Which AI model scores highest on MRCR v2 (8-needle)?

Gemini 3.7 Flash by Google holds the best MRCR v2 (8-needle) (128k average) result among tracked models, at 97% (released Aug 13 2026). Higher scores are better on this benchmark.

What are the top 5 models on MRCR v2 (8-needle)?

1. Gemini 3.7 Flash (Google) — 97%; 2. GPT-5.5 (OpenAI) — 94.8%; 3. Claude Sonnet 4.6 (Anthropic) — 84.9%; 3. Gemini 3.1 Pro (Google) — 84.9%; 5. Gemini 3.5 Flash (Google) — 77.3%.

How many models have a published MRCR v2 (8-needle) score?

7 tracked models have a published MRCR v2 (8-needle) (128k average) score. Scores are collected from published lab reports and benchmark sources, with recorded sources credited alongside the results. We do not re-run the evaluations.

Long context

MRCR v2 (8-needle)128k average

Tests whether the AI can find specific details buried inside a very long document (around 128k tokens — roughly a long book). Higher is better.

128k average 1M pointwise

Rankings

Higher is better

MRCR v2 (8-needle) — frequently asked questions

: Tests whether the AI can find specific details buried inside a very long document (around 128k tokens — roughly a long book). Higher is better.
: Gemini 3.7 Flash by Google holds the best MRCR v2 (8-needle) (128k average) result among tracked models, at 97% (released Aug 13 2026). Higher scores are better on this benchmark.
: 1. Gemini 3.7 Flash (Google) — 97%; 2. GPT-5.5 (OpenAI) — 94.8%; 3. Claude Sonnet 4.6 (Anthropic) — 84.9%; 3. Gemini 3.1 Pro (Google) — 84.9%; 5. Gemini 3.5 Flash (Google) — 77.3%.
: 7 tracked models have a published MRCR v2 (8-needle) (128k average) score. Scores are collected from published lab reports and benchmark sources, with recorded sources credited alongside the results. We do not re-run the evaluations.