# FrontierSWE V2 — AI model rankings

Engineering problems that would occupy a person for days: systems implementation, performance work, scientific computing and AI research, with up to twenty hours per task. Partial credit is awarded, because finishing one outright is still rare. Higher is better.

4 tracked models have a published FrontierSWE V2 score. Higher is better. Scores come from published lab reports and benchmark sources; recorded sources appear beside the scores.

## Ranking

| Rank | Model | Developer | Score | Source | Released |
| --- | --- | --- | --- | --- | --- |
| 1 | Gemini 4 Carbon | Google | 61.2% | Lab | Oct 28 2026 |
| 2 | Gemini 4 Argon | Google | 55% | Lab | Sep 30 2026 |
| 3 | Grok 4.7 | SpaceXSI | 29% | Lab | Sep 21 2026 |
| 4 | Grok 4.6 | SpaceXSI | 25.3% | Lab | Aug 12 2026 |


---

Canonical page: https://aireleasetracker.com/benchmark/frontierswe-v2
Site index: https://aireleasetracker.com/llms.txt
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.