RLTasksby ulam.ai
Models / Meta

Meta / MODEL EVIDENCE

Llama 3.1-70B-Inst

6 benchmarks · 11 observations · 3 sources

Scores at a glance

6 benchmarks · large dot: Llama 3.1-70B-Inst; small dots: closest models where reported

RULER ↗75.8%
65.393.3

Llama-3.1-70B-Inst · RULER · 128k context · HELMET paper · RULER comparison ↗

InfiniteBench ↗39.7 points
1.960.3

Llama-3.1-70B-Inst · InfiniteBench · InfiniteBench aggregate · HELMET paper · original-author harness ↗

LongProc (Long Procedural Generation) ↗72.9 points
494.8

Llama-3.1-70B-Inst · LongProc (Long Procedural Generation) · 0.5K · average task score · original evaluation ↗

2 more reported results

58 points · Llama-3.1-70B-Inst · LongProc (Long Procedural Generation) · 2K · average task score · original evaluation · LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation ↗

24.2 points · Llama-3.1-70B-Inst · LongProc (Long Procedural Generation) · 8K · average task score · original evaluation · LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation ↗

Closest models by score

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

How similarity is measured

Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.

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. HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly — published result table ↗

    Howard Yen, Tianyu Gao, Minmin Hou, Ke Ding, Daniel Fleischer, Peter Izsak et al. · 2024

    All 8 authors

    Howard Yen, Tianyu Gao, Minmin Hou, Ke Ding, Daniel Fleischer, Peter Izsak, Moshe Wasserblat, Danqi Chen

  2. LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation — published result table ↗

    Xi Ye, Fangcong Yin, Yinghui He, Joie Zhang, Howard Yen, Tianyu Gao et al. · 2025

    All 8 authors

    Xi Ye, Fangcong Yin, Yinghui He, Joie Zhang, Howard Yen, Tianyu Gao, Greg Durrett, Danqi Chen

  3. KernelBench: Can LLMs Write Efficient GPU Kernels? — published result table ↗

    Ouyang, Anne, Guo, Simon, Arora, Simran, Zhang, Alex L., Hu, William, Ré, Christopher et al. · 2025

    All 7 authors

    Ouyang, Anne, Guo, Simon, Arora, Simran, Zhang, Alex L., Hu, William, Ré, Christopher, Mirhoseini, Azalia

Names used in source tables

Llama 3.1-70B Inst. · Llama-3.1-70B-Inst