Graphwalks BFS <128k
Progress Over Time
Interactive timeline showing model performance evolution on Graphwalks BFS <128k
Graphwalks BFS <128k Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Google | — | — | — | ||
| 2 |  OpenAI | — | 400K | $1.75 / $14.00 | ||
| 3 | OpenAI | — | 1.0M | $2.50 / $15.00 | ||
| 4 | OpenAI | — | — | — | ||
| 5 | OpenAI | — | 400K | $0.75 / $4.50 | ||
| 6 | OpenAI | — | 400K | $0.20 / $1.25 | ||
| 7 | OpenAI | — | — | — | ||
| 8 |  ByteDance | — | 256K | $0.10 / $0.40 | ||
| 9 | OpenAI | — | 1.0M | $2.00 / $8.00 | ||
| 9 | OpenAI | — | 1.0M | $0.40 / $1.60 | ||
| 11 | OpenAI | — | — | — | ||
| 12 | OpenAI | — | 128K | $2.50 / $10.00 | ||
| 13 | OpenAI | — | 1.0M | $0.10 / $0.40 |
What is Graphwalks BFS <128k?
A graph reasoning benchmark that evaluates language models' ability to perform breadth-first search (BFS) operations on graphs with context length under 128k tokens, returning nodes reachable at specified depths.
Graphwalks BFS <128k is a text benchmark evaluating models on reasoning and spatial reasoning tasks. LLM Stats tracks 13 models on this benchmark, scored on a 0–1 scale. The current average is 0.7, with the leader at 1.0.
Compare leaders on the best AI for reasoning and best AI for spatial reasoning leaderboards.
Current leaders
Gemini 4 Argon from Google currently leads the Graphwalks BFS <128k leaderboard with a score of 0.997 across 13 evaluated AI models.
FAQ
Common questions about the Graphwalks BFS <128k benchmark and leaderboard.