RLTasksby ulam.ai
Models / DeepSeek

DeepSeek / MODEL EVIDENCE

DeepSeek V2.5

4 benchmarks · 6 observations · 4 sources

Scores at a glance

4 benchmarks · large dot: DeepSeek V2.5; small dots: closest models where reported

CodeElo ↗629 Elo
211578

DS-V2.5 · CodeElo · Overall competition Elo · main comparison ↗

ZebraLogic ↗22.1%
6.481

DeepSeek-v2.5 · ZebraLogic · Grid-level accuracy · complete puzzles ↗

Closest models by score

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

34.6 percentile-point gap

3 of 4 shared benchmark comparisons

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. Aider refactoring benchmark ↗

    Paul Gauthier, Aider contributors

  2. Commit0: Library Generation from Scratch — published result table ↗

    Zhao, Wenting, Jiang, Nan, Lee, Celine, Chiu, Justin T, Cardie, Claire, Gallé, Matthias et al. · 2024

    All 7 authors

    Zhao, Wenting, Jiang, Nan, Lee, Celine, Chiu, Justin T, Cardie, Claire, Gallé, Matthias, Rush, Alexander M

  3. CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings — published result table ↗

    Shanghaoran Quan, Jiaxi Yang, Bowen Yu, Bo Zheng, Dayiheng Liu, An Yang et al. · 2025

    All 17 authors

    Shanghaoran Quan, Jiaxi Yang, Bowen Yu, Bo Zheng, Dayiheng Liu, An Yang, Xuancheng Ren, Bofei Gao, Yibo Miao, Yunlong Feng, Zekun Wang, Jian Yang, Zeyu Cui, Yang Fan, Yichang Zhang, Binyuan Hui, Junyang Lin

  4. ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning — published result table ↗

    Bill Yuchen Lin, Ronan Le Bras, Kyle Richardson, Ashish Sabharwal, Radha Poovendran, Peter Clark et al. · 2025

    All 7 authors

    Bill Yuchen Lin, Ronan Le Bras, Kyle Richardson, Ashish Sabharwal, Radha Poovendran, Peter Clark, Yejin Choi

Names used in source tables

DS-V2.5 · DeepSeek V2.5 · DeepSeek-V2.5 · DeepSeek-v2.5