Benchmark Almanac

LLM-IOAA

GPT-5 86.3% leads since October 2025
Not in model cards

Models solve 49 theory problems and eight data analysis problems from four astronomy olympiads. Two expert graders score the solutions using the official rubrics.

The international olympiad organizers published the five models’ results in their resources. Synced covered the evaluation on 36Kr.

Released
October 2025
Kind
Science olympiads
Level
Competition
Scored
Graded by people
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Tables → Text
Interaction
Single turn
Items from
Exams and contests
Refresh
One fixed set
Run by
Anyone
Strongest model tested
GPT-5 #71 on the capability index
Last model added
August 2025
Scores refreshed
November 20th, 2026
5
Entries in its paper, 4 models we track

GPT-5 leads with 86.3% among models released by August 2025 GPT-5 leads with 86.3% among models released by August 2025

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 the theory and data analysis exam 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. This view shows only models we track, each at its best.

The newest model with a score here came out in August 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 GPT-5 86.3%
  2. 2 Gemini 2.5 Pro (snapshot unspecified) 80.7%
  3. 3 o3 72.6%
  4. 4 Claude Opus 4.1 59.8%
  5. 5 Claude Sonnet 4 54.3%

Source: The LLM-IOAA paper

Source: The LLM-IOAA paper

#EntryScoreSettingDateSource
1 GPT-5 86.3% Aug 2025 Official leaderboard
2 Gemini 2.5 Pro (snapshot unspecified) 80.7% Official leaderboard
3 o3 72.6% Apr 2025 Official leaderboard
4 Claude Opus 4.1 59.8% Aug 2025 Official leaderboard
5 Claude Sonnet 4 54.3% May 2025 Official leaderboard
#ModelScoreSettingDateSource
1 GPT-5 86.3% Aug 2025 Official leaderboard
2 o3 72.6% Apr 2025 Official leaderboard
3 Claude Opus 4.1 59.8% Aug 2025 Official leaderboard
4 Claude Sonnet 4 54.3% May 2025 Official leaderboard

Rankings by part

We read 17 parts from the benchmark’s paper in 2 groups: theory exams and data analysis exams. Each ranks models on one part of the test. GPT-5 leads 15 of them, and o3 leads the other 2. Arrows show how far a model moved from its overall rank among the models we track.

Theory Exams

4 models we track have a score here.

  1. 1 GPT-5 84.2%
  2. 2 o3 77.5%
  3. 3 Claude Opus 4.1 64.7%
  4. 4 Claude Sonnet 4 60.6%

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI
Benchmark paper Passed 85% in Oct 2025, by GPT-5
GPT-5 86.3%

Source: The LLM-IOAA paper

GPT-5 on the official leaderboard passed 85% in August 2025

Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
In the benchmark’s paper Best so far
0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) GPT-5 o3 0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) GPT-5 o3

Source: Official LLM-IOAA 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

All 203 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

All 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the benchmark’s paper (5 entries).
  • Pass Models scored 4 models we track, plus 1 other entry on its leaderboard.
  • Note Newest score The newest came 15 months ago, in August 2025, for GPT-5. That’s expected for a saturated test.
  • Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is GPT-5 (#71).
  • Note Headroom Saturated. The best is 86.3%, past 85% since August 2025.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 4 rows for models we track and 1 other entry 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.

How we check