Benchmark Almanac

ProgramDistill

GPT-6 Astra 84.3% leads since September 2026
Not in model cards

Agents inspect working web applications and restore missing features in editable copies. Replayed browser traces check whether patches recover the reference behavior. The paper evaluates partial repairs and full application reconstruction.

The paper constructs 4,063 tasks across 26 applications and uses a 300-task subset for partial reconstruction. It states that public release is in progress. Restoration depth and lineage scoring define distinct reporting settings.

Released
September 2026
Kind
Web and app front ends
Level
University
Scored
Checked automatically
Answers
Agent task
Tasks
Kept private
Measures
Capability
Language
English
In and out
Text, Screens, Code → Code, Actions
Interaction
Agentic
Environment
Terminal, Browser
Items from
Real work and use
Refresh
One fixed set
Run by
A host
In views
Computer use, Agents
Strongest model tested
GPT-6 Astra #4 on the capability index
Last model added
September 2026
Scores refreshed
November 20th, 2026

In the authors’ words

Coding agents are typically evaluated with desired behavior specified through issues or instructions. In practical web development, however, agents may need to infer behavior from working software and implement it in an incomplete application. We introduce ProgramDistill, a benchmark evaluating coding agents on features discovered through interaction with fully functional reference applications. We build ProgramDistill by factorizing applications into features of different granularities, each associated with replayable behaviors executable via its gold patch. Our pipeline, mine-craft-patch, discovers 1,975 replay-verified behaviors across 26 applications and constructs 4,063 tasks without human intervention. Across nine frontier coding agents, GPT-6 Astra and Claude Opus 5 achieve 49.2% and 28.8% success on cumulative workflows in full-application reconstruction. In partial-application reconstruction, success falls from 100% to 64.0% and from 96% to 32% as restoration depth increases from 1 to 8. ProgramDistill thus provides a scalable benchmark with controlled difficulty for evaluating and diagnosing coding agents, and a natural basis for future curriculum-based training.

Abstract of ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks (arXiv:2609.18805, CC0)
9
Models scored in its paper

GPT-6 Astra leads with 84.3% among models released by September 2026

Best score per model from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best.

The newest model with a score here came out in September 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

Source: The ProgramDistill paper

#ModelScoreSettingDateSource
1 GPT-6 Astra 84.3% ProgramDistill-300; partial reconstruction; high effort; 1000 steps Sep 2026 Official leaderboard
2 Claude Opus 5 68.7% ProgramDistill-300; partial reconstruction; high effort; 1000 steps Jul 2026 Official leaderboard
3 GPT-5.6 Sol 60.7% ProgramDistill-300; partial reconstruction; high effort; 1000 steps Jul 2026 Official leaderboard
4 Grok 4.6 48.3% ProgramDistill-300; partial reconstruction; high effort; 1000 steps Aug 2026 Official leaderboard
5 Claude Sonnet 5 47.3% ProgramDistill-300; partial reconstruction; high effort; 1000 steps Jun 2026 Official leaderboard
6 GPT-5.3 Codex 45.7% ProgramDistill-300; partial reconstruction; high effort; 1000 steps Feb 2026 Official leaderboard
7 Gemini 3.7 Flash 45.3% ProgramDistill-300; partial reconstruction; high effort; 1000 steps Aug 2026 Official leaderboard
8 Gemini 3.6 Flash 29.7% ProgramDistill-300; partial reconstruction; high effort; 1000 steps Jul 2026 Official leaderboard
9 Gemini 3.1 Pro 22.3% ProgramDistill-300; partial reconstruction; high effort; 1000 steps Feb 2026 Official leaderboard

Rankings by part

We read 3 parts from the benchmark’s paper: Cumulative tasks, Logic only and Logic and UI. Each ranks models on one part of the test. GPT-6 Astra leads every one of them. Arrows show how far a model moved from its overall rank among the models we track.

Cumulative tasks

9 models we track have a score here.

  1. 1 GPT-6 Astra 81.2%
  2. 2 Claude Opus 5 63.2%
  3. 3 GPT-5.6 Sol 54.4%
  4. 4 Claude Sonnet 5 ↑1 40.8%
  5. 5 Grok 4.6 ↓1 40.4%
  6. 6 GPT-5.3 Codex 38.8%
  7. 7 Gemini 3.7 Flash 37.6%
  8. 8 Gemini 3.6 Flash 23.2%
  9. 9 Gemini 3.1 Pro 12.8%

2 models have held number one in the benchmark’s paper since its release in September 2026

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

Anthropic OpenAI
Benchmark paper Not tested since Sep 2026
GPT-6 Astra 84.3%

Source: The ProgramDistill paper

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
In the benchmark’s paper Best so far
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) GPT-6 Astra Claude Opus 5 GPT-5.6 Sol Claude Sonnet 5 GPT-5.3 Codex 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) GPT-6 Astra Claude Opus 5

Source: Official ProgramDistill 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 Coding

All 523 in Coding
  • SWE-bench Verified In use 500 human-validated GitHub issues from 12 Python repos. Agent writes a patch that must pass hidden tests. Claude Opus 4.7 83.5%
  • LiveCodeBench v6 In use Competitive programming problems collected after model cutoffs from LeetCode, AtCoder, Codeforces. Scored pass@1 on hidden tests. DeepSeek-V4-Pro 93.5%
  • SWE-bench Multilingual In use 300 GitHub-issue tasks across nine programming languages in SWE-bench format. Patch graded by repository tests. Claude Fable 5.2 96.6%
  • DeepSWE In use 113 original long-horizon engineering tasks across 91 repos and five languages, written from scratch. Hand-written verifiers accept alternative solutions. GPT-6 Astra 74.1%
  • SciCode In use Scientist-curated research coding problems split into subproblems across natural sciences. Code checked against test cases. Seed2.1 Pro 59.8%
  • Codeforces rating In use Model solves recent Codeforces contest problems. An Elo-style rating is computed from simulated contest performance. DeepSeek V4.1 Flash 3,471

Data audit

All 10 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access The tasks are private.
  • Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
  • Pass Independent runs Scores from the benchmark’s paper (9 entries).
  • Pass Models scored 9 models we track.
  • Pass Newest score The newest is from September 2026, for GPT-6 Astra.
  • Note Frontier models Only 1 of the top 10 has a score. The strongest tested is GPT-6 Astra (#4).
  • Pass Headroom The best is 84.3%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 9 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