Skip to main content
Radar

Every change to the models you run, with its source and its date. Releases, price changes, retirements, API changes, and incidents.Every change to the models you run, with its source.

Follow model changes

ProgramBench: Can Language Models Rebuild Programs From Scratch? (ProgramBench)

We mirror this table; we do not rank on it.

Data verified 36 confirmed releases in the last 30 daysFollow model changes

A cleanroom software-engineering benchmark where agents receive only a compiled executable and documentation, then must architect and implement a complete codebase that reproduces the original program's behavior.

Almost resolved rate on ProgramBench — Sep. 9, 2026

We mirror the published almost resolved rate view for ProgramBench. Claude Opus 5 leads the public snapshot at 37.0%, followed by Claude Opus 4.8 (16.5%) and GPT-5.6 Sol (15.5%). We do not use these results to rank models overall.

21 modelsCodingCurrentDisplay onlyUpdated Sep. 9, 2026

Almost resolved rate table (21 models)

Score
1
Claude Opus 5Anthropic · Closed
37.0%
2
Claude Opus 4.8Anthropic · Closed
16.5%
3
GPT-5.6 SolOpenAI · Closed
15.5%
4
GPT-5.5OpenAI · Closed
13.5%
5
GLM-5.2Z.AI · Open weight
8.5%
6
Gemini 3.7 FlashGoogle · Closed
5.5%
7
GPT-5.5OpenAI · Closed
5.0%
8
Claude Opus 4.7Anthropic · Closed
4.5%
9
Gemini 3.6 FlashGoogle · Closed
4.0%
10
Gemini 3.5 FlashGoogle · Closed
3.0%
11
Claude Opus 4.7Anthropic · Closed
3.0%
12
GPT-5.6 SolOpenAI · Closed
2.5%
13
Claude Opus 4.6Anthropic · Closed
2.5%
14
GPT-5.5OpenAI · Closed
1.5%
15
Claude Sonnet 4.6Anthropic · Closed
1.0%
16
GPT-5.4OpenAI · Closed
0.0%
17
Gemini 3.1 ProGoogle · Closed
0.0%
18
Gemini 3 FlashGoogle · Closed
0.0%
19
Claude Haiku 4.5Anthropic · Closed
0.0%
20
GPT-5.4 miniOpenAI · Closed
0.0%
21
GPT-5 miniOpenAI · Closed
0.0%

How ProgramBench is shown here

BenchLM mirrors the public ProgramBench leaderboard from Sep. 9, 2026. The official benchmark uses mini-SWE-agent on 200 cleanroom program-reconstruction tasks and reports both fully resolved and almost-resolved rates.

BenchLM displays the published almost-resolved rate as the visible score because the primary fully resolved metric is still very low and less differentiating. Almost resolved means the agent passed at least 95% of the hidden behavioral tests for a task. ProgramBench remains display only on BenchLM and is excluded from weighted coding and overall rankings until public model coverage broadens.

Snapshot

21 models200 tasks248,853 behavioral tests4.5% best fully resolvedDisplay only

The published ProgramBench snapshot places Claude Opus 5 first at 37.0%. The third row is 21.5 points behind. The broader top-10 range is 34.0 points, so the table still separates the published systems.

21 models have been evaluated on ProgramBench. The benchmark falls in the Coding category. This category carries a 20% weight in BenchLM.ai's overall scoring system. ProgramBench is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About ProgramBench

Year

2026

Tasks

200 program reconstruction tasks

Format

Cleanroom executable reimplementation

Difficulty

Full-repository software architecture

ProgramBench turns open-source projects into cleanroom reconstruction tasks. Each task starts from an execute-only binary and usage documentation, with no source code, internet, decompilation, or prescribed skeleton. Evaluation uses hidden behavioral tests generated through agent-driven fuzzing. BenchLM shows ProgramBench as display-only because all current public rows are tied at 0% fully resolved and the visible score is the auxiliary almost-resolved metric.

Freshness and provenance

Version

ProgramBench 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public task metadata and hidden behavioral tests

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Questions

What does ProgramBench measure?

A cleanroom software-engineering benchmark where agents receive only a compiled executable and documentation, then must architect and implement a complete codebase that reproduces the original program's behavior.

Which model leads the published ProgramBench snapshot?

Claude Opus 5 currently leads the published ProgramBench snapshot with 37.0% almost resolved rate. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on ProgramBench?

The Sep. 9, 2026 snapshot contains 21 AI models.

Last updated: Sep. 9, 2026 · mirrored from the public benchmark leaderboard

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 2,000+ readers.

One email each week. Unsubscribe anytime.