Skip to main content

Benchmark profile

DeepSWE

A long-horizon software engineering benchmark from Datacurve for measuring frontier coding agents on original tasks drawn from active open-source repositories.

Data verified

How BenchLM shows DeepSWE

BenchLM mirrors the public DeepSWE leaderboard JSON from Datacurve. The snapshot shows the best available mini-swe-agent configuration per model, while preserving 41 underlying effort-level rows in the source metadata.

DeepSWE evaluates coding agents on 113 original, long-horizon software engineering tasks across 91 repositories and 5 languages, using isolated task environments and program-based verifiers.

DeepSWE is display only on BenchLM. The public rows combine a model, mini-swe-agent harness, and reasoning-effort setting, so BenchLM does not use these scores as weighted model-only ranking inputs.

13 best-per-model rows113 tasks91 repositories5 languages41 effort rows in sourceDisplay only

Pass@1 on DeepSWE — July 7, 2026

BenchLM mirrors the published pass@1 view for DeepSWE. gpt-5-6-sol[max] leads the public snapshot at 72.7% , followed by claude-fable-5[max] (69.7%) and gpt-5-6-terra[max] (69.6%). BenchLM does not use these results to rank models overall.

13 modelsExternal benchmark mirrorsCurrentDisplay onlyUpdated July 7, 2026

Pass@1 table (13 models)

Score
1
72.7%
2
claude-fable-5[max]Anthropic · Closed
69.7%
3
69.6%
4
67.2%
5
gpt-5-5[xhigh]OpenAI · Closed
67.0%
6
claude-opus-4-8[max]Anthropic · Closed
59.0%
7
claude-sonnet-5[max]Anthropic · Closed
53.8%
8
gpt-5-4[xhigh]OpenAI · Closed
51.8%
9
glm-5-2[max]Z.AI · Open weight
43.8%
10
gemini-3-5-flash[medium]Google · Closed
37.4%
11
kimi-k2-7-codeMoonshot AI · Open weight
30.5%
12
claude-sonnet-4-6[high]Anthropic · Closed
29.9%
13
11.8%

The published DeepSWE snapshot is tightly clustered at the top: gpt-5-6-sol[max] sits at 72.7%, while the third row is only 3.1 points behind. The broader top-10 spread is 35.3 points, so the benchmark still separates strong models even when the leaders cluster.

13 models have been evaluated on DeepSWE. The benchmark falls in the External benchmark mirrors category. BenchLM tracks this category separately from its weighted global scoring system, so these results are best compared on the dedicated Korean benchmark views. DeepSWE is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About DeepSWE

Year

2026

Tasks

113 software engineering tasks across 91 repositories and 5 languages

Format

Pass@1 with confidence interval, cost, time, and token metadata

Difficulty

Long-horizon software engineering

DeepSWE includes original tasks with isolated environments and program-based verifiers. BenchLM mirrors the public DeepSWE leaderboard JSON as display-only, using the best available mini-swe-agent configuration per model and preserving cost, time, token, and effort-level source metadata. Each row combines a model, agent harness, and reasoning-effort setting rather than a pure model-only benchmark score.

BenchLM freshness & provenance

Version

DeepSWE 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

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.

FAQ

What does DeepSWE measure?

A long-horizon software engineering benchmark from Datacurve for measuring frontier coding agents on original tasks drawn from active open-source repositories.

Which model leads the published DeepSWE snapshot?

gpt-5-6-sol[max] currently leads the published DeepSWE snapshot with 72.7% pass@1. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on DeepSWE?

13 AI models are included in BenchLM's mirrored DeepSWE snapshot, based on the public leaderboard captured on July 7, 2026.

Last updated: July 7, 2026 · mirrored from the public benchmark leaderboard

The AI models change fast. We track them for you.

A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.