Benchmark
FrontierSWE Benchmark
What is FrontierSWE?
FrontierSWE measures whether an agent can complete open-ended technical projects at the scale of hours to tens of hours, spanning systems optimization…
- Modality
- text
- Evaluates
- agents, code
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 16
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/frontierswe?top_n=500
FrontierSWE results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Claude Fable 5 | Anthropic | 0.9 | 2026-06-09 | evidence |
| Claude Opus 4.6 | Anthropic | 0.56 | 2026-02-05 | evidence |
| Claude Opus 4.7 | Anthropic | 0.63 | 2026-04-16 | evidence |
| Claude Opus 4.8 | Anthropic | 0.75 | 2026-05-28 | evidence |
| DeepSeek-V4-Pro-Max | DeepSeek | 0.29 | 2026-04-23 | evidence |
| Gemini 3.1 Pro | 0.4 | 2026-02-19 | evidence | |
| GLM-5.1 | Z.ai | 0.31 | 2026-04-07 | evidence |
| GLM-5.2 | Z.ai | 0.74 | 2026-06-16 | evidence |
| GLM-5.3 | Z.ai | 0.781 | 2026-08-14 | evidence |
| GPT-5.4 | OpenAI | 0.54 | 2026-03-05 | evidence |
| GPT-5.5 | OpenAI | 0.73 | 2026-04-23 | evidence |
| Kimi K2.5 | Moonshot AI | 0.26 | 2026-01-27 | evidence |
| Kimi K2.6 | Moonshot AI | 0.27 | 2026-04-20 | evidence |
| Kimi K3 | Moonshot AI | 0.812 | 2026-07-16 | evidence |
| Qwen3.6 Plus | Qwen | 0.22 | 2026-04-02 | evidence |
| Qwen3.8 Max | Qwen | 0.735 | 2026-08-02 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.