GraphWalks leaderboard
As of November 14, 2026, among the results listed here, Google Gemini 4 Carbon has the highest reported GraphWalks score, 96.2% (256k to 1M, BFS (F1)), published by Google on October 28, 2026, ahead of Google Gemini 4 Argon at 84.2%. 2 models have a GraphWalks result in our records.
Scores as the model makers published them, not re-run by us; each row links to its announcement.
Best reported score
96.2%
Reported by Google, October 28, 2026 · 256k to 1M, BFS (F1)
2 models ranked · 1 maker
| Rank | Model | Score | Setting | Reported by | Date |
|---|---|---|---|---|---|
| 1 | Gemini 4 Carbon | 96.2% | 256k to 1M, BFS (F1) | October 28, 2026 · read from the maker's chart | |
| 2 | Gemini 4 Argon | 84.2% | 256k to 1M, BFS (F1) | October 13, 2026 (model release) |
Other reported runs
| Model | Score | Setting | Reported by | Date |
|---|---|---|---|---|
| Gemini 4 Argon | 99.7% | Up to 128k, BFS (F1) | October 13, 2026 (model release) |
How much to trust these numbers
- Source
- Reported by the model makers themselves. Not re-run by LLMBenchmark or anyone independent.
- Settings
- All ranked results use the same reported setting.
- Spread
- 96.2% to 84.2% across 2 models.
- Freshness
- Newest result published October 28, 2026; oldest October 13, 2026.
- Charts
- Some values were read from charts in the announcements. Two independent readings had to match exactly.
What GraphWalks measures
GraphWalks tests multi-hop reasoning over long contexts using graphs represented as edge lists; the search results do not specify what its numerical score means. Source: openai/graphwalks