Reasoning benchmark
MRCR v2 128K-256K leaderboard
OpenAI MRCR v2 8-needle 128K-256K. Every model the catalog carries a published MRCR v2 128K-256K value for, ranked by that value.
CategoryReasoning
MeasureVery-long-context retrieval
Tasks8-needle retrieval tasks
DifficultyVery long-context reasoning
Published byIntroducing GPT-5.4 mini and nano
MRCR v2 slice focused on very long contexts at 128K-256K lengths.
MRCR v2 128K-256K ranking
2 models with a published MRCR v2 128K-256K 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 | Very-long-context retrieval |
|---|---|---|---|
| 1 |  GPT-5.5 | OpenAI | 87.5 |
| 2 |  Claude Opus 4.7 (Adaptive) | Anthropic | 59.2 |
Evidence key: Observed
Rows are ordered by the value Introducing GPT-5.4 mini and nano 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.