FrontierSWE
Frontier-difficulty engineering projects scored on implementation, performance and research quality.
Agent Index weight
5%
in the Agentic coding pillar
Models tested
25
from the benchmark’s leaderboard and reports
Results
| # | Model | Score | Normalised | Harness | Cost/task | Date |
|---|---|---|---|---|---|---|
| 1 | Claude Fable 5.2 Supported Anthropic | 69.9% | proximus | $168.78 | — | |
| 2 | GPT-6 Astra Supported OpenAI | 65.5% | proximus | $1029.65 | — | |
| 3 | Claude Opus 5.5 Supported Anthropic | 62.3% | proximus | $98.87 | — | |
| 4 | Claude Sonnet 5.5 Estimated Anthropic | 61.9% | proximus | $110.45 | — | |
| 5 | Gemini 4 Carbon Supported Google | 61.2% | proximus | $61.93 | — | |
| 6 | Claude Fable 5.1 Supported Anthropic | 56.3% | proximus | $138.55 | — | |
| 7 | Gemini 4 Argon Supported Google | 55.0% | proximus | $129.36 | — | |
| 8 | Gemini 4 Hydrogen Estimated Google | 53.1% | proximus | $61.79 | — | |
| 9 | Claude Opus 5 Supported Anthropic | 52.0% | proximus | $196.71 | — | |
| 10 | Claude Fable 5 Supported Anthropic | 47.0% | proximus | $301.28 | — | |
| 11 | Claude Haiku 5.5 Estimated Anthropic | 43.8% | proximus | $20.55 | — | |
| 12 | GPT-5.6 Sol Supported OpenAI | 32.2% | proximus | $179.64 | — | |
| 13 | GLM-5.3 Supported Z.ai (Zhipu) | 30.2% | proximus | $97.22 | — | |
| 14 | Grok 4.7 Estimated xAI | 29.5% | proximus | $318.77 | — | |
| 15 | Kimi K3 Supported Moonshot AI | 25.9% | proximus | $109.71 | — | |
| 16 | Muse Spark 1.3 Estimated Meta | 25.8% | proximus | $243.34 | — | |
| 17 | Grok 4.6 Supported xAI | 25.3% | proximus | $243.43 | — | |
| 18 | Inkling 2 Small Estimated thinkingmachines | 25.1% | proximus | $11.84 | — | |
| 19 | Gemini 3.7 Flash Estimated Google | 20.3% | proximus | $34.14 | — | |
| 20 | Gemini 3.8 Flash Supported Google | 19.6% | proximus | $38.75 | — | |
| 21 | GLM-5.3-Flash Supported Z.ai (Zhipu) | 18.1% | proximus | $11.03 | — | |
| 22 | Qwen3.8 Max 0902 Alibaba (Qwen) | 17.8% | proximus | $51.27 | — | |
| 23 | Qwen3.8 Max Preview Estimated Alibaba (Qwen) | 15.8% | proximus | $55.14 | — | |
| 24 | Muse Spark 1.2 Estimated Meta | 12.0% | proximus | $27.81 | — | |
| 25 | Inkling Estimated thinkingmachines | 4.1% | proximus | $9.15 | — |
For models without a FrontierSWE result, the index estimates one from Epoch’s Capabilities Index using a logistic fit on 23 models (residual SD 0.32 on the logit scale). Estimates are labelled and widen the model’s range.