Benchmark

Graphwalks BFS 1M

GraphWalks BFS variant evaluated on 1M-token contexts.

Modality
text
Categories
long_context, reasoning, spatial_reasoning
Openness
unknown
Source
llm_stats
Reported scores
3

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
GPT-5.6 LunaOpenAI0.5122026-07-09evidence
GPT-5.6 SolOpenAI0.7712026-07-09evidence
GPT-5.6 TerraOpenAI0.7122026-07-09evidence

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.