LeanLean
Agents shorten Lean projects while preserving protected theorem statements and passing the build and axiom checks.
The October edition reports credited token reduction across 32 projects.
- Made by
- MathArena
- Released
- November 2026
- Kind
- Formal proofs
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Agentic
- Environment
- Terminal
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Agents
- Strongest model tested
- Claude Opus 5.5 #5 on the capability index
- Last model added
- October 2026
- Scores refreshed
- November 20th, 2026
GPT-6.1 Sol leads with 50.5%
Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.
- 1 GPT-6.1 Sol max 50.5%
- 2 Claude Opus 5.5 high 47.3%
- 3
Gemini 4 Argon high 38.7%
- 4 Kimi K3.1 Pro max 11.9%
- 5
DeepSeek V4.1 Flash 1017 max, dsh 9.78%
Source: Official LeanLean leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-6.1 Sol | 50.5% | max, Codex 0.159.0 | Sep 2026 | Official leaderboard |
| 2 | Claude Opus 5.5 | 47.3% | high, Claude Code 2.1.280 | Sep 2026 | Official leaderboard |
| 3 | | 38.7% | high, Antigravity 1.3.5 | Sep 2026 | Official leaderboard |
| 4 | Kimi K3.1 Pro | 11.9% | max, Kimi Code 2.3.1 | Oct 2026 | Official leaderboard |
| 5 | | 9.78% | max, dsh, DeepSeek Harness 0.2.1-rc.5 | Oct 2026 | 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 LeanLean leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official LeanLean 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
- 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 11 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 5 pass
- Pass Independent runs Scores from the official leaderboard (5 entries).
- Pass Models scored 5 models we track.
- Pass Newest score The newest is from October 2026, for Kimi K3.1 Pro.
- Pass Frontier models 3 of the top 10 have a score, led by Claude Opus 5.5 (#5).
- Pass Headroom The best is 50.5%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on matharena.ai: 5 rows for models we track 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.