Evalio

Evaluate.
Compare.
Explore data.
Make better decisions.

Benchmark models, track every evaluation run, and turn raw results into confident choices.

Projects

Name DatasetsModelsUpdated
LLM Benchmarking128May 12
Vision Eval Suite95May 10
RAG Evaluation73May 8
Internal Tests42May 6
1–4 of 4

LLM Benchmarking

Recent Evaluations

May 12GPT-4o on MMLU72.1
May 11Claude 3.5 on MMLU64.8
May 10Llama 3 70B on GSM8K61.3
May 10Gemini 1.5 Pro on TruthfulQA55.7

Leaderboard · Top 5

1GPT-4o72.1
2Claude 3.564.8
3Llama 3 70B61.3
4Mistral Large58.2
5Gemini 1.5 Pro55.7

Results

DatasetModel ScorePrice / 1K tokUpdated
1–5 of 5

Evaluation Tasks

To Do 3
Run MMLU on Gemini 1.5
ARMay 14
Analyze new dataset
JMMay 15
QA review
ARMay 16
In Progress 2
Run Llama 3 70B on GSM8K
JMMay 12
Analyze results
ARMay 12
Done 4
Run GPT-4o on MMLU
ARMay 12
Run Claude 3.5 on MMLU
JMMay 12
Baseline comparison
ARMay 11
Prompt regression suite
JMMay 10

File Manager

datasetsMay 12
resultsMay 11
benchmark_report.pdfMay 10
pricing_snapshot.csvMay 9
notes.txtMay 8
Trash is empty
1–5 of 5

Notification Center

Evaluation completedGPT-4o on MMLU finished with score 72.1
2m
New comment on “LLM Benchmarking”@alex left a comment: “GSM8K numbers look off, can we re-run?”
1h
Evaluation failedGemini 1.5 Pro on GSM8K hit a rate limit — retrying
3h
You're all caught up — no unread notifications.

Settings

Profile

How you appear across your workspace.

AR
Alex Riveraalex@evalio.io · Admin

Project created!

“Multimodal Eval” has been successfully created and is ready for its first evaluation.