Text Industrial Code Multi
Leaderboard Tasks How MERA works
Return to the leaderboard

GPT-5.4

MERA Created at 03.04.2026 10:15

Ratings for leaderboard tasks

The table will scroll to the left

Task name Result Place in the rating
Agricultural industry 0.759 1
Medicine and healthcare 0.834 3

ruTXTAgroBench

Metric: F1, Exact Match

Discipline Result
Botany 0.89
General genetics 0.835
The basics of breeding 0.869
Crop production 0.735
General agriculture 0.73
Reclamation farming 0.659
Seed production and seed science 0.74
Forage production and meadow farming 0.674
Farming systems on various agricultural landscapes 0.733
Technologies of cultivation of agricultural crops 0.806

ruTXTAquaBench

Metric: F1, Exact Match

Discipline Result
Industrial aquaculture 0.749
Feeding of fish and other aquatic organisms 0.722
Mariculture. Breeding of crayfish and shrimps. Artificial pearl cultivation 0.653
Ichthyopathology: veterinary medicine, prevention and optimization of fish farming technologies 0.593

ruTXTMedQFundamental

Metric: F1, Exact Match

Discipline Result
Anatomy 0.874
Hygiene 0.8
Histology 0.811
Biophysics 0.837
Biochemistry 0.826
Microbiology 0.833
Biology (parasitology) 0.811
Pharmacology 0.848
Faculty Surgery 0.811
General Surgery 0.815
General chemistry 0.744
Normal physiology 0.844
Bioorganic chemistry 0.819
Pathological anatomy 0.785
Pathophysiology 0.819
Clinical laboratory diagnostics 0.822
Propaedeutics in internal medicine 0.848

Information about the submission

Mera version
v1.0.0
Torch Version
2.10.0
The version of the codebase
0ac3a14
CUDA version
12.8
Precision of the model weights
auto
Seed
1234
Batch
1
Transformers version
4.57.6
The number of GPUs and their type
1 x NVIDIA A100-SXM4-80GB
Architecture
openai-chat-completions

Team:

MERA

Name of the ML model:

GPT-5.4

Link to the ML model:

https://openai.com/ru-RU/index/introducing-gpt-5-4/

Model type:

Closed

License:

Proprietary

Inference parameters

Generation Parameters:
aqua_bench - do_sample=false;until=[];max_gen_toks=32768;reasoning={"enabled":true,"effort":"high","exclude":false}; \nmed_bench - do_sample=false;until=[];max_gen_toks=32768;reasoning={"enabled":true,"effort":"high","exclude":false}; \nagro_bench - do_sample=false;until=[];max_gen_toks=32768;reasoning={"enabled":true,"effort":"high","exclude":false};

MERA

Useful links

© 2025 MERA. All rights reserved.
User agreement Privacy policy

We use cookies to store data. By continuing to use the site, you consent to work with these files