Codesota · Tasks · Vol. IICapability-first task ontologyEditorial review: October 7, 2026

§ 00 · Index

Every AI capability,
mapped to benchmark evidence.

Tasks are capabilities. Benchmarks are evidence. Domains, modalities, and safety properties are filters. This page groups 72 task pages into nine stable capability areas, then shows the canonical benchmark, recorded model, and trust grade for each row.

Reasoning, safety, robustness, multilingual coverage, and vertical domains are treated as cross-cutting overlays rather than competing top-level roots.

Browse capability areas →Compare leaderboards Check benchmark lineages

§ 01 · Counts

The register, by the numbers.

Registry view cached for 10 minutes · collection dates and protocol coverage vary

Capability areas

Stable top-level ontology

149

Tasks catalogued

72 with evidence rows

782

Datasets indexed

Canonical scope now labelled

11,851

Benchmark results

Result dates shown where recorded

§ 02 · Product map

Three different questions.

Tasks are taxonomy. Leaderboards are evidence. Lineages are benchmark history.

Tasks

Start with the problem

Use this page when you know the capability you care about: OCR, code generation, ASR, retrieval, VQA, detection.

Browse taxonomy →

Leaderboards

Then inspect the evidence

Use benchmark pages when you need result counts, source quality, trust badges, metric definitions, and current top rows.

Open leaderboards →

Lineages

Check if the benchmark still matters

Use lineage pages when a benchmark looks saturated, outdated, contaminated, or replaced by a harder successor.

View evolution →

§ 03 · Area map

Nine stable capability areas.

Domains, modalities, methods, and safety properties are filters. They do not compete with the top-level task ontology.

Code & Software Engineering

06 · 9 tasks

Agents & Tool Use

07 · 6 tasks

Structured Data & Forecasting

08 · 2 tasks

Robotics, Control & RL

09 · 3 tasks

Science, Medicine & Industry

§ 04 · Capability area

Language & Knowledge.

Language understanding, retrieval, QA, RAG, factuality, and knowledge extraction. Reasoning appears here as a capability tag, not as a separate root.

Tasks: 17
Registry verified flags: 5
Results: 583

Language & Knowledge · 17 tasks

Sorted by result count, then name

#	Task	Canonical benchmark	Recorded model	Score	Results
01	Multi-step Reasoning Multi-step reasoning — maintaining coherent inference chains across 5+ sequential steps — is the meta-capabili… reasoning lineage →	Graduate-Level Google-Proof Q&A Diamond date unknown	Claude 3.5 Sonnet Result date unknown	59.4% accuracy	161
02	Mathematical Reasoning Mathematical reasoning benchmarks — GSM8K, MATH, Minerva, and the competition-level AIME/AMC tests — have beco… math lineage →	Mathematics Aptitude Test of Heuristics date unknown	Apertus-70B-Instruct Result date unknown	30.8% accuracy	127
03	Commonsense Reasoning Commonsense reasoning — answering questions that require everyday knowledge about how the physical and social… reasoning lineage →nlp lineage →	Massive Multitask Language Understanding legacylegacyambiguous MMLU is saturated and better treated as general knowledge / legacy LLM eval, not canonical commonsense reasoning.	Claude Opus 4.6 Registry date: 2026-03-01 (unverified)	91.2% accuracy	109
04	Question Answering Question answering now spans extractive reading comprehension, open-domain retrieval QA, multi-hop reasoning,…	Natural Questions: a Benchmark for Question Answering Research date unknown	—	—	67
05	Text Embeddings Generating dense vector embeddings for retrieval, ranking, clustering, and semantic search.	Legacy MTEB English, 2024 snapshot historicallegacyambiguous NV-Embed-v2 is a historical MTEB English 56-task snapshot, not a fresh 2026 embedding frontier.	—	—	44
06	Text Summarization Text summarization compresses documents while preserving key information — a task that became dramatically mor…	CNN/DailyMail Summarization stale	Llama 3.1 405B Registry date: 2024-07-31 (unverified)	45.1% rouge-1	16
07	Logical Reasoning Logical reasoning — formal deduction, constraint satisfaction, and syllogistic inference — exposes a core weak…	LogiQA date unknown	Claude 3.5 Sonnet Result date unknown	53.8% accuracy	12
08	Text Ranking Text ranking is the invisible backbone of every search engine and RAG pipeline. The field was transformed by C…	BEIR legacy retrieval legacylegacyambiguous Legacy retrieval snapshot. Split modern retrieval, reranking, multilingual, and long-context RAG evals before calling this current SOTA.	—	—	9
09	Natural Language Inference Determining entailment relationships between sentences (SNLI, MNLI).	Stanford Natural Language Inference stale	Llama 3.1 405B Registry date: 2024-07-31 (unverified)	91.2% accuracy	8
10	Named Entity Recognition Named entity recognition (NER) extracts structured mentions — people, organizations, locations, dates — from u…	CoNLL-2003 Named Entity Recognition stale	Llama 3.1 405B Registry date: 2024-07-31 (unverified)	90.6% f1	7
11	Arithmetic Reasoning Arithmetic reasoning — solving computation-heavy problems stated in natural language — tests whether models ca…	Math Word Problem Repository date unknown	Claude 3.5 Sonnet Result date unknown	95.8% accuracy	6
12	Entity Linking Linking mentions to knowledge base entities.	AIDA-CoNLL-YAGO (test-b) date unknown	GENRE Result date unknown	93.30 micro_f1	3
13	Knowledge Graph Completion Predicting missing links in knowledge graphs.	FB15k-237 Knowledge Graph Completion date unknown	NBFNet Result date unknown	0.415 mrr	3
14	Relation Extraction Extracting relationships between entities from text.	TAC Relation Extraction Dataset date unknown	KEPLER Result date unknown	71.7% f1	3
15	Semantic Textual Similarity Semantic similarity measures how close two pieces of text are in meaning — the foundation of duplicate detecti…	STS Benchmark stale	E5-Mistral-7B-instruct Registry date: 2024-01-01 (unverified)	84.70 spearman	3
16	Table Question Answering Table question answering bridges natural language and structured data — asking "what was Q3 revenue?" over a s…	WikiTableQuestions stale	TAPAS-large Registry date: 2020-04-06 (unverified)	48.7% accuracy	3
17	Reading Comprehension Understanding and answering questions about passages.	ReAding Comprehension from Examinations date unknown	ALBERT ensemble Result date unknown	89.4% accuracy	2

