LLM-SRBench
Models infer scientific equations from observations on 239 problems across four scientific domains. Symbolic accuracy checks whether the discovered equation recovers the underlying relationship.
LSR-Transform rewrites familiar physical models, while LSR-Synth supplies synthetic discovery problems.
- Made by
- Virginia Tech, VinUniversity, Carnegie Mellon University and others
- Released
- April 2025
- Kind
- Research science
- Level
- Research frontier
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Subject
- Mathematics, Physical sciences
- Language
- English
- Interaction
- Agentic
- Environment
- Code sandbox
- Items from
- Generated
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Agents
- Strongest model tested
-
Llama 3.1-8B #203 on the capability index
- Last model added
- July 2024
- Scores refreshed
- November 20th, 2026
In the authors’ words
Scientific equation discovery is a fundamental task in the history of scientific progress, enabling the derivation of laws governing natural phenomena. Recently, Large Language Models (LLMs) have gained interest for this task due to their potential to leverage embedded scientific knowledge for hypothesis generation. However, evaluating the true discovery capabilities of these methods remains challenging, as existing benchmarks often rely on common equations that are susceptible to memorization by LLMs, leading to inflated performance metrics that do not reflect discovery. In this paper, we introduce LLM-SRBench, a comprehensive benchmark with 239 challenging problems across four scientific domains specifically designed to evaluate LLM-based scientific equation discovery methods while preventing trivial memorization. Our benchmark comprises two main categories: LSR-Transform, which transforms common physical models into less common mathematical representations to test reasoning beyond memorized forms, and LSR-Synth, which introduces synthetic, discovery-driven problems requiring data-driven reasoning. Through extensive evaluation of several state-of-the-art methods, using both open and closed LLMs, we find that the best-performing system so far achieves only 31.5% symbolic accuracy. These findings highlight the challenges of scientific equation discovery, positioning LLM-SRBench as a valuable resource for future research.
GPT-4o-mini (snapshot unspecified) tops the leaderboard with 17.9% Llama 3.1-8B leads with 15.1%
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The paper reports no overall score, so this is the plain mean of its five symbolic accuracy scores. 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. The best model we track is Llama 3.1-8B, at 15.1%. This view shows only models we track, each at its best.
- 1 GPT-4o-mini (snapshot unspecified) 17.9%
- 2
Llama 3.1-8B 15.1%
- 3 GPT-3.5-turbo (snapshot unspecified) 8.02%
Source: The LLM-SRBench paper
- 1
Llama 3.1-8B 15.1%
Source: The LLM-SRBench paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4o-mini (snapshot unspecified) | 17.9% | LLM-SR | Official leaderboard | |
| 2 | | 15.1% | LLM-SR | Jul 2024 | Official leaderboard |
| 3 | GPT-3.5-turbo (snapshot unspecified) | 8.02% | LaSR | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 15.1% | LLM-SR | Jul 2024 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The LLM-SRBench 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 LLM-SRBench 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 Science and reasoning
- GPQA Diamond In use 198 graduate-level 'Google-proof' multiple-choice questions in biology, chemistry and physics.
Gemini 4 Carbon 97%
- Terminal-Bench-Science In use 70 scientific research-workflow tasks across five science areas, run in Harbor containers. Hidden tests give the resolution rate. GPT-6 Astra 68.1%
- BioMysteryBench In use Bioinformatics problems on anonymized real datasets that require real analysis with tools. Rubric-graded, with human-solvable and human-difficult splits. Claude Fable 5.2 83.7%
- FrontierScience In use Models solve physics, chemistry, and biology problems in an Olympiad track graded by short answer and a Research track graded by 10-point rubrics.
Intern-S2-397B 87%
- HiPhO In use Models solve theory problems from 2024 and 2025 physics olympiad exams, some with diagrams. Official marking schemes grade answers and steps, mapped to medal levels.
Gemini 3 Pro 78.3%
- LABBench2 In use 11 biology research sub-tasks (literature, figures, tables, patents, trials and more) with tool access. Macro-averaged accuracy. GPT-5.2 60.9%
Data audit
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 2 years ago, in July 2024, for Llama 3.1-8B. 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 (3 entries).
- Note Models scored Only 1 model we track, plus 2 other entries on its leaderboard.
- Warning Newest score The newest came 2 years ago, in July 2024, for Llama 3.1-8B.
- Note Frontier models None of the top 10 has a score. The strongest tested is Llama 3.1-8B (#203).
- Pass Headroom The best is 15.1%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 4 rows for models we track and 2 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.