RLTasksby ulam.ai
Models / DeepSeek

DeepSeek / MODEL EVIDENCE

DeepSeek V3 (Mar 2025)

15 benchmarks · 16 observations · 15 sources · released 2025-03-24

Scores at a glance

15 benchmarks · large dot: DeepSeek V3 (Mar 2025); small dots: closest models where reported

GPQA Diamond ↗67.61%
9.2896.4

DeepSeek-V3 (Mar 2025) · GPQA diamond · Best score (across scorers) · % ↗

MATH Level 5 ↗75.55%
3.2998.13

DeepSeek-V3 (Mar 2025) · MATH level 5 · Best score (across scorers) · % ↗

SimpleBench ↗27.2%
10.781.9

DeepSeek-V3 (Mar 2025) · SimpleBench · Score (AVG@5) · % ↗

CritPt ↗0%
032.29

DeepSeek-V3 (Mar 2025) · CritPt · Accuracy · % ↗

LMCA ↗15.47%
2.7868.26

DeepSeek-V3 (Mar 2025) · LMCA · Score · % ↗

DTBench ↗64.8%
41.6598.93

DeepSeek-V3 (Mar 2025) · DTBench · Accuracy · % ↗

LiveBench ↗66.86%
22.0882.35

DeepSeek-V3 (Mar 2025) · LiveBench · Global average · % ↗

SciCode ↗39%
1.2766.9

DeepSeek-V3 (Mar 2025) · SciCode · Score · % ↗

Closest models by score

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

2.3 percentile-point gap

3 of 3 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 LLM Leaderboards — Polyglot coding benchmark ↗

    Aider

  2. SciCode Benchmark | Artificial Analysis ↗

    Artificial Analysis

  3. DTBench — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  4. LMCA — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  5. CritPt v1 ↗

    Epoch AI

  6. GPQA Diamond ↗

    Epoch AI

  7. MATH Level 5 ↗

    Epoch AI

  8. OTIS Mock AIME 2024-2025 ↗

    Epoch AI

  9. SimpleBench ↗

    Epoch AI

  10. AI benchmarks & capabilities ↗

    Epoch AI

  11. Fiction.liveBench — March 14, 2025 benchmark release ↗

    Fiction.live · 2025

  12. Writing benchmark — incorporating mandatory story elements ↗

    lechmazur

  13. WeirdML ↗

    Håvard Tveit Ihle

  14. LiveBench — model evaluation leaderboard ↗

    LiveBench Team

  15. Measuring AI Ability to Complete Long Software Tasks ↗

    METR

Names used in source tables

DeepSeek-V3 (Mar 2025)