d0172140ec79863.md>)

Recorded evaluation configuration: {"system prompt":"none","answer reordering":"none","sampling":"single sample"}. This record does not assert independent reproduction.

### QwQ-32B

LR Accuracy: 92. Result ID: 69ddf1e747f34ce924c523eb.

[Reporting paper](<https://www.sota2.com/research/paper/69ddc9ee7d0172140ec79863.md>)

Recorded evaluation configuration: {"system prompt":"none","answer reordering":"none","sampling":"single sample"}. This record does not assert independent reproduction.

### DeepSeek-R1 Distill 7B

LR Accuracy: 54. Result ID: 69ddf1e747f34ce924c523ec.

[Reporting paper](<https://www.sota2.com/research/paper/69ddc9ee7d0172140ec79863.md>)

Recorded evaluation configuration: {"system prompt":"none","answer reordering":"none","sampling":"single sample"}. This record does not assert independent reproduction.

### DeepSeek-R1 Distill Llama 8B

LR Accuracy: 46. Result ID: 69ddf1e747f34ce924c523ed.

[Reporting paper](<https://www.sota2.com/research/paper/69ddc9ee7d0172140ec79863.md>)

Recorded evaluation configuration: {"system prompt":"none","answer reordering":"none","sampling":"single sample"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.