A task with its own rules.
Software engineering repository tasks designed as a refreshed SWE-bench style evaluation.
- Organisation
- SWE-Rebench
- Version
- Current / rolling
Loading benchmark header
Loading benchmark registry
Coding / Benchmark profile
Software engineering repository tasks designed as a refreshed SWE-bench style evaluation.
Observed results
13 ranked models · higher is better · labels show rank and score
| Model | Rank | Model ID | Provider | Score | Unit |
|---|---|---|---|---|---|
| Claude Opus 4.6 | #1 | claude-opus-4-6 | Anthropic | 65.3 | percent |
| GLM-5 | #2 | glm-5 | Z.AI | 62.8 | percent |
| GLM-5.1 | #3 | glm-5-1 | Z.AI | 62.7 | percent |
| DeepSeek V3.2 | #4 | deepseek-v3-2 | DeepSeek | 60.9 | percent |
| Claude Sonnet 4.6 | #5 | claude-sonnet-4-6 | Anthropic | 60.7 | percent |
| Qwen3.5 27B | #6 | qwen3-5-27b | Alibaba Cloud | 58.9 | percent |
| GLM-4.7 | #7 | glm-4-7 | Z.AI | 58.7 | percent |
| Kimi K2.5 | #8 | kimi-k2-5 | Moonshot AI | 58.5 | percent |
| GPT-5.3-Codex | #9 | gpt-5-3-codex | OpenAI | 58.2 | percent |
| Composer 2 | #10 | composer-2 | Cursor | 58 | percent |
| Qwen3.5-35B-A3B | #11 | qwen3-5-35b-a3b | Alibaba Cloud | 53.7 | percent |
| MiniMax M2.7 | #12 | minimax-m2-7 | MiniMax | 51.9 | percent |
| Gemma 4 31B | #13 | gemma-4-31b | 41.6 | percent |
One best compatible score per canonical product · higher is better
| Rank | Model | Weights | Evidence | Score |
|---|---|---|---|---|
| 01 | Claude Opus 4.6Anthropic | Closed weights | Source carrier | 65.3% |
| 02 | GLM-5Z.AI | Open weights | Source carrier | 62.8% |
| 03 | GLM-5.1Z.AI | Open weights | Source carrier | 62.7% |
| 04 | DeepSeek V3.2DeepSeek | Open weights | Source carrier | 60.9% |
| 05 | Claude Sonnet 4.6Anthropic | Closed weights | Source carrier | 60.7% |
| 06 | Qwen3.5 27BAlibaba Cloud | Open weights | Source carrier | 58.9% |
| 07 | GLM-4.7Z.AI | Open weights | Source carrier | 58.7% |
| 08 | Kimi K2.5Moonshot AI | Open weights | Source carrier | 58.5% |
| 09 | GPT-5.3-CodexOpenAI | Closed weights | Source carrier | 58.2% |
| 10 | Composer 2Cursor | Closed weights | Source carrier | 58% |
Each distinct published measurement is retained. Same-snapshot canonical and configuration projections appear once.
| Published model / configuration | Score | Evidence & protocol | Source & dates |
|---|---|---|---|
Exact BenchLM registry variant Claude Opus 4.6; bulk export does not retain a complete upstream harness configuration.Claude Opus 4.6Exact identitySource label without a registered configuration ID Canonical product: claude-opus-4-6 | 65.3% | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant GLM-5; bulk export does not retain a complete upstream harness configuration.GLM-5Exact identitySource label without a registered configuration ID Canonical product: glm-5 | 62.8% | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant GLM-5.1; bulk export does not retain a complete upstream harness configuration.GLM-5.1Exact identitySource label without a registered configuration ID Canonical product: glm-5-1 | 62.7% | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant DeepSeek V3.2; bulk export does not retain a complete upstream harness configuration.DeepSeek V3.2Exact identitySource label without a registered configuration ID Canonical product: deepseek-v3-2 | 60.9% | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant Claude Sonnet 4.6; bulk export does not retain a complete upstream harness configuration.Claude Sonnet 4.6Exact identitySource label without a registered configuration ID Canonical product: claude-sonnet-4-6 | 60.7% | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant Qwen3.5-27B; bulk export does not retain a complete upstream harness configuration.Qwen3.5 27BExact identitySource label without a registered configuration ID Canonical product: qwen3-5-27b | 58.9% | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant GLM-4.7; bulk export does not retain a complete upstream harness configuration.GLM-4.7Exact identitySource label without a registered configuration ID Canonical product: glm-4-7 | 58.7% | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant Kimi K2.5; bulk export does not retain a complete upstream harness configuration.Kimi K2.5Exact identitySource label without a registered configuration ID Canonical product: kimi-k2-5 | 58.5% | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant GPT-5.3 Codex; bulk export does not retain a complete upstream harness configuration.GPT-5.3-CodexExact identitySource label without a registered configuration ID Canonical product: gpt-5-3-codex | 58.2% | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant Composer 2; bulk export does not retain a complete upstream harness configuration.Composer 2Exact identitySource label without a registered configuration ID Canonical product: composer-2 | 58% | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
From result to context
Software engineering repository tasks designed as a refreshed SWE-bench style evaluation.
The summary shows one best compatible source result per canonical product. Versions, effort settings and execution systems remain attached to the underlying records.
Scores from different versions or harnesses may not be interchangeable. The published source rows preserve those distinctions and their original units. A source result is not automatically an input to a current index.
This catalogue entry preserves available source evidence. Current indices admit only their specifically reviewed tracks and configurations.
Contamination risk: Unknown. Lifecycle: Active.