long context benchmark
MRCR v2 (8-needle) Leaderboard
MRCR v2 (8-needle) is a variant of the Multi-Round Coreference Resolution benchmark that includes 8 needle items to retrieve from long contexts. This tests models' ability to simultaneously track and reason about multiple pieces of information across extended conversations.
Updated Aug 17, 2026
Models23
Model coverage23
MetricScore
EvidenceC
MRCR v2 (8-needle) Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelGO | Score97.0% | Percentile100.0% | Participants23 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score92.9% | Percentile95.5% | Participants23 | EvidenceC | Evaluated |
| Rank03 | ModelOP | Score91.5% | Percentile90.9% | Participants23 | EvidenceC | Evaluated |
| Rank04 | ModelOP | Score89.6% | Percentile86.4% | Participants23 | EvidenceC | Evaluated |
| Rank05 | ModelAN | Score76.0% | Percentile81.8% | Participants23 | EvidenceC | Evaluated |
| Rank06 | ModelOP | Score74.0% | Percentile77.3% | Participants23 | EvidenceC | Evaluated |
| Rank07 | ModelGO | Score66.4% | Percentile72.7% | Participants23 | EvidenceC | Evaluated |
| Rank08 | ModelGO | Score60.1% | Percentile68.2% | Participants23 | EvidenceC | Evaluated |
| Rank09 | ModelGO | Score54.0% | Percentile63.6% | Participants23 | EvidenceC | Evaluated |
| Rank10 | ModelGO | Score44.1% | Percentile59.1% | Participants23 | EvidenceC | Evaluated |
| Rank11 | ModelGO | Score43.4% | Percentile54.5% | Participants23 | EvidenceC | Evaluated |
| Rank12 | ModelOP | Score41.3% | Percentile50.0% | Participants23 | EvidenceC | Evaluated |
| Rank13 | ModelOP | Score33.6% | Percentile45.5% | Participants23 | EvidenceC | Evaluated |
| Rank14 | ModelOP | Score33.1% | Percentile40.9% | Participants23 | EvidenceC | Evaluated |
| Rank15 | ModelGO | Score26.6% | Percentile36.4% | Participants23 | EvidenceC | Evaluated |
| Rank16 | ModelGO | Score26.3% | Percentile31.8% | Participants23 | EvidenceC | Evaluated |
| Rank17 | ModelGO | Score26.3% | Percentile27.3% | Participants23 | EvidenceC | Evaluated |
| Rank18 | ModelGO | Score25.4% | Percentile22.7% | Participants23 | EvidenceC | Evaluated |
| Rank19 | ModelGO | Score22.1% | Percentile18.2% | Participants23 | EvidenceC | Evaluated |
| Rank20 | ModelGO | Score21.3% | Percentile13.6% | Participants23 | EvidenceC | Evaluated |
| Rank21 | ModelGO | Score19.1% | Percentile9.1% | Participants23 | EvidenceC | Evaluated |
| Rank22 | ModelGO | Score16.4% | Percentile4.5% | Participants23 | EvidenceC | Evaluated |
| Rank23 | ModelGO | Score13.5% | Percentile0.0% | Participants23 | EvidenceC | Evaluated |
MRCR v2 (8-needle) Highlights
The leading models and scores on this benchmark.
MRCR v2 (8-needle) Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for MRCR v2 (8-needle)
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis mrcr v2 (8-needle) AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01GOGemini 3.7 FlashGoogle
- Score
- 97.0%
- Price
- $0.75 input / $3.8 output per 1M tokens
- Speed
- Up to 13 tok/s via Google
Strengths
- Ranks #1 of 23 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures MRCR v2 (8-needle), not total model capability
- 02ACQwen3.8 MaxAlibaba Cloud / Qwen Team
- Score
- 92.9%
- Price
- $2.0 input / $6.0 output per 1M tokens
Strengths
- Ranks #2 of 23 compared models
- 95th percentile on this benchmark
- C evidence result
Considerations
- This result measures MRCR v2 (8-needle), not total model capability
- 03OPGPT-5.6 SolOpenAI
- Score
- 91.5%
- Price
- $5.0 input / $30 output per 1M tokens
- Speed
- Up to 27 tok/s via OpenAI
Strengths
- Ranks #3 of 23 compared models
- 91th percentile on this benchmark
- C evidence result
Considerations
- This result measures MRCR v2 (8-needle), not total model capability
- 04OPGPT-5.6 TerraOpenAI
- Score
- 89.6%
- Price
- $2.0 input / $12 output per 1M tokens
- Speed
- Up to 35 tok/s via OpenAI
Strengths
- Ranks #4 of 23 compared models
- 86th percentile on this benchmark
- C evidence result
Considerations
- This result measures MRCR v2 (8-needle), not total model capability
- 05ANClaude Opus 4.6Anthropic
- Score
- 76.0%
- Price
- $5.0 input / $25 output per 1M tokens
- Speed
- Up to 17 tok/s via Anthropic
Strengths
- Ranks #5 of 23 compared models
- 82th percentile on this benchmark
- C evidence result
Considerations
- This result measures MRCR v2 (8-needle), not total model capability
Selection summary
Best AI Models for MRCR v2 (8-needle)
Gemini 3.7 Flash currently leads MRCR v2 (8-needle) with 97.0%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is MRCR v2 (8-needle)?
What MRCR v2 (8-needle) measures and how its scores work.
MRCR v2 (8-needle) is a variant of the Multi-Round Coreference Resolution benchmark that includes 8 needle items to retrieve from long contexts. This tests models' ability to simultaneously track and reason about multiple pieces of information across extended conversations.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of C.
- Family
- MRCR v2 (8-needle)
- Modality
- text
- Primary category
- long context
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- mrcr-v2-(8-needle)|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MRCR v2 (8-needle).
Which model scores highest on MRCR v2 (8-needle)?
Gemini 3.7 Flash is currently ranked first with 97.0%.
What does MRCR v2 (8-needle) measure?
MRCR v2 (8-needle) is a variant of the Multi-Round Coreference Resolution benchmark that includes 8 needle items to retrieve from long contexts. This tests models' ability to simultaneously track and reason about multiple pieces of information across extended conversations.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
23 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.