{"schema":"postcutoff/event@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/e/2025-11-27-deepseekmath-v2/","md":"https://postcutoff.com/e/2025-11-27-deepseekmath-v2/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2025-11-27-deepseekmath-v2","date":"2025-11-27","date_precision":"day","short_title":"DeepSeekMath-V2: open-weights self-verifying prover reaches IMO 2025 gold level and 118/120 on Putnam 2024","deck":null,"takeaway":"DeepSeek released DeepSeekMath-V2 (685B parameters, built on DeepSeek-V3.2-Exp-Base, Apache 2.0).","category":"open-source","category_label":"Open source","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"arXiv 2511.22570","url":"https://arxiv.org/abs/2511.22570","type":"paper","group":"primary","domain":"arxiv.org"},{"n":2,"title":"Hugging Face: deepseek-ai/DeepSeek-Math-V2","url":"https://huggingface.co/deepseek-ai/DeepSeek-Math-V2","type":"code","group":"primary","domain":"huggingface.co"}],"official":2,"filed":"2026-09-29","updated":"2026-09-29","orgs":["DeepSeek"],"title":"DeepSeekMath-V2: open-weights self-verifying prover reaches IMO 2025 gold level and 118/120 on Putnam 2024","summary":"DeepSeek released DeepSeekMath-V2 (685B parameters, built on DeepSeek-V3.2-Exp-Base, Apache 2.0). It is trained to write natural-language proofs and check them with an LLM verifier, including a meta-verifier. With scaled test-time compute it reached gold-medal level on IMO 2025 and CMO 2024 and scored 118/120 on Putnam 2024. It was the first openly downloadable model at IMO-gold level.","key_facts":["Paper: arXiv 2511.22570 'DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning' (27 Nov 2025)","685B parameters; base DeepSeek-V3.2-Exp-Base; Apache 2.0 weights on Hugging Face","Gold-level scores on IMO 2025 and CMO 2024; 118/120 on Putnam 2024 (scaled test-time compute)","Method: faithful LLM proof verifier plus meta-verification to cut hallucinated issues; the generator is rewarded for finding and fixing its own errors; verifier compute is scaled to auto-label hard proofs without human annotation"],"key_numbers":[],"tags":["math","theorem-proving","open-weights","self-verification","imo","putnam"],"science":null,"body_md":"## What happened\n\nFour months after closed models from Google DeepMind and OpenAI reached IMO gold, DeepSeek released open weights for a proof-writing model at the same level. It made self-verification (generator + verifier + meta-verifier) the main training signal instead of final-answer rewards.\n\n## Why it matters\n\nIt made olympiad-level natural-language proof generation reproducible outside the big US labs. The generate-then-verify recipe became a common pattern in 2026 AI-for-math systems.","disputed":[],"related":[{"id":"2025-12-06-axiomprover-putnam-2025","url":"https://postcutoff.com/e/2025-12-06-axiomprover-putnam-2025/","date":"2025-12-06","date_precision":"day","short_title":"AxiomProver produces machine-checked Lean proofs for all 12 Putnam 2025 problems","deck":null,"takeaway":"Formal verification removes grading disputes like those around informal IMO proofs, and showed formal provers catching up with informal LLMs on hard competition maths.","category":"science","category_label":"Science & math","importance":3,"confidence":"medium","status":{"key":"confirmed","labels":["Result confirmed"]},"sources":2,"official":2,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Axiom Math"]},{"id":"2025-07-21-imo-gold-ai","url":"https://postcutoff.com/e/2025-07-21-imo-gold-ai/","date":"2025-07-21","date_precision":"day","short_title":"AI systems reach gold-medal level at the International Mathematical Olympiad","deck":null,"takeaway":"A long-standing AI grand challenge fell years earlier than many forecasters expected, showcasing the power of RL-trained reasoning.","category":"science","category_label":"Science & math","importance":5,"confidence":"high","status":{"key":"confirmed","labels":["Result confirmed"]},"sources":5,"official":4,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Google DeepMind","OpenAI"]},{"id":"2024-12-26-deepseek-v3","url":"https://postcutoff.com/e/2024-12-26-deepseek-v3/","date":"2024-12-26","date_precision":"day","short_title":"DeepSeek-V3: frontier-level open model trained for ~$5.6M in GPU time","deck":null,"takeaway":"Upended assumptions about the cost of frontier AI and China's position; it was the base for DeepSeek-R1 weeks later.","category":"open-source","category_label":"Open source","importance":5,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":2,"official":2,"filed":"2026-09-29","updated":"2026-09-29","orgs":["DeepSeek"]}],"people":[],"posts":[],"videos":[],"models":[{"id":"deepseekmath-v2","name":"DeepSeekMath-V2","url":"https://postcutoff.com/m/deepseekmath-v2/"}],"changes":[{"date":"2026-09-29","type":"filed","text":"Created"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-09-29","run":null,"sources_read":null,"updated":"2026-09-29","human_review":null,"version":{"date":"2026-10-04"}},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":null,"in_training_data":true},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":null,"in_training_data":true},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":null,"in_training_data":true},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":null,"in_training_data":true}],"short_url":"https://postcutoff.com/s/deepseekmath-v2-open-weights"}