SWE-smith
Agents repair software faults generated from real repositories. Harbor evaluates a 100-task sample from the larger training collection using tests for each fault.
The adapter comparison available November 19, 2026 reports 38% for Claude Sonnet 4 on Terminal-Bench and 0% for Claude 3 Haiku on Harbor.
- Made by
- SWE-bench team
- Released
- April 2025
- Kind
- Fixing real repositories
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Agentic
- Environment
- Terminal
- Items from
- Real work and use, Generated
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Agents
- Strongest model tested
- Claude Sonnet 4 #113 on the capability index
- Last model added
- May 2025
- Scores refreshed
- November 20th, 2026
Claude Sonnet 4 leads with 38%
Best score per model from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Table 3 lists SWE-bench Verified first in the benchmark record, so this is the Verified pass@1 resolve rate. Where a model ran with several settings or harnesses, we keep its best.
Source: The SWE-smith paper
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Sonnet 4 | 38% | Terminal-Bench adapter, mini-swe-agent | May 2025 | Official leaderboard |
| 2 | Claude 3 Haiku | 0% | Terminal-Bench adapter, mini-swe-agent | Mar 2024 | Official leaderboard |
2 models have held number one in the benchmark’s paper since its release in April 2025
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The SWE-smith paper
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official SWE-smith 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
- 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
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 18 months ago, in May 2025, for Claude Sonnet 4. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the benchmark’s paper (2 entries).
- Note Models scored Only 2 models we track.
- Warning Newest score The newest came 18 months ago, in May 2025, for Claude Sonnet 4.
- Note Frontier models None of the top 10 has a score. The strongest tested is Claude Sonnet 4 (#113).
- Pass Headroom The best is 38%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on github.com: 4 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.