FeatEng
Models write Python functions to transform 103 tabular datasets. The score measures how much those changes reduce prediction error for an XGBoost model.
The authors publish a ranking of 23 model configurations and an automated machine learning baseline.
- Released
- October 2024
- Kind
- Data science and SQL
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Code
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Environment
- Code sandbox
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
- o1-mini #142 on the capability index
- Last model added
- September 2024
- Scores refreshed
- November 21st, 2026
o1-preview leads with 11.1% among models released by September 2024 o1-preview leads with 11.1% among models released by September 2024
Best score per entry from the benchmark's paper, read on November 21st, 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. 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
- 11.1 o1-preview
- 7.77
Gemini 1.5 Pro
- 7.33
Gemini 1.5 Flash
- 7.20 o1-mini
- 7.04 GPT-4o
- 6.85
DeepSeek-V2.5
- 6.75 Claude 3.5 Sonnet
- 6.46 Mistral Large 2407
- 6.41 GPT-4o
- 6.30
Llama 3.1-405B
- 6.04 GPT-4o mini
- 5.78 GPT-4 Turbo
- 5.76 Codestral 22B
- 5.02 Claude 3 Opus
- 4.58
Llama 3.1-70B
- 4.39 Claude 3 Haiku
- 4.00 Mistral Small 2409
- 3.46 Mixtral 8x22B v0.1
- 2.91 Yi Coder 9B
- 2.36 Jamba 1.5 Large
- 1.25 Command R+ 08-2024
- 1.01
Mixtral 8x7B
- 1 o1-preview 11.1%
- 2
Gemini 1.5 Pro Sep 2024 7.77%
- 3
Gemini 1.5 Flash Sep 2024 7.33%
- 4 o1-mini 7.20%
- 5 GPT-4o Aug 2024 7.04%
- 6
DeepSeek-V2.5 Sep 2024 6.85%
- 7 Claude 3.5 Sonnet 6.75%
- 8 Mistral Large 2407 6.46%
- 9 GPT-4o May 2024 6.41%
- 10
Llama 3.1-405B 6.30%
- 11 GPT-4o mini 6.04%
- 12 GPT-4 Turbo Apr 2024 5.78%
- 13 Codestral 22B 5.76%
- 14 Claude 3 Opus 5.02%
- 15
Llama 3.1-70B 4.58%
- 16 Claude 3 Haiku 4.39%
- 17 Mistral Small 2409 4.00%
- 18 Mixtral 8x22B v0.1 3.46%
- 19 Yi Coder 9B 2.91%
- 20 Jamba 1.5 Large 2.36%
- 21 Command R+ 08-2024 1.25%
- 22
Mixtral 8x7B 1.01%
Source: The FeatEng paper
- 1 o1-preview 11.1%
- 2
Gemini 1.5 Pro Sep 2024 7.77%
- 3
Gemini 1.5 Flash Sep 2024 7.33%
- 4 o1-mini 7.20%
- 5 GPT-4o Aug 2024 7.04%
- 6
DeepSeek-V2.5 Sep 2024 6.85%
- 7 Claude 3.5 Sonnet 6.75%
- 8 GPT-4o May 2024 6.41%
- 9
Llama 3.1-405B 6.30%
- 10 GPT-4o mini 6.04%
- 11 GPT-4 Turbo Apr 2024 5.78%
- 12 Claude 3 Opus 5.02%
- 13
Llama 3.1-70B 4.58%
- 14 Claude 3 Haiku 4.39%
- 15 Jamba 1.5 Large 2.36%
- 16
Mixtral 8x7B 1.01%
Source: The FeatEng paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | o1-preview | 11.1% | Sep 2024 | Official leaderboard | |
| 2 | | 7.77% | Sep 2024 | Official leaderboard | |
| 3 | | 7.33% | Aug 2024 | Official leaderboard | |
| 4 | o1-mini | 7.20% | Sep 2024 | Official leaderboard | |
| 5 | GPT-4o Aug 2024 | 7.04% | Aug 2024 | Official leaderboard | |
