Benchmark Almanac

SPOT

o3 6.10% leads since May 2025
Not in model cards

Models inspect published manuscripts for errors that led to corrections or retractions. A judge checks whether each reported error matches the documented error and location.

Made by
Guijin Son and colleagues
Released
May 2025
Kind
Research science
Level
Expert
Scored
Graded by a model
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Documents → Text
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
Strongest model tested
o3 #84 on the capability index
Last model added
April 2025
Scores refreshed
November 20th, 2026
9
Models scored in its paper

o3 leads with 6.10% among models released by April 2025

Best score per model from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Table 2 lists precision first, the percentage of model-flagged errors that match a documented error. Where a model ran with several settings or harnesses, we keep its best.

The newest model with a score here came out in April 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 o3 Thinking 6.10%
  2. 2 Claude 3.7 Sonnet Non-thinking 3.20%
  3. 3 Gemini 2.5 Pro Mar 2025, Thinking 3.10%
  4. 4 GPT-4.1 Non-thinking 2.80%
  5. 5 Llama 4 Maverick Non-thinking 2.00%
  6. 6 Qwen2.5-VL-32B Non-thinking 1.90%
  7. 7 Gemini 2.0 Flash-Lite Non-thinking 1.00%
  8. 8 Llama 4 Scout Non-thinking 0.80%
  9. 9 Qwen2.5-VL-72B Non-thinking 0.60%

Source: The SPOT paper

#ModelScoreSettingDateSource
1 o3 6.10% Thinking Apr 2025 Official leaderboard
2 Claude 3.7 Sonnet 3.20% Non-thinking Feb 2025 Official leaderboard
3 Gemini 2.5 Pro Mar 2025 3.10% Thinking Mar 2025 Official leaderboard
4 GPT-4.1 2.80% Non-thinking Apr 2025 Official leaderboard
5 Llama 4 Maverick 2.00% Non-thinking Apr 2025 Official leaderboard
6 Qwen2.5-VL-32B 1.90% Non-thinking Mar 2025 Official leaderboard
7 Gemini 2.0 Flash-Lite 1.00% Non-thinking Feb 2025 Official leaderboard
8 Llama 4 Scout 0.80% Non-thinking Apr 2025 Official leaderboard
9 Qwen2.5-VL-72B 0.60% Non-thinking Jan 2025 Official leaderboard

Number one over time

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

OpenAI
Benchmark paper Not tested since May 2025
o3 6.10%

Source: The SPOT paper

Scores over time

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%) o3 Claude 3.7 Sonnet 0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) o3

Source: Official SPOT 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

9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 19 months ago, in April 2025, for o3. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
  • Pass Independent runs Scores from the benchmark’s paper (9 entries).
  • Pass Models scored 9 models we track.
  • Warning Newest score The newest came 19 months ago, in April 2025, for o3.
  • Note Frontier models None of the top 10 has a score. The strongest tested is o3 (#84).
  • Pass Headroom The best is 6.10%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 10 rows for models we track 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