SWE-Race
Agents fix concurrency and asynchronous lifecycle bugs in Python projects. The benchmark has 95 public and 93 private tasks. Harbor distributes 94 public tasks.
On November 19, 2026, GLM-5.3 Flash had the highest pass@1 estimate at 81.9%. Its interval overlapped those of GPT-5.6 Luna and DeepSeek V4 Flash.
- Made by
- Evaligo Labs
- Released
- October 2026
- Kind
- Fixing real repositories
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- Public, plus a private test set
- Measures
- Capability
- Language
- English
- Interaction
- Agentic
- Environment
- Terminal
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- A host
- In views
- Agents
- Strongest model tested
- GPT-5.6 Luna #36 on the capability index
- Last model added
- August 2026
- Scores refreshed
- November 20th, 2026
GLM-5.3-Flash leads with 81.9% among models released by August 2026
Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.
The newest model with a score here came out in August 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
Source: Official SWE-Race leaderboard
| # | Model | Score ± | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | GLM-5.3-Flash | 81.9% 77 to 86.3 | medium, 100 steps, offline, BenchGen | Aug 2026 | Oct 2026 | Official leaderboard |
| 2 | GPT-5.6 Luna | 81.3% 76.4 to 85.7 | medium, 100 steps, offline, BenchGen | Jul 2026 | Oct 2026 | Official leaderboard |
| 3 | | 72.1% 66.1 to 77.6 | medium, 100 steps, offline, BenchGen | Apr 2026 | Oct 2026 | Official leaderboard |
Rankings by part
We read 4 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Hard, Public and Private. GLM-5.3-Flash leads 3 of them, and GPT-5.6 Luna leads the other one. Arrows show how far a model moved from its overall rank among the models we track.
Hard
3 models we track have a score here.
- 1 GLM-5.3-Flash 49.9%
- 2 GPT-5.6 Luna 44.7%
- 3
DeepSeek-V4-Flash 23.2%
Public
3 models we track have a score here.
- 1 GPT-5.6 Luna ↑1 82.9%
- 2 GLM-5.3-Flash ↓1 80.2%
- 3
DeepSeek-V4-Flash 69.2%
Private
3 models we track have a score here.
- 1 GLM-5.3-Flash 83.7%
- 2 GPT-5.6 Luna 79.8%
- 3
DeepSeek-V4-Flash 75%
Composites
3 models we track have a score here.
- 1 GLM-5.3-Flash 68%
- 2 GPT-5.6 Luna 66.9%
- 3
DeepSeek-V4-Flash 56.5%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official SWE-Race leaderboard
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-Race 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
All 9 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access Public tasks, plus a private test set.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (3 entries).
- Note Models scored Only 3 models we track.
- Pass Newest score The newest is from August 2026, for GLM-5.3-Flash.
- Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.6 Luna (#36).
- Pass Headroom The best is 81.9%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on labs.evaligo.com: 3 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.