Benchmark Almanac

Autoform-Hard

GPT-6.2 Astra 87.5% leads since November 2026
Not in model cards

Agents complete Lean 4 proofs on 56 formalization tasks that earlier models failed.

Vals corrected five tasks from the AutoformBench validation set and checks proofs in a clean workspace.

Made by
Vals AI
Released
November 2026
Kind
Formal proofs
Level
Expert
Scored
Checked automatically
Answers
Written proof
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Code → Code
Interaction
Agentic
Environment
Terminal
Items from
Another benchmark
Refresh
One fixed set
Run by
Anyone
Based on
AutoformBench
In views
Agents
Strongest model tested
GPT-6.2 Astra #1 on the capability index
Last model added
November 2026
Scores refreshed
November 20th, 2026
8
Models scored on its own leaderboard

GPT-6.2 Astra leads with 87.5%

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. 1 GPT-6.2 Astra 87.5%
  2. 2 Claude Fable 5.2 85.7%
  3. 3 GPT-6.2 Sol 85.7%
  4. 4 Gemini 4 Carbon 71.4%
  5. 5 Gemini 4 Hydrogen 64.3%
  6. 6 Gemini 4 Argon 48.2%
  7. 7 Beam 1.0 0%
  8. 8 MiniMax-M3.1-Flash 0%

Source: Official Autoform-Hard leaderboard

#ModelScore ±SettingDateSource
1 GPT-6.2 Astra 87.5% ±8.7 Nov 2026 Official leaderboard
2 Claude Fable 5.2 85.7% ±9.2 Nov 2026 Official leaderboard
3 GPT-6.2 Sol 85.7% ±9.2 Nov 2026 Official leaderboard
4 Gemini 4 Carbon 71.4% ±11.9 Oct 2026 Official leaderboard
5 Gemini 4 Hydrogen 64.3% ±12.7 Nov 2026 Official leaderboard
6 Gemini 4 Argon 48.2% ±13.2 Sep 2026 Official leaderboard
7 Beam 1.0 0% Oct 2026 Official leaderboard
8 MiniMax-M3.1-Flash 0% Oct 2026 Official leaderboard

3 models have held number one on the official leaderboard since its release in November 2026

Lab claims count from the day the card came out, independent runs from the model’s release.

Google DeepMind Anthropic OpenAI
Own leaderboard Passed 85% in Nov 2026, by Claude Fable 5.2

Source: Official Autoform-Hard leaderboard

Claude Fable 5.2 on the official leaderboard passed 85% in November 2026

Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2027 Near the ceiling (85%) GPT-6.2 Astra Gemini 4 Carbon Gemini 4 Argon 0% 20% 40% 60% 80% 100% 2027 Near the ceiling (85%) GPT-6.2 Astra Gemini 4 Carbon

Source: Official Autoform-Hard 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

All 10 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (8 entries).
  • Pass Models scored 8 models we track.
  • Pass Newest score The newest is from November 2026, for GPT-6.2 Astra.
  • Pass Frontier models 4 of the top 10 have a score, led by GPT-6.2 Astra (#1).
  • Note Headroom Saturated. The best is 87.5%, past 85% since November 2026.
Leaderboard import 3 pass
  • Pass Importer We read the board on vals.ai: 8 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.

How we check