A long-context retrieval benchmark that measures whether a model can recover relevant information embedded deep inside very long contexts.
As of March 2026, Claude Opus 4.5 leads the AI-Needle leaderboard with 74% , followed by Kimi K2.5 (70%) and Qwen3.5 397B (68.7%).
Claude Opus 4.5
Anthropic
Kimi K2.5
Moonshot AI
Qwen3.5 397B
Alibaba
According to BenchLM.ai, Claude Opus 4.5 leads the AI-Needle benchmark with a score of 74%, followed by Kimi K2.5 (70%) and Qwen3.5 397B (68.7%). The scores show moderate spread, with meaningful differences between the top tier and mid-tier models.
5 models have been evaluated on AI-Needle. The benchmark falls in the Reasoning category. This category carries a 17% weight in BenchLM.ai's overall scoring system. AI-Needle is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
Year
2026
Tasks
Long-context retrieval
Format
Needle-in-a-haystack recall
Difficulty
Long-context memory
AI-Needle is useful for testing whether very large context windows are actually usable rather than just headline numbers. It rewards precise recall under distractors and long-document clutter.
Qwen3.6 launch benchmarksVersion
AI-Needle 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
A long-context retrieval benchmark that measures whether a model can recover relevant information embedded deep inside very long contexts.
Claude Opus 4.5 by Anthropic currently leads with a score of 74% on AI-Needle.
5 AI models have been evaluated on AI-Needle on BenchLM.
Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.
Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.