DS-Arena-Code
DeepSeek-V2.5 Sep 2024 63.1% Models answer common coding requests in an internal subjective test. GPT-4o judges responses against competitor models to give a win rate.
This is an in-house evaluation, and DeepSeek never released the prompts.
- Made by
- DeepSeek-AI
- Released
- September 2024
- Kind
- Function-level problems
- Level
- University
- Scored
- Graded by a model
- Answers
- Open-ended
- Tasks
- Kept private
- Last in a launch post
- September 2024, dropped before it saturated
- Last model added
- September 2024
- Scores refreshed
- November 12th, 2026
DeepSeek-V2.5 leads with 63.1%
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | DeepSeek-V2.5 Sep 2024 | 63.1% | Sep 2024 | Lab model card |
The benchmark's own leaderboard has 2 entries, 1 of them models we track. We plot every source in the charts below.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Sources: Official DS-Arena-Code leaderboard and labs’ model cards
No launch post has listed it since September 2024
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Sep 5, 2024 | DeepSeek-V2.5 | 63.1 | DS-Arena-Code (in-house) |
One lab claim next to the leaderboard
Each score a lab reported for its own model, beside the same model's best score on the leaderboard. Gaps mostly come from different harnesses, effort levels and task subsets. 1 of them match, which usually means one side copied the other. Every benchmark.
| Model | Lab says | Board says | Gap |
|---|---|---|---|
| DeepSeek-V2.5 Sep 2024 | 63.1% DS-Arena-Code (in-house) | 63.1% Leaderboard | Same |
More in Coding
- SWE-bench Verified In use 500 human-validated GitHub issues from 12 Python repos. Agent writes a patch that must pass hidden tests. Claude Opus 4.7 83.5%
- LiveCodeBench v6 In use Competitive programming problems collected after model cutoffs from LeetCode, AtCoder, Codeforces. Scored pass@1 on hidden tests. DeepSeek-V4-Pro 93.5%
- SWE-bench Multilingual In use 300 GitHub-issue tasks across nine programming languages in SWE-bench format. Patch graded by repository tests. Claude Fable 5.2 96.6%
- DeepSWE In use 113 original long-horizon engineering tasks across 91 repos and five languages, written from scratch. Hand-written verifiers accept alternative solutions. GPT-6 Astra 74.1%
- SciCode In use Scientist-curated research coding problems split into subproblems across natural sciences. Code checked against test cases.
Seed2.1 Pro 59.8% - Codeforces rating In use Model solves recent Codeforces contest problems. An Elo-style rating is computed from simulated contest performance. DeepSeek V4.1 Flash 3,471