| 6 | | 6.85% | Sep 2024 | Official leaderboard | |
| 7 | Claude 3.5 Sonnet | 6.75% | Jun 2024 | Official leaderboard | |
| 8 | Mistral Large 2407 | 6.46% | Official leaderboard | ||
| 9 | GPT-4o May 2024 | 6.41% | May 2024 | Official leaderboard | |
| 10 | | 6.30% | Jul 2024 | Official leaderboard | |
| 11 | GPT-4o mini | 6.04% | Jul 2024 | Official leaderboard | |
| 12 | GPT-4 Turbo Apr 2024 | 5.78% | Apr 2024 | Official leaderboard | |
| 13 | Codestral 22B | 5.76% | Official leaderboard | ||
| 14 | Claude 3 Opus | 5.02% | Feb 2024 | Official leaderboard | |
| 15 | | 4.58% | Jul 2024 | Official leaderboard | |
| 16 | Claude 3 Haiku | 4.39% | Mar 2024 | Official leaderboard | |
| 17 | Mistral Small 2409 | 4.00% | Official leaderboard | ||
| 18 | Mixtral 8x22B v0.1 | 3.46% | Official leaderboard | ||
| 19 | Yi Coder 9B | 2.91% | Official leaderboard | ||
| 20 | Jamba 1.5 Large | 2.36% | Aug 2024 | Official leaderboard | |
| 21 | Command R+ 08-2024 | 1.25% | Official leaderboard | ||
| 22 | | 1.01% | Dec 2023 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | o1-preview | 11.1% | Sep 2024 | Official leaderboard | |
| 2 | | 7.77% | Sep 2024 | Official leaderboard | |
| 3 | | 7.33% | Aug 2024 | Official leaderboard | |
| 4 | o1-mini | 7.20% | Sep 2024 | Official leaderboard | |
| 5 | GPT-4o Aug 2024 | 7.04% | Aug 2024 | Official leaderboard | |
| 6 | | 6.85% | Sep 2024 | Official leaderboard | |
| 7 | Claude 3.5 Sonnet | 6.75% | Jun 2024 | Official leaderboard | |
| 8 | GPT-4o May 2024 | 6.41% | May 2024 | Official leaderboard | |
| 9 | | 6.30% | Jul 2024 | Official leaderboard | |
| 10 | GPT-4o mini | 6.04% | Jul 2024 | Official leaderboard | |
| 11 | GPT-4 Turbo Apr 2024 | 5.78% | Apr 2024 | Official leaderboard | |
| 12 | Claude 3 Opus | 5.02% | Feb 2024 | Official leaderboard | |
| 13 | | 4.58% | Jul 2024 | Official leaderboard | |
| 14 | Claude 3 Haiku | 4.39% | Mar 2024 | Official leaderboard | |
| 15 | Jamba 1.5 Large | 2.36% | Aug 2024 | Official leaderboard | |
| 16 | | 1.01% | Dec 2023 | 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 Classification, Regression and Failure. o1-preview leads 5 of them, and Mixtral 8x7B leads the other one. Arrows show how far a model moved from its overall rank among the models we track.
Classification
The paper reports this score on classification datasets. 16 models we track have a score here.
- 1 o1-preview 8.90%
- 2
Gemini 1.5 Pro Sep 2024 6.18%
- 3 o1-mini ↑1 5.91%
- 4 Claude 3.5 Sonnet ↑3 5.79%
- 5
Gemini 1.5 Flash Sep 2024 ↓2 4.70%
- 6
Llama 3.1-405B ↑3 4.43%
- 7
DeepSeek-V2.5 Sep 2024 ↓1 4.34%
- 8 GPT-4o Aug 2024 ↓3 4.27%
- 9 GPT-4 Turbo Apr 2024 ↑2 4.16%
- 10 GPT-4o May 2024 ↓2 3.74%
Regression
The paper reports this score on regression datasets. 16 models we track have a score here.
