SWE-sweep
The official leaderboard hasn’t scored a model released after MiniMax-M3.1-Flash (October 2026). Labs report their own numbers for 3 newer models, such as Gemini 4 Hydrogen at 13.5%.
Agents get a real repository with no hint of bug type or location and must find and repair as many bugs as they can. Score is the share of bugs resolved.
100 repositories with 4.1k bugs, run through Harbor with mini-SWE-agent. Authors include the SWE-bench team.
- Released
- October 2026
- Kind
- Fixing real repositories
- Level
- Research frontier
- Scored
- Checked automatically
- Answers
- Code
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Agentic
- Environment
- Terminal
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Agents
- Strongest model tested
-
Gemini 4 Carbon #3 on the capability index
- Last in a launch post
- November 2026
- Last model added
- November 2026
- Scores refreshed
- November 19th, 2026
GPT-6 Astra leads with 8.90%
Best score per model from the benchmark's own leaderboard, read on November 19th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart.
Gemini 4 Hydrogen leads with 13.5%, claims included
Best score per model from every source, including labs’ own numbers and claims Epoch AI collected from reports and papers. Labs pick their own settings, so a claim can beat an independent run of the same model. Striped bars are claims, and dotted bars are reruns by Epoch AI or another board.
- 1 GPT-6 Astra 8.90%
- 2 GPT-5.6 Sol xhigh 4.70%
- 3 Claude Opus 5.5 xhigh 3.60%
- 4 Claude Fable 5.1 2.90%
- 5 GPT-5.6 Luna xhigh 2.50%
- 6
DeepSeek V4.1 Flash max 1.60%
- 7 GPT-5.6 Terra xhigh 1.50%
- 8 Claude Opus 5 xhigh 1.30%
- 9 GLM-5.3-Flash max 0.70%
- 10
MiniMax-M3.1-Flash max 0.70%
- 11 Kimi K3 0.60%
- 12 GPT-5.4 Mini high 0.50%
- 13
Gemini 3.5 Flash-Lite 0.10%
Source: Official SWE-sweep leaderboard
- 13.5
Gemini 4 Hydrogen
- 12.8
Gemini 4 Neon
- 9.60
Gemini 4 Carbon
- 8.90 GPT-6 Astra
- 4.70 GPT-5.6 Sol
- 3.60 Claude Opus 5.5
- 2.90 Claude Fable 5.1
- 2.50 GPT-5.6 Luna
- 1.60
DeepSeek V4.1 Flash
- 1.50 GPT-5.6 Terra
- 1.30 Claude Opus 5
- 0.70 GLM-5.3-Flash
- 0.70
MiniMax-M3.1-Flash
- 0.60 Kimi K3
- 0.50 GPT-5.4 Mini
- 0.10
Gemini 3.5 Flash-Lite
- 1
Gemini 4 Hydrogen 13.5%
- 2
Gemini 4 Neon 12.8%
- 3
Gemini 4 Carbon 9.60%
- 4 GPT-6 Astra 8.90%
- 5 GPT-5.6 Sol xhigh 4.70%
- 6 Claude Opus 5.5 xhigh 3.60%
- 7 Claude Fable 5.1 2.90%
- 8 GPT-5.6 Luna xhigh 2.50%
- 9
DeepSeek V4.1 Flash max 1.60%
- 10 GPT-5.6 Terra xhigh 1.50%
- 11 Claude Opus 5 xhigh 1.30%
- 12 GLM-5.3-Flash max 0.70%
- 13
MiniMax-M3.1-Flash max 0.70%
- 14 Kimi K3 0.60%
- 15 GPT-5.4 Mini high 0.50%
- 16
Gemini 3.5 Flash-Lite 0.10%
Sources: Labs’ model cards and official SWE-sweep leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-6 Astra | 8.90% | mini-SWE-agent | Sep 2026 | Official leaderboard |
| 2 | GPT-5.6 Sol | 4.70% | xhigh, mini-SWE-agent | Jul 2026 | Official leaderboard |
| 3 | Claude Opus 5.5 | 3.60% | xhigh, mini-SWE-agent | Sep 2026 | Official leaderboard |
| 4 | Claude Fable 5.1 | 2.90% | mini-SWE-agent | Sep 2026 | Official leaderboard |
| 5 | GPT-5.6 Luna | 2.50% | xhigh, mini-SWE-agent | Jul 2026 | Official leaderboard |
| 6 | | 1.60% | max, mini-SWE-agent | Sep 2026 | Official leaderboard |
| 7 | GPT-5.6 Terra | 1.50% | xhigh, mini-SWE-agent | Jul 2026 | Official leaderboard |
| 8 | Claude Opus 5 | 1.30% | xhigh, mini-SWE-agent | Jul 2026 | Official leaderboard |
| 9 | GLM-5.3-Flash | 0.70% | max, mini-SWE-agent | Aug 2026 | Official leaderboard |
| 10 | | 0.70% | max, mini-SWE-agent | Oct 2026 | Official leaderboard |
| 11 | Kimi K3 | 0.60% | mini-SWE-agent | Jul 2026 | Official leaderboard |
| 12 | GPT-5.4 Mini | 0.50% | high, mini-SWE-agent | Mar 2026 | Official leaderboard |
| 13 | | 0.10% | mini-SWE-agent | Jul 2026 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | 13.5% | Nov 2026 | Lab model card | ||
| 2 | 12.8% | Nov 2026 | Lab model card | ||
| 3 | 9.60% | Oct 2026 | Lab model card | ||
| 4 | GPT-6 Astra | 8.90% | mini-SWE-agent | Sep 2026 | Official leaderboard |
| 5 | GPT-5.6 Sol | 4.70% | xhigh, mini-SWE-agent | Jul 2026 | Official leaderboard |
| 6 | Claude Opus 5.5 | 3.60% | xhigh, mini-SWE-agent | Sep 2026 | Official leaderboard |
| 7 | Claude Fable 5.1 | 2.90% | mini-SWE-agent | Sep 2026 | Official leaderboard |
| 8 | GPT-5.6 Luna | 2.50% | xhigh, mini-SWE-agent | Jul 2026 | Official leaderboard |
| 9 | 1.60% | max, mini-SWE-agent | Sep 2026 | Official leaderboard | |
| 10 | GPT-5.6 Terra | 1.50% | xhigh, mini-SWE-agent | Jul 2026 | Official leaderboard |
| 11 | Claude Opus 5 | 1.30% | xhigh, mini-SWE-agent | Jul 2026 | Official leaderboard |
| 12 | GLM-5.3-Flash | 0.70% | max, mini-SWE-agent | Aug 2026 | Official leaderboard |
| 13 | 0.70% | max, mini-SWE-agent | Oct 2026 | Official leaderboard | |
| 14 | Kimi K3 | 0.60% | mini-SWE-agent | Jul 2026 | Official leaderboard |
| 15 | GPT-5.4 Mini | 0.50% | high, mini-SWE-agent | Mar 2026 | Official leaderboard |
| 16 | 0.10% | mini-SWE-agent | Jul 2026 | Official leaderboard |
Labs report scores for 3 models in their cards. Switch the scores above to rank them together.
Pareto: bugs resolved against turns
The Pareto tab with turns on the x axis: each point is one model, and the line marks the best result for a given number of turns per repository. The line joins the runs that no other run beats on both measures. We redrew this chart from the numbers on the official leaderboard.
| Model | Setting | Bugs resolved | Turns per repository |
|---|---|---|---|
| GPT-6 Astra | mini-SWE-agent | 8.9% | 113 |
| GPT-5.6 Sol | xhigh, mini-SWE-agent | 4.7% | 233 |
| Claude Opus 5.5 | xhigh, mini-SWE-agent | 3.6% | 266 |
| Claude Fable 5.1 | mini-SWE-agent | 2.9% | 319 |
| GPT-5.6 Luna | xhigh, mini-SWE-agent | 2.5% | 204 |
| GPT-5.6 Terra | xhigh, mini-SWE-agent | 1.5% | 76 |
| GPT-5.6 Luna | high, mini-SWE-agent | 1.4% | 75 |
| Claude Opus 5 | xhigh, mini-SWE-agent | 1.3% | 323 |
| high, mini-SWE-agent | 0.9% | 347 | |
| max, mini-SWE-agent | 0.7% | 363 | |
| GLM-5.3-Flash | high, mini-SWE-agent | 0.6% | 332 |
| Kimi K3 | mini-SWE-agent | 0.6% | 337 |
| GPT-5.6 Luna | mini-SWE-agent | 0.5% | 22 |
| GPT-5.4 Mini | high, mini-SWE-agent | 0.5% | 75 |
| GPT-5.4 Mini | mini-SWE-agent | 0.2% | 13 |
| mini-SWE-agent | 0.1% | 34 |
The best score, 8.90%, costs $35 a task
Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official SWE-sweep leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| GPT-6 Astra | mini-SWE-agent | 8.90% | $35 | 119,500 | |
| GPT-5.6 Sol | xhigh | mini-SWE-agent | 4.70% | $72 | 104,800 |
| Claude Opus 5.5 | xhigh | mini-SWE-agent | 3.60% | $22 | 112,700 |
| Claude Fable 5.1 | mini-SWE-agent | 2.90% | $39 | 165,000 | |
| GPT-5.6 Luna | xhigh | mini-SWE-agent | 2.50% | $2.24 | 61,200 |
| max | mini-SWE-agent | 1.60% | $1.78 | ||
| GPT-5.6 Terra | xhigh | mini-SWE-agent | 1.50% | $3.57 | 46,600 |
| GPT-5.6 Luna | high | mini-SWE-agent | 1.40% | $0.28 | 20,300 |
| Claude Opus 5 | xhigh | mini-SWE-agent | 1.30% | $54 | 192,700 |
| high | mini-SWE-agent | 0.90% | $0.97 | 241,100 | |
| GLM-5.3-Flash | max | mini-SWE-agent | 0.70% | $2.89 | |
| max | mini-SWE-agent | 0.70% | $1.56 | 204,800 | |
| Kimi K3 | mini-SWE-agent | 0.60% | $25 | 152,600 | |
| GLM-5.3-Flash | high | mini-SWE-agent | 0.60% | $1.81 | 115,600 |
| GPT-5.4 Mini | high | mini-SWE-agent | 0.50% | $1.22 | 40,500 |
| GPT-5.6 Luna | mini-SWE-agent | 0.50% | $0.04 | 4,500 | |
| GPT-5.4 Mini | mini-SWE-agent | 0.20% | $0.05 | 2,100 | |
| mini-SWE-agent | 0.10% | $0.06 | 5,200 |
Number one over time 3 models have held number one with claims included since its release in October 2026
Lab claims count from the day the card came out, independent runs from the model’s release. We draw one row each for the benchmark’s own leaderboard and what labs claim in their cards.
Sources: Official SWE-sweep leaderboard and labs’ model cards
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Sources: Official SWE-sweep leaderboard and labs’ model cards
One lab put it in a launch post in the last six months
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Nov 18, 2026 | 12.8 | SWE-sweep (Mini-SWE harness). 39.0% with the provider harness, Google Antigravity | |
| Nov 12, 2026 | 13.5 | SWE-sweep | |
| Oct 28, 2026 | 9.6 | SWE-sweep |
2 system cards report it, from 1 lab
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| Nov 18, 2026 | | 12.8 | SWE-sweep (Mini-SWE harness). 39.0% with the provider harness, Google Antigravity (results table, p.4) | Capabilities |
| Nov 10, 2026 | | 9.6 | SWE-sweep (results table) | Capabilities |
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
All 11 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 5 pass
- Pass Independent runs Scores from the official leaderboard (13 entries), launch posts (3 scores) and system cards (2 scores).
- Pass Models scored 16 models we track.
- Pass Newest score The newest is from November 2026, for Gemini 4 Neon.
- Pass Frontier models 4 of the top 10 have a score, led by Gemini 4 Carbon (#3).
- Pass Headroom The best is 13.5%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on swesweep.com: 18 rows for models we track at the last read.
- Pass Last read November 19th, 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.