BenchmarkActivecategory · codingfamily · swe-bench · variant Verified

SWE-bench Verified

swebench.com

resolve real GitHub issues (500 human-validated instances)

data quality57

Updated 6 h ago · first seen 11 Sept 2026

Metric: resolved · % ↑
Current results: 158
Models: 82
Current leader: claude-35-sonnet 50.8%

Filters

Comparability group

Trust level

Views

Score history · gpt-4o 8 rows

gpt-4o

21.62%date=2025-07-20 · board=Verified · system=mini-SWE-agent · model_tag=gpt-4o-2024112020 Jul 2025
38.8%date=2024-10-28 · board=Verified · system=Agentless-1.5 · model_tag=gpt-4o-2024-05-1328 Oct 2024
27%date=2024-10-16 · board=Verified · system=EPAM AI/Run Developer Agent · model_tag=gpt-4o-2024-08-0616 Oct 2024
24%date=2024-08-20 · board=Verified · system=EPAM AI/Run Developer Agent · model_tag=gpt-4o-2024-08-0620 Aug 2024
23.2%date=2024-07-28 · board=Verified · system=SWE-agent · model_tag=gpt-4o-2024-05-1328 Jul 2024
38.4%date=2024-06-28 · board=Verified · system=AutoCodeRover · model_tag=gpt-4o-2024-05-1328 Jun 2024
26.2%date=2024-06-15 · board=Verified · system=AppMap Navie · model_tag=gpt-4o-2024-05-1315 Jun 2024
32.6%date=2024-06-12 · board=Verified · system=MASAI · model_tag=gpt-4o-2024-08-0612 Jun 2024

Back to the leaderboard

Frontier over time · resolved · board=Verified · system=Agentless-1.5

50.8%claude-35-sonnet Anthropic Community2 Dec 2024
38.8%gpt-4o OpenAI Community28 Oct 2024

Includes closed rows (history). A point is emitted whenever a result beats every earlier result of the same group, ordered by evaluated_at when the source publishes it, else observed_at.

Leaderboard 2 models

Select models with +, then Compare.

Leaderboard
#	Model	Score	Trust	Configuration	vs leader	Evaluated	Source	Actions
1	claude-35-sonnetClosedAnthropic · Claude 35	50.8%	Community	group defaults	leader	2 Dec 2024	swebench.comT2	History
2	gpt-4oClosedOpenAI · GPT 4	38.8%	Community	group defaults	Partially comparable-12.0 pt	28 Oct 2024	swebench.comT2	History

2 results

One row per canonical model — its best current row inside this comparability group (effort variants are folded into the model). Bars are relative to the page's best score. “vs leader” reads comparability: partially comparable = same task, conditions differ (reasoning effort, temperature, judge). Rules →

Definition

Task: Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 16 h agomedium
Metric: Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 16 h agomedium
Metric range: Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 6 h agomedium
Variant: Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 6 h agomedium
Harness: Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 6 h agomedium
Comparability note: Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 6 h agomedium
Known limitations: Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 16 h agomedium
Paper: Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 16 h agomedium
Website: swebench.com
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 16 h agomedium

Active group

resolved · board=Verified · system=Agentless-1.5

2 models · 2 current rows

Comparability

Comparable same task and conditions · Partially comparable same task, conditions differ (effort, temperature, judge) · Not comparable different variant or metric

Also known as

SWE-bench, SWE-bench Verified

slug swe-bench-verified · bench_01M293SPEGA1XMKH0SMTFTCK2R

Rows are grouped by comparability group = canonical metric × config_key (hash of the task-defining configuration keys: variant, evaluator, harness, shots, pass regime…). A leaderboard shows one row per canonical model: its best current row inside the group. Reasoning effort, temperature or judge differences keep rows in the same group but mark them partially comparable. delta_rank compares with the ranking built from the closed (previous) rows of the same group.