Fig 04 · Each row links to the task page with full history. Shaded rows mark independently verified state of the art; empty score cells mean no benchmark in the register yet clears our trust bar.

§ 05 · Capability area

Vision & Documents.

Images, video frames, OCR, layout, tables, document parsing, detection, segmentation, and visual anomaly detection.

Tasks: 17
Registry verified flags: 2
Results: 2,326

Vision & Documents · 17 tasks

Sorted by result count, then name

#	Task	Canonical benchmark	Recorded model	Score	Results
01	Document OCR Reading text, structure, and layout from document images. ocr lineage →vision lineage →	OCRBench v2 public overall submetricdate unknownambiguous Scope is public overall. Do not compare directly with English-private OCRBench v2 or full document parsing metrics.	—	—	831
02	Scene Text Detection Detecting text regions in natural scene images	COCO-Text detection scope needs review misclassifieddate unknownmisclassified CLIP4STR-style scene text recognition rows do not belong under detection. Detection needs region metrics such as precision, recall, F-measure, or hmean.	—	—	581
03	Document Parsing Parsing document structure and content ocr lineage →	OmniDocBench v1.5 submetricdate unknownambiguous Reading order is only one OmniDocBench facet. Summary SOTA needs text, layout, table TEDS, reading order, and end-to-end structure facets.	clearOCR Result date unknown	31.70 composite	149
04	Document Layout Analysis Analyzing the layout structure of documents	d4la date unknown	—	—	133
05	Scene Text Recognition Recognizing text in natural scene images	cute80 stale	DTrOCR 105M Registry date: 2023-08-30 (unverified)	99.1% accuracy	127
06	Object Detection Object Detection is a computer vision task that involves identifying and localizing objects within an image. T… vision lineage →	Microsoft Common Objects in Context stale	ScyllaNet Registry date: 2025-09-01 (unverified)	66.12 box-map	104
07	Image Classification Image Classification is a fundamental task in computer vision that aims to assign a label or class to an entir… vision lineage →	ImageNet Large Scale Visual Recognition Challenge 2012 date unknown	AIMv2-3B Result date unknown	89.50 top-1-accuracy	87
08	Table Recognition Detecting and parsing tables in documents	ICDAR2013 table structure (legacy) legacylegacyambiguous ICDAR2013 is too narrow for 2026 table recognition. Promote PubTables-1M, PubTabNet, FinTabNet, or table-specific document parsing metrics.	—	—	71
09	General OCR Capabilities Comprehensive benchmarks covering multiple aspects of OCR performance. ocr lineage →	OCRBench v2 needs coveragedate unknownambiguous Fold this into OCR unless the metric scope is explicit: public overall, English-private, recognition, understanding, or full parsing.	—	—	70
10	Document Image Classification Classifying documents by type or category	aip date unknown	—	—	63
11	Handwriting Recognition Recognizing handwritten text	— date unknown	—	—	40
12	Document Understanding Document understanding requires parsing visually rich documents — invoices, forms, scientific papers, tables —… ocr lineage →	Form Understanding in Noisy Scanned Documents date unknown	—	—	28
13	Semantic Segmentation Semantic segmentation assigns a class label to every pixel — the dense prediction problem that underpins auton… vision lineage →	ADE20K Scene Parsing Benchmark date unknown	BEiT-3 (ViT-L) Result date unknown	62.8% mIoU	24
14	Video classification The task of classifying videos into predefined categories or classes. Video classification involves analyzing…	Kinetics-400 date unknown	—	—	13
15	Image segmentation Image segmentation is a computer vision technique that divides a digital image into multiple parts or "segment…	— date unknown	—	—	3
16	Keypoint Detection Keypoint detection localizes specific anatomical or structural landmarks — body joints, facial features, hand…	COCO Keypoints date unknown	ViTPose-G Result date unknown	80.9% map	1
17	OCR OCR, or Optical Character Recognition, is the task of converting an image containing text into machine-readabl…	— date unknown	—	—	1

