Skip to main content
Radar

Every change to the models you run, with its source and its date. Releases, price changes, retirements, API changes, and incidents.Every change to the models you run, with its source.

Follow model changes
BenchLM

MRCRv2

Data verified 36 confirmed releases in the last 30 daysFollow model changes

A long-context benchmark for memory, retrieval, and multi-round coherence over large contexts.

Top models on MRCRv2 — September 18, 2026

As of September 18, 2026, Sakana Fugu-Ultra leads the MRCRv2 leaderboard with 93.6% , followed by Qwen3.8 Max (92.9%) and Qwen3.7 Plus (91.7%).

1Proprietary

Sakana Fugu-Ultra

Sakana AI

93.6%
Context 1M
2Open weights

Qwen3.8 Max

Alibaba

92.9%
Overall 73.17Context 1M
3Proprietary

Qwen3.7 Plus

Alibaba

91.7%
Overall 61.6Context 1M

9 modelsReasoning20% of category scoreCurrentUpdated September 18, 2026

Leaderboard (9 models)

Score
1
Sakana Fugu-UltraSakana AI · Closed
93.6%
2
Qwen3.8 MaxAlibaba · Open weight
92.9%
3
Qwen3.7 PlusAlibaba · Closed
91.7%
4
Qwen3.7 MaxAlibaba · Closed
90.4%
5
Sakana FuguSakana AI · Closed
86.6%
6
Gemini 3.5 FlashGoogle · Closed
77.3%
7
Gemini 3.5 Flash-LiteGoogle · Closed
72.2%
8
Pokee-Isaac 28BPokee AI · Closed
60.7%
9
Gemma 4 12BGoogle · Open weight
43.4%

According to BenchLM.ai, Sakana Fugu-Ultra leads the MRCRv2 benchmark with a score of 93.6%, followed by Qwen3.8 Max (92.9%) and Qwen3.7 Plus (91.7%). The top models are clustered within 1.9 points, suggesting this benchmark is nearing saturation for frontier models.

9 models have been evaluated on MRCRv2. The benchmark falls in the Reasoning category. This category carries a 17% weight in BenchLM.ai's overall scoring system. Within that category, MRCRv2 contributes 20% of the category score, so strong performance here directly affects a model's overall ranking.

About MRCRv2

Year

2025

Tasks

Long-context retrieval

Format

Multi-round long-context evaluation

Difficulty

Hard long-context

MRCRv2 is especially useful for models that compete on long context, since it checks whether they can retrieve the right information across long, multi-round interactions.

Introducing GPT-5.2 and GPT-5.2 Pro

Freshness and provenance

Version

MRCRv2 2025

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

Current

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.

Questions

What does MRCRv2 measure?

A long-context benchmark for memory, retrieval, and multi-round coherence over large contexts.

Which model scores highest on MRCRv2?

Sakana Fugu-Ultra by Sakana AI currently leads with a score of 93.6% on MRCRv2.

How many models are evaluated on MRCRv2?

9 AI models have been evaluated on MRCRv2 on BenchLM.

Compare top models on MRCRv2

Sakana Fugu-Ultra vs Qwen3.8 MaxQwen3.8 Max vs Qwen3.7 PlusQwen3.7 Plus vs Qwen3.7 MaxQwen3.7 Max vs Sakana Fugu
Last updated: September 18, 2026 · BenchLM version MRCRv2 2025

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 2,000+ readers.

One email each week. Unsubscribe anytime.