Putnam-like
Gemini 2.5 Pro Mar 2025 94.5% leads since September 2025 Models write proofs for 96 university problems in 8 sets of 12, in the style of the easier and middle Putnam tiers. Each problem has a Lean statement and a point rubric for grading.
Ships graded sample answers from Gemini models such as gemini-2-5-pro_20250718.
- Made by
- Google DeepMind
- Released
- September 2025
- Kind
- Written proofs
- Level
- University
- Scored
- Graded by a model
- Answers
- Written proof
- Tasks
- All public
- Strongest model tested
- o4-mini #94 on the capability index
- Last model added
- June 2025
- Scores refreshed
- November 12th, 2026
Gemini 2.5 Pro leads with 94.5% among models released by June 2025
Best score per entry from the benchmark's own leaderboard, read on November 12th, 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.
The newest model with a score here came out in June 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- Claude Fable 5.2
- Gemini 4 Carbon
- GPT-6 Astra
- Claude Opus 5.5
- and 16 more
- 1 Gemini 2.5 Pro Mar 2025 94.5%
- 2 Gemini 2.5 Pro Jun 2025 91.2%
- 3 Gemini 2.5 Flash Apr 2025 84%
- 4 o4-mini high 70.4%
- 5 Claude 3.7 Sonnet 67.9%
- 6 o3-mini high 64.4%
- 7 DeepSeek R1 (snapshot unspecified) 53.5%
Source: Official Putnam-like leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Gemini 2.5 Pro Mar 2025 | 94.5% | Published Gemini 2.5 Pro judge (2025-07-18) | Mar 2025 | Official leaderboard |
| 2 | Gemini 2.5 Pro Jun 2025 | 91.2% | Published Gemini 2.5 Pro judge (2025-07-18) | Jun 2025 | Official leaderboard |
| 3 | Gemini 2.5 Flash Apr 2025 | 84% | Published Gemini 2.5 Pro judge (2025-07-18) | Apr 2025 | Official leaderboard |
| 4 | o4-mini | 70.4% | high, Published Gemini 2.5 Pro judge (2025-07-18) | Apr 2025 | Official leaderboard |
| 5 | Claude 3.7 Sonnet | 67.9% | Published Gemini 2.5 Pro judge (2025-07-18) | Feb 2025 | Official leaderboard |
| 6 | o3-mini | 64.4% | high, Published Gemini 2.5 Pro judge (2025-07-18) | Jan 2025 | Official leaderboard |
| 7 | DeepSeek R1 (snapshot unspecified) | 53.5% | Published Gemini 2.5 Pro judge (2025-07-18) | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Putnam-like leaderboard
Gemini 2.5 Pro on the official leaderboard passed 85% in March 2025
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Putnam-like leaderboard
No lab model card reports it yet
We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.
More 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%