BenchmarkActivecategory · codingfamily · swe-bench · variant Multimodal

SWE-bench Multimodal

swebench.com/multimodal

resolve visual JavaScript issues (screenshots + code)

data quality57

Updated 6 h ago · first seen 11 Sept 2026

Metric: resolved · % ↑
Current results: 22
Models: 10
Current leader: Claude Sonnet 3.5 12.2%

Filters

Comparability group

Trust level

Views

Score history · Claude Sonnet 3.5 2 rows

Not enough history to chart — 2 observations, all dated 6 Oct 2024. Rows under different configurations count separately; the list below shows each one.

11.99%date=2024-10-06 · board=Multimodal · system=SWE-agent JavaScript · submission=20241006_SWE-agent_JS_claude3.56 Oct 2024
12.19%date=2024-10-06 · board=Multimodal · system=SWE-agent · submission=20241006_SWE-agent_claude3.56 Oct 2024

Back to the leaderboard

Frontier over time · resolved · board=Multimodal · system=SWE-agent

1 leader change recorded, all dated 6 Oct 2024 — the frontier line needs at least two distinct dates. The corpus is young: every result was first observed on the same day, so leader changes will separate in time as sources are re-crawled.

12.2%Claude Sonnet 3.5 Anthropic Official board6 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 Sonnet 3.5Anthropic · Claude	12.2%	Official board	group defaults	leader	6 Oct 2024	swebench.comT2	History
2	gpt-4oClosedOpenAI · GPT 4	12.0%	Official board	group defaults	Comparable-0.20 pt	6 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
Website: swebench.com/multimodal
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 16 h agomedium

Active group

resolved · board=Multimodal · system=SWE-agent

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 MM, SWE-bench Multimodal

slug swe-bench-multimodal · bench_01M293SPGC8HWGJ1NKFWQ04G29

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.