Benchmark Almanac

Putnam-AXIOM

Not in model cards

Models solve Putnam mathematics problems and equivalent variants. The evaluator checks final answers to test whether models generalize beyond familiar problem statements.

The date uses the creation month of the published dataset repository.

Made by
Aryan Gulati and colleagues
Released
May 2025
Kind
Competition problems with answers
Level
Competition
Scored
Checked automatically
Answers
Short answer
Tasks
All public
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
Anyone
Strongest model tested
o1-preview #149 on the capability index
Last model added
September 2024
Scores refreshed
November 20th, 2026
18
Entries in its paper, 2 models we track

o1-preview leads with 41.9% o1-preview leads with 41.9%

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. 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.

  1. 1 o1-preview 41.9%
  2. 2 GPT-4o (snapshot unspecified) 19.4%
  3. 3 Claude-3.5 Sonnet (snapshot unspecified) 16%
  4. 4 Qwen2-Math-7B-Instruct 11.5%
  5. 5 GPT-4 (snapshot unspecified) 11.3%
  6. 6 NuminaMath-7B-Base 10.3%
  7. 7 Qwen2-Math-7B-Base 9.57%
  8. 8 DeepSeek-Math-7B-RL 8.62%
  9. 9 DeepSeekMath-7B-Instruct 6.89%
  10. 10 Llama-3-8b Instruct 5.75%
  11. 11 Gemma-7B-Base 4.60%
  12. 12 Gemma-7B-Instruct 4.60%
  13. 13 DeepSeek-Math-7B-Base 4.02%
  14. 14 Mistral-7B-Instruct-v0.3 4.02%
  15. 15 Mistral-7B-v0.3-Base 4.02%
  16. 16 Llama-3-8B-Base 3.25%
  17. 17 Gemma-2B-Base 2.87%
  18. 18 Gemma-2B-Instruct 0.95%

Source: The Putnam-AXIOM paper

Source: The Putnam-AXIOM paper

#EntryScoreSettingDateSource
1 o1-preview 41.9% Sep 2024 Official leaderboard
2 GPT-4o (snapshot unspecified) 19.4% Official leaderboard
3 Claude-3.5 Sonnet (snapshot unspecified) 16% Official leaderboard
4 Qwen2-Math-7B-Instruct 11.5% Official leaderboard
5 GPT-4 (snapshot unspecified) 11.3% Official leaderboard
6 NuminaMath-7B-Base 10.3% Official leaderboard
7 Qwen2-Math-7B-Base 9.57% Official leaderboard
8 DeepSeek-Math-7B-RL 8.62% Official leaderboard
9 DeepSeekMath-7B-Instruct 6.89% Feb 2024 Official leaderboard
10 Llama-3-8b Instruct 5.75% Official leaderboard
11 Gemma-7B-Base 4.60% Official leaderboard
12 Gemma-7B-Instruct 4.60% Official leaderboard
13 DeepSeek-Math-7B-Base 4.02% Official leaderboard
14 Mistral-7B-Instruct-v0.3 4.02% Official leaderboard
15 Mistral-7B-v0.3-Base 4.02% Official leaderboard
16 Llama-3-8B-Base 3.25% Official leaderboard
17 Gemma-2B-Base 2.87% Official leaderboard
18 Gemma-2B-Instruct 0.95% Official leaderboard
#ModelScoreSettingDateSource
1 o1-preview 41.9% Sep 2024 Official leaderboard
2 DeepSeekMath-7B-Instruct 6.89% Feb 2024 Official leaderboard

Scores over time

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

In the benchmark’s paper Best so far
0% 20% 40% 60% 80% 100% 2024 Near the ceiling (85%) o1-preview DeepSeekMath-7B-Instruct 0% 20% 40% 60% 80% 100% 2024 Near the ceiling (85%) o1-preview DeepSeekMath-7B-Instruct

Source: Official Putnam-AXIOM 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

9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 2 years ago, in September 2024, for o1-preview. 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 (18 entries).
  • Pass Models scored 2 models we track, plus 16 other entries on its leaderboard.
  • Warning Newest score The newest came 2 years ago, in September 2024, for o1-preview.
  • Note Frontier models None of the top 10 has a score. The strongest tested is o1-preview (#149).
  • Pass Headroom The best is 41.9%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 2 rows for models we track and 16 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.

How we check