RLTasksby ulam.ai
Models / Meta

Meta / MODEL EVIDENCE

Llama 2-Chat-70B

3 benchmarks · 4 observations · 3 sources

Scores at a glance

3 benchmarks · large dot: Llama 2-Chat-70B; small dots: closest models where reported

Belebele ↗41.5%
27.760.2

Llama-2-chat / 70B · Belebele · 122-language average accuracy · reported evaluation settings ↗

Closest models by score

Similar positions on shared benchmark leaderboards. Smaller gaps are closer.

There are not enough shared scored settings to identify close comparisons reliably.

Filter comparisons to this model →

Sources

Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.

  1. The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants — published result table ↗

    Bandarkar, Lucas, Liang, Davis, Muller, Benjamin, Artetxe, Mikel, Shukla, Satya Narayan, Husa, Donald et al. · 2023

    All 10 authors

    Bandarkar, Lucas, Liang, Davis, Muller, Benjamin, Artetxe, Mikel, Shukla, Satya Narayan, Husa, Donald, Goyal, Naman, Krishnan, Abhinandan, Zettlemoyer, Luke, Khabsa, Madian

  2. FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models — published result table ↗

    Jiang, Yuxin, Wang, Yufei, Zeng, Xingshan, Zhong, Wanjun, Li, Liangyou, Mi, Fei et al. · 2023

    All 10 authors

    Jiang, Yuxin, Wang, Yufei, Zeng, Xingshan, Zhong, Wanjun, Li, Liangyou, Mi, Fei, Shang, Lifeng, Jiang, Xin, Liu, Qun, Wang, Wei

  3. Evaluating Very Long-Term Conversational Memory of LLM Agents — published result table ↗

    Maharana, Adyasha, Lee, Dong-Ho, Tulyakov, Sergey, Bansal, Mohit, Barbieri, Francesco, Fang, Yuwei · 2024

Names used in source tables

LLaMA2-Chat-70B · Llama-2-Chat-70B · Llama-2-chat / 70B