Fig 05 · Each row links to the task page with full history. Shaded rows mark independently verified state of the art; empty score cells mean no benchmark in the register yet clears our trust bar.

§ 06 · Capability area

Audio & Speech.

ASR, TTS, speaker intelligence, music, sound events, audio-language understanding, and audio safety.

Tasks: 7
Registry verified flags: 1
Results: 545

Audio & Speech · 7 tasks

Sorted by result count, then name

#	Task	Canonical benchmark	Recorded model	Score	Results
01	Speech Recognition Automatic speech recognition went from a specialized pipeline (acoustic model + language model + decoder) to a… audio lineage →speech lineage →	Mozilla Common Voice stale	Whisper Large v2 Registry date: 2022-12-06 (unverified)	11.20 wer	526
02	Audio Captioning Generating text descriptions of audio content.	AudioCaps historicaldate unknownambiguous Baseline-style AudioCaps rows should not read as current leading audio-language SOTA without a refresh.	AudioCaps baseline (TopDown+Align) Result date unknown	36.9% spider	7
03	Music Generation Generating music from text, audio, or other inputs.	MusicCaps historicaldate unknownambiguous MusicLM is historically important, but this needs MusicCaps/MusicBench, human eval, and proprietary/open splits.	MusicGen Large Result date unknown	3.800 fad	3
04	Sound Event Detection Detecting and localizing sound events in audio.	Domestic Environment Sound Event Detection (DCASE Task 4) date unknown	ATST-SED Result date unknown	58.10 event-f1	3
05	Speaker Verification Verifying speaker identity from voice samples.	VoxCeleb1 Original Test Set (VoxCeleb1-O) date unknown	ECAPA-TDNN Result date unknown	0.870 eer	3
06	Speech Translation Translating spoken audio directly to another language.	MuST-C English-German tst-COMMON date unknown	Fairseq S2T (MuST-C) Result date unknown	22.7% bleu	3
07	Speech Enhancement Recovering clean speech from noisy recordings. Benchmarked on VoiceBank+DEMAND (PESQ, STOI, SI-SDR) and the Mi… audio lineage →speech lineage →	— date unknown	—	—	0

Fig 06 · Each row links to the task page with full history. Shaded rows mark independently verified state of the art; empty score cells mean no benchmark in the register yet clears our trust bar.

§ 07 · Capability area

Multimodal Media.

Cross-modal tasks only: VQA, image-text retrieval, video QA, document VQA, text-to-image, image editing, and any-to-any media models.

Tasks: 4
Registry verified flags: 1
Results: 206

Multimodal Media · 4 tasks

Sorted by result count, then name

#	Task	Canonical benchmark	Recorded model	Score	Results
01	Visual Question Answering Visual question answering (VQA) is the original multimodal reasoning task — given an image and a natural langu… multimodal lineage →vqa lineage →	Visual Question Answering v2.0 stale	GPT-4o Registry date: 2024-10-25 (unverified)	78.5% accuracy	147
02	Video Understanding Video understanding asks models to reason over temporal sequences — answering questions, generating summaries,…	MVBench date unknown	LongCat-Flash-Omni Result date unknown	75.2% accuracy	44
03	Text-to-Image Generation Text-to-image generation went from "interesting research" to cultural phenomenon in 18 months. DALL-E 2 (2022)… multimodal lineage →vision lineage →	DPG-Bench date unknown	—	—	8
04	Image Captioning Image captioning — generating natural language descriptions of images — was the task that launched the modern… multimodal lineage →vision lineage →	COCO Captions legacylegacyambiguous COCO captioning is legacy and saturated. Add NoCaps, Flickr30k, caption QA, or preference-based caption evals.	Chameleon-SFT Result date unknown	140.8% cider	7

Fig 07 · Each row links to the task page with full history. Shaded rows mark independently verified state of the art; empty score cells mean no benchmark in the register yet clears our trust bar.

§ 08 · Capability area

Code & Software Engineering.

Code generation, completion, repair, repository understanding, tests, vulnerability work, UