Monthly-SWEBench
Coding agents resolve 100 fresh GitHub tasks each month, half bug fixes and half features, from newly merged pull requests. Harbor verifiers score pass@1.
Each monthly snapshot is a new task set, so scores from different months do not compare. The 2026-06 snapshot rated 19 models.
- Level
- Expert Specialists with years of training, often over hours of work
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Code A program or patch run against tests.
GPT-5.5 leads with 76% among models released by Jun 2026
Best score per model from the benchmark's own leaderboard, read on 2 Nov 2026. Where a model ran with several settings or harnesses, we keep its best.
The newest model with a score here came out in Jun 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6 Astra
- Claude Opus 5.5
- GPT-6.1 Terra
- GPT-6.1 Sol
- and 14 more
- 1 GPT-5.5 high 76%
- 2 Claude Opus 4.8 xhigh 69%
- 3 GLM-5.2 max 65%
- 4
MiniMax-M3 adaptive 58% - 5
DeepSeek-V4-Pro high 57% - 6
Seed2.1 Pro high 53% - 7
Qwen3.7-Max thinking 51% - 8 Qwen3.7-Plus thinking 47%
- 9 DeepSeek-V4-Flash high 45%
- 10
Tencent Hy3 preview high 38% - 11
Gemini 3.5 Flash high 29% - 12
Step 3.7 Flash high 22%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5.5 | 76% | high, OpenHands | Apr 2026 | Official leaderboard |
| 2 | Claude Opus 4.8 | 69% | xhigh, OpenHands | May 2026 | Official leaderboard |
| 3 | GLM-5.2 | 65% | max, OpenHands | Jun 2026 | Official leaderboard |
| 4 | MiniMax-M3 | 58% | adaptive, OpenHands | Jun 2026 | Official leaderboard |
| 5 | DeepSeek-V4-Pro | 57% | high, OpenHands | Apr 2026 | Official leaderboard |
| 6 | Seed2.1 Pro | 53% | high, OpenHands | Jun 2026 | Official leaderboard |
| 7 | Qwen3.7-Max | 51% | thinking, OpenHands | May 2026 | Official leaderboard |
| 8 | Qwen3.7-Plus | 47% | thinking, OpenHands | Jun 2026 | Official leaderboard |
| 9 | DeepSeek-V4-Flash | 45% | high, OpenHands | Apr 2026 | Official leaderboard |
| 10 | Tencent Hy3 preview | 38% | high, OpenHands | Apr 2026 | Official leaderboard |
| 11 | Gemini 3.5 Flash | 29% | high, OpenHands | May 2026 | Official leaderboard |
| 12 | Step 3.7 Flash | 22% | high, OpenHands | May 2026 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
No lab model card reports it yet
We read the headline results of 479 launch posts from 51 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%
- SWE-bench Multilingual In use 300 GitHub-issue tasks across nine programming languages in SWE-bench format. Patch graded by repository tests. Claude Opus 5.5 93.9%
- 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%
- 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