DyCodeEval
Models solve dynamically rewritten HumanEval and MBPP problems with equivalent program behavior. The evaluator runs tests and computes DyPass@K across generated variants.
The repository supplies pregenerated variants. Its leaderboard link is a placeholder, so it does not establish a public leaderboard.
- Made by
- Columbia University
- Released
- March 2025
- Kind
- Function-level problems
- Level
- School
- Scored
- Checked automatically
- Answers
- Code
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Items from
- Another benchmark, Generated
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
-
Llama 3.1-8B #203 on the capability index
- Last model added
- September 2024
- Scores refreshed
- November 20th, 2026
Llama-3.1-8B-Instruct tops the leaderboard with 64% Llama 3.1-8B leads with 39% among models released by September 2024
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is Llama 3.1-8B, at 39%. This view shows only models we track, each at its best.
The newest model with a score here came out in September 2024, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1 Llama-3.1-8B-Instruct In the wild 64%
- 2
Llama 3.1-8B In the wild 39%
- 3 CodeLlama-13b-hf In the wild 37%
- 4 CodeLlama-7b-hf In the wild 34%
- 5
Llama 3.2 3B In the wild 31%
- 6
Llama 3.2 1B In the wild 17%
Source: The DyCodeEval paper
- 1
Llama 3.1-8B In the wild 39%
- 2
Llama 3.2 3B In the wild 31%
- 3
Llama 3.2 1B In the wild 17%
Source: The DyCodeEval paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Llama-3.1-8B-Instruct | 64% | In the wild | Official leaderboard | |
| 2 | | 39% | In the wild | Jul 2024 | Official leaderboard |
| 3 | CodeLlama-13b-hf | 37% | In the wild | Official leaderboard | |
| 4 | CodeLlama-7b-hf | 34% | In the wild | Official leaderboard | |
| 5 | | 31% | In the wild | Sep 2024 | Official leaderboard |
| 6 | | 17% | In the wild | Sep 2024 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 39% | In the wild | Jul 2024 | Official leaderboard |
| 2 | | 31% | In the wild | Sep 2024 | Official leaderboard |
| 3 | | 17% | In the wild | Sep 2024 | Official leaderboard |
Rankings by part
We read 6 parts from the benchmark’s paper, each ranking models on one part of the test, such as DyPass@3, DyPass@5 and DyPass@10. Llama 3.1-8B leads 3 of them, and Llama 3.2 3B leads the other 3. Arrows show how far a model moved from its overall rank among the models we track.
DyPass@3
3 models we track have a score here.
- 1
Llama 3.1-8B 39%
- 2
Llama 3.2 3B 31%
- 3
Llama 3.2 1B 17%
DyPass@5
3 models we track have a score here.
- 1
Llama 3.1-8B 45%
- 2
Llama 3.2 3B 36%
- 3
Llama 3.2 1B 21%
DyPass@10
3 models we track have a score here.
- 1
Llama 3.1-8B 53%
- 2
Llama 3.2 3B 43%
- 3
Llama 3.2 1B 26%
Pass@3
3 models we track have a score here.
- 1
Llama 3.2 3B ↑1 88%
- 2
Llama 3.2 1B ↑1 82%
- 3
Llama 3.1-8B ↓2 48%
Pass@5
3 models we track have a score here.
- 1
Llama 3.2 3B ↑1 88%
- 2
Llama 3.2 1B ↑1 83%
- 3
Llama 3.1-8B ↓2 56%
Pass@10
3 models we track have a score here.
- 1
Llama 3.2 3B ↑1 89%
- 2
Llama 3.2 1B ↑1 85%
- 3
Llama 3.1-8B ↓2 65%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The DyCodeEval paper
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official DyCodeEval leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
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
Data audit
9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 2 years ago, in September 2024, for Llama 3.2 1B. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
- Pass Independent runs Scores from the benchmark’s paper (6 entries).
- Pass Models scored 3 models we track, plus 3 other entries on its leaderboard.
- Warning Newest score The newest came 2 years ago, in September 2024, for Llama 3.2 1B.
- Note Frontier models None of the top 10 has a score. The strongest tested is Llama 3.1-8B (#203).
- Pass Headroom The best is 39%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 5 rows for models we track and 3 other entries at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.