Reasoning benchmark
AI-Needle leaderboard
Every model the catalog carries a published AI-Needle value for, ranked by that value.
CategoryReasoning
MeasureNeedle-in-a-haystack recall
TasksLong-context retrieval
DifficultyLong-context memory
Published byQwen3.6 launch benchmarks
A long-context retrieval benchmark that measures whether a model can recover relevant information embedded deep inside very long contexts.
AI-Needle ranking
4 models with a published AI-Needle value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Needle-in-a-haystack recall |
|---|---|---|---|
| 1 |  Claude Opus 4.5 | Anthropic | 74 |
| 2 |  Qwen3.5 397B | Alibaba | 68.7 |
| 3 | Qwen3.6 Plus | Alibaba | 68.3 |
| 4 |  GLM-5 | Z.AI | 63.3 |
Evidence key: Observed
Rows are ordered by the value Qwen3.6 launch benchmarks published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.