Benchmark Almanac

Math24o

o3-mini 85.7% leads since March 2025
Not in model cards

Models solve Chinese high school mathematics olympiad preliminary problems from 2024. A program compares their final answers with reference answers.

The authors publish model accuracy and an automatic evaluation script.

Made by
SuperCLUE team
Released
March 2025
Kind
Competition problems with answers
Level
Competition
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Measures
Capability
Subject
Mathematics
Language
Chinese
In and out
Text → Text
Interaction
Single turn
Items from
Exams and contests
Refresh
One fixed set
Run by
Anyone
Strongest model tested
o1 #118 on the capability index
Last model added
March 2025
Scores refreshed
November 20th, 2026
7
Entries on its own leaderboard, 6 models we track

o3-mini leads with 85.7% among models released by March 2025 o3-mini leads with 85.7% among models released by March 2025

Best score per entry from the benchmark's own leaderboard, read on November 20th, 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 March 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-mini high 85.7%
  2. 2 Gemini 2.0 Flash Thinking Jan 2025 71.4%
  3. 3 o1 66.7%
  4. 4 QwQ-32B 66.7%
  5. 5 QwQ-Max-Preview 66.7%
  6. 6 DeepSeek-R1 57.1%
  7. 7 Claude 3.7 Sonnet 57.1%

Source: Official Math24o leaderboard

#EntryScoreSettingReleasedRun onSource
1 o3-mini 85.7% high, API Jan 2025 Mar 2025 Official leaderboard
2 Gemini 2.0 Flash Thinking Jan 2025 71.4% API Jan 2025 Mar 2025 Official leaderboard
3 o1 66.7% API Dec 2024 Mar 2025 Official leaderboard
4 QwQ-32B 66.7% 模型 Mar 2025 Mar 2025 Official leaderboard
5 QwQ-Max-Preview 66.7% 官网 Mar 2025 Official leaderboard
6 DeepSeek-R1 57.1% API Jan 2025 Mar 2025 Official leaderboard
7 Claude 3.7 Sonnet 57.1% POE Feb 2025 Mar 2025 Official leaderboard
#ModelScoreSettingReleasedRun onSource
1 o3-mini 85.7% high, API Jan 2025 Mar 2025 Official leaderboard
2 Gemini 2.0 Flash Thinking Jan 2025 71.4% API Jan 2025 Mar 2025 Official leaderboard
3 o1 66.7% API Dec 2024 Mar 2025 Official leaderboard
4 QwQ-32B 66.7% 模型 Mar 2025 Mar 2025 Official leaderboard
5 DeepSeek-R1 57.1% API Jan 2025 Mar 2025 Official leaderboard
6 Claude 3.7 Sonnet 57.1% POE Feb 2025 Mar 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
Own leaderboard Passed 85% in Mar 2025, by o3-mini
o3-mini 85.7%

Source: Official Math24o leaderboard

O3-mini on the official leaderboard passed 85% in January 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
On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) o3-mini Gemini 2.0 Flash Thinking o1 0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) o3-mini Gemini 2.0 Flash Thinking

Source: Official Math24o 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

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 official leaderboard (7 entries).
  • Pass Models scored 6 models we track, plus 1 other entry on its leaderboard.
  • Note Newest score The newest came 20 months ago, in March 2025, for QwQ-32B. 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 o1 (#118).
  • Note Headroom Saturated. The best is 85.7%, past 85% since January 2025.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 6 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