Long context

Reasoning that requires holding a large input in view at once. A large advertised context window is not evidence of this; these benchmarks measure whether the window is usable.

Ordered by how many of these benchmarks place a model in their top 10, then by its best placing. Each column keeps its own order; nothing here is averaged.

Model	In top 10	Artificial Analysis LLM Leaderboard AA-LCR
Muse Spark 1.2 meta	1/1	#1 83.3%
Kimi K3 kimi	1/1	#2 82.7%
Gemini 3.7 Flash google	1/1	#3 81.0%
MiniMax-M3 minimax	1/1	#4 80.3%
Muse Glimmer meta	1/1	#5 80.0%
GPT-5.6 Terra openai	1/1	#6 79.7%
Gemini 3.5 Flash google	1/1	#7 79.7%
Gemini 3.1 Pro Preview google	1/1	#8 79.0%
Gemini 3.6 Flash google	1/1	#9 79.0%
Claude Opus 5 anthropic	1/1	#10 78.7%

A dash means the source does not cover that model, not that it scored zero. Models with no registry entry are excluded here because they cannot be joined across sources — they are still shown, flagged, on their own source's board.