Benchmark Almanac

Hardest SAT Problems (Vellum)

Claude Sonnet 4 94% leads since May 2025
Not in model cards

Models solve 50 hard SAT math problems. A judge compares each final answer with a reference, and a person reviews the result.

Vellum published a ranked chart for five models and repeated the evaluation across model launches. The chart reports percentage accuracy.

Made by
Vellum
Kind
Word problems
Level
School
Scored
Graded by a model
Answers
Short answer
Measures
Capability
Subject
Mathematics
Language
English
In and out
Text → Text
Interaction
Single turn
Items from
Exams and contests
Refresh
One fixed set
Run by
A host
Strongest model tested
o3 #84 on the capability index
Last model added
May 2025
Scores refreshed
November 21st, 2026
5
Entries on its own leaderboard, 4 models we track

Claude Sonnet 4 leads with 94% among models released by May 2025 Claude Sonnet 4 leads with 94% among models released by May 2025

Best score per entry from the benchmark's own leaderboard, read on November 21st, 2026. 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 May 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 Claude Sonnet 4 94%
  2. 2 Qwen 90%
  3. 3 o4-mini 88%
  4. 4 Claude Opus 4 88%
  5. 5 o3 86%

Source: Official Hardest SAT Problems (Vellum) leaderboard

Source: Official Hardest SAT Problems (Vellum) leaderboard

#EntryScoreSettingDateSource
1 Claude Sonnet 4 94% May 2025 Official leaderboard
2 Qwen 90% Official leaderboard
3 o4-mini 88% Apr 2025 Official leaderboard
4 Claude Opus 4 88% May 2025 Official leaderboard
5 o3 86% Apr 2025 Official leaderboard
#ModelScoreSettingDateSource
1 Claude Sonnet 4 94% May 2025 Official leaderboard
2 o4-mini 88% Apr 2025 Official leaderboard
3 Claude Opus 4 88% May 2025 Official leaderboard
4 o3 86% Apr 2025 Official leaderboard

2 models have held number one on the official leaderboard since 2023

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

OpenAI Anthropic
Own leaderboard Passed 85% in Apr 2025, by o4-mini

Source: Official Hardest SAT Problems (Vellum) leaderboard

O4-mini on the official leaderboard passed 85% in April 2025

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) Claude Sonnet 4 o4-mini 0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) Claude Sonnet 4

Source: Official Hardest SAT Problems (Vellum) 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 Math

All 140 in Math
  • AIME 2026 In use Models solve the 30 integer-answer problems from the 2026 AIME I and II math competitions. Scored by exact answer match. GPT-5.5 100%
  • IMO-AnswerBench In use 400 olympiad problems with short verifiable answers, robustified against memorization. Scored by answer match. GLM-5.2 91%
  • HMMT 2026 In use Models solve the 33 final-answer problems from the February 2026 Harvard-MIT Mathematics Tournament. Scored by exact answer match. GPT-5.5 98.5%
  • PolyMath In use Models solve 9,000 parallel math problems in 18 languages across four difficulty levels, from school math to frontier math. Final answers are checked. Qwen3.7-Max 86.5%
  • MathArena (Apex, IMO, USAMO) In use Evaluates models on newly released math competitions after release. Final-answer or human/LLM-judged proof scores. Claude Opus 4.8 81.3%
  • MathArena Apex Shortlist In use Models solve 47 hard final-answer problems that MathArena selected from 2025 competitions, where the best models scored about 50% at selection. Scored by accuracy over repeated attempts. GPT-5.5 98.4%

Data audit

7 of 8 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark

Catalog record 1 warning 1 pass
  • Warning Task access We don’t know whether the tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (5 entries).
  • Pass Models scored 4 models we track, plus 1 other entry on its leaderboard.
  • Note Newest score The newest came 18 months ago, in May 2025, for Claude Opus 4. 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 o3 (#84).
  • Note Headroom Saturated. The best is 94%, past 85% since April 2025.
Leaderboard import 3 pass
  • Pass Importer We read the board on vellum.ai: 4 rows for models we track and 1 other entry at the last read.
  • Pass Last read November 21st, 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