DeepSeek
A reasoning model trained with reinforcement learning, on par with OpenAI o1
Running this yourself: likely needs a high-memory cloud gpu.
80.9
Quality Score
1373
Arena ELO
671B
Parameters
16K
Context
This measures the amount of verifiable public evidence we have, not how capable the model is. A missing field means it has not been verified yet, not that its value is zero.
21 of 22 public signals
Use this section to answer one simple question first: how much outside evidence do we have that this model performs well? Structured benchmark scores appear first, then official provider evidence, then live arena signal.
This model has normalized benchmark rows, so scores here are directly comparable across benchmark sources.
Sign in to join the discussion
880.0K
Downloads
13.6K
Likes
May 2026
Released
5/5 signals
4/4 signals
5/5 signals
3/4 signals
4/4 signals
Parameters
671B
Training compute
3.5e24 FLOP
Dataset scale
14.8T units
Base model
DeepSeek-V3
Source-reported access: Open weights (unrestricted) · Confident confidence
Gaps we are still tracking
These are recent benchmark or leaderboard claims from official provider sources. They are useful for freshness and context, but they are not treated the same as normalized independent benchmark rows.
deepseek-r1 - Arena-Hard-Auto
Arena-Hard-Auto official Gemini-2.5 judged score 58.0 with CI -2.2/2
View sourceDeepSeek-R1-0528 - LiveCodeBench
LiveCodeBench pass@1 84.4 across 1055 tasks
View sourceDeepSeek-R1-0528 - LiveCodeBench
LiveCodeBench pass@1 84.4 across 1055 tasks
View source1373
ELO Score
1368 - 1376
95% Confidence
+/-4 points
19.4K
Battles
Sep 5, 2026
Last Updated