SWE-Rebench
Claude Opus 4.6 leads the SWE-Rebench leaderboard on BenchLM's October 2026 update with 65.3%, ahead of GLM-5 (62.8%) and GLM-5.1 (62.7%), across 13 models.
A continuously updated software engineering benchmark by Nebius using fresh GitHub issues to avoid contamination. Models are evaluated 5 times per problem under a fixed ReAct scaffolding; the Resolved Rate (best pass@1) is reported.
Top models on SWE-Rebench — October 29, 2026
As of October 29, 2026, Claude Opus 4.6 leads the SWE-Rebench leaderboard with 65.3% , followed by GLM-5 (62.8%) and GLM-5.1 (62.7%).
Claude Opus 4.6
Anthropic
GLM-5
Z.AI
GLM-5.1
Z.AI
13 modelsCoding5% of Coding reference weightCurrentUpdated October 29, 2026
Leaderboard (13 models)
| Rank | Model / configuration | Score | Parameters (B) | Open / closed |
|---|---|---|---|---|
| 1 | Claude Opus 4.6Anthropic | 65.3% | Not reported | Closed |
| 2 | GLM-5Z.AI | 62.8% | Not reported | Open |
| 3 | GLM-5.1Z.AI | 62.7% | Not reported | Open |
| 4 | DeepSeek V3.2DeepSeek | 60.9% | Not reported | Open |
| 5 | Claude Sonnet 4.6Anthropic | 60.7% | Not reported | Closed |
| 6 | Qwen3.5-27BAlibaba | 58.9% | Not reported | Open |
| 7 | GLM-4.7Z.AI | 58.7% | Not reported | Open |
| 8 | Kimi K2.5Moonshot AI | 58.5% | Not reported | Open |
| 9 | GPT-5.3 CodexOpenAI | 58.2% | Not reported | Closed |
| 10 | Composer 2Cursor | 58% | Not reported | Closed |
| 11 | Qwen3.5-35B-A3BAlibaba | 53.7% | Not reported | Open |
| 12 | MiniMax M2.7MiniMax | 51.9% | Not reported | Open |
| 13 | Gemma 4 31BGoogle | 41.6% | Not reported | Open |
According to BenchLM.ai, Claude Opus 4.6 leads the SWE-Rebench benchmark with a score of 65.3%, followed by GLM-5 (62.8%) and GLM-5.1 (62.7%). The top models are clustered within 2.6 points, suggesting this benchmark is nearing saturation for frontier models.
13 models have been evaluated on SWE-Rebench. The benchmark falls in the Coding category. BenchAlign v5.8 gives SWE-Rebench 5% of the Coding reference weight, so it moves the Coding leaderboard and the overall ranking. Reference weights are relative weights in the calibrated model, not fixed shares of a score.
About SWE-Rebench
Year
2026
Tasks
Fresh GitHub issues (rolling window)
Format
Code patch generation
Difficulty
Professional software engineering
SWE-Rebench uses a rolling window of fresh problems from real GitHub repositories, sourced after each model's release date to prevent contamination. Each model runs 5 times with a standardized 128K-context ReAct scaffold. Unlike SWE-bench Verified (2023 problems), scores reflect consistent, up-to-date difficulty.
Freshness and provenance
Version
Rolling 2026 window
Refresh cadence
Rolling
Staleness state
Current
Question availability
Rolling public issues
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does SWE-Rebench measure?
A continuously updated software engineering benchmark by Nebius using fresh GitHub issues to avoid contamination. Models are evaluated 5 times per problem under a fixed ReAct scaffolding; the Resolved Rate (best pass@1) is reported.
Which model scores highest on SWE-Rebench?
Claude Opus 4.6 by Anthropic currently leads with a score of 65.3% on SWE-Rebench.
How many models are evaluated on SWE-Rebench?
13 AI models have published results on SWE-Rebench in the BenchLM catalog.
Compare top models on SWE-Rebench
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 6,100+ subscribers.
One email each week. Unsubscribe anytime.