- 1 o1-preview 19.4%
- 2 GPT-4o Aug 2024 ↑3 17.8%
- 3
Gemini 1.5 Flash Sep 2024 17.6%
- 4 GPT-4o May 2024 ↑4 16.8%
- 5
DeepSeek-V2.5 Sep 2024 ↑1 16.6%
- 6 GPT-4o mini ↑4 15.3%
- 7
Gemini 1.5 Pro Sep 2024 ↓5 14%
- 8
Llama 3.1-405B ↑1 13.6%
- 9 o1-mini ↓5 12.3%
- 10 GPT-4 Turbo Apr 2024 ↑1 12.1%
Failure
The paper reports the fraction of failed runs. 16 models we track have a score here.
- 1
Mixtral 8x7B ↑15 88.4%
- 2 Jamba 1.5 Large ↑13 69.2%
- 3 Claude 3 Haiku ↑11 67.4%
- 4 Claude 3 Opus ↑8 42.7%
- 5
Llama 3.1-70B ↑8 42.6%
- 6 Claude 3.5 Sonnet ↑1 41.9%
- 7 o1-mini ↓3 40.1%
- 8
Gemini 1.5 Flash Sep 2024 ↓5 37.8%
- 9
Gemini 1.5 Pro Sep 2024 ↓7 29.5%
- 10 GPT-4 Turbo Apr 2024 ↑1 29.4%
Improved classification
The paper reports this score on classification datasets after feature engineering. 16 models we track have a score here.
- 1 o1-preview 43.4%
- 2
Gemini 1.5 Pro Sep 2024 35.7%
- 3
Gemini 1.5 Flash Sep 2024 33.6%
- 4 GPT-4o Aug 2024 ↑1 32.6%
- 5
DeepSeek-V2.5 Sep 2024 ↑1 32.6%
- 6 o1-mini ↓2 32.2%
- 7 GPT-4 Turbo Apr 2024 ↑4 31.9%
- 8
Llama 3.1-405B ↑1 31.9%
- 9 Claude 3.5 Sonnet ↓2 31.4%
- 10 GPT-4o May 2024 ↓2 30.5%
Improved regression
The paper reports this score on regression datasets after feature engineering. 16 models we track have a score here.
- 1 o1-preview 72.4%
- 2
Gemini 1.5 Flash Sep 2024 ↑1 63%
- 3 GPT-4o Aug 2024 ↑2 62.5%
- 4
Gemini 1.5 Pro Sep 2024 ↓2 60.8%
- 5 GPT-4o May 2024 ↑3 59.5%
- 6
DeepSeek-V2.5 Sep 2024 58.9%
- 7 GPT-4o mini ↑3 57.3%
- 8
Llama 3.1-405B ↑1 53%
- 9 GPT-4 Turbo Apr 2024 ↑2 52.1%
- 10 o1-mini ↓6 49.7%
Best
The paper reports the best result across the task types. 16 models we track have a score here.
- 1 o1-preview 19.5%
- 2 o1-mini ↑2 9.10%
- 3 Claude 3.5 Sonnet ↑4 8.30%
- 4
Gemini 1.5 Pro Sep 2024 ↓2 5.40%
- 5
Llama 3.1-70B ↑8 4.50%
- 6 GPT-4o May 2024 ↑2 3.20%
- 7 GPT-4o mini ↑3 3.10%
- 8 GPT-4 Turbo Apr 2024 ↑3 3.00%
- 9
Llama 3.1-405B 3.00%
- 10 Claude 3 Opus ↑2 2.90%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The FeatEng 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 FeatEng 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 Gemini 1.5 Pro. 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 (22 entries).
- Pass Models scored 16 models we track, plus 6 other entries on its leaderboard.
- Warning Newest score The newest came 2 years ago, in September 2024, for Gemini 1.5 Pro.
- Note Frontier models None of the top 10 has a score. The strongest tested is o1-mini (#142).
- Pass Headroom The best is 11.1%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 17 rows for models we track and 6 other entries at the last read.
- Pass Last read November 21st, 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.