Putnam 2025
DeepSeek-V4-Pro 120.0 Fading Models solve the 12 problems of the 2025 William Lowell Putnam competition with full proofs. Scored out of 120 points.
DeepSeek scored it with a hybrid informal and formal Lean pipeline checked by a strict verifier.
- Level
- Competition The strongest students, in olympiad-style contests
- Scored
- Graded by people Human experts grade or compare the outputs.
- Answers
- Written proof
DeepSeek-V4-Pro leads with 120.0
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
- 1 DeepSeek-V4-Pro 120.0
- 2
Seed-Prover 1.5 11.0
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | DeepSeek-V4-Pro | 120.0 | Apr 2026 | Model card | |
| 2 | Seed-Prover 1.5 | 11.0 | Dec 2025 | Model card |
The benchmark's own leaderboard has 5 entries, 4 of them models we track. We plot every source in the charts below.
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Labs headline it less often now, last in Dec 2025
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| 19 Dec 2025 | Seed-Prover 1.5 | 11 | Putnam 2025, 11 of 12 problems in 9 hours |
| 9 Dec 2025 | Nomos 1 | 72.5 | Putnam 2025: 87/120 with the Nomos reasoning harness |
2 system cards report it, from 2 labs
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 9 Jun 2026 |  Nemotron 3 Ultra technical report | 96.7 | Putnam 2025, 116/120, generate-verify-refine test-time scaling, human graded (Table 11) | Capabilities |
| 26 Apr 2026 | DeepSeek-V4-Pro technical report | 120 | Putnam-2025, hybrid formal-informal pipeline, 120/120 (Figure 8 right). The figure names the model only as DeepSeek-V4 | Capabilities |
Versions
More in Math
- IMO-AnswerBench In use 400 olympiad problems with short verifiable answers, robustified against memorization. Scored by answer match. GLM-5.2 91%
- 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%
- 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%
- 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%
- 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% - USAMO 2026 In use Models write full proofs for the six problems of the 2026 USA Mathematical Olympiad. Judges grade each proof from 0 to 7 against rubrics. GPT-5.5 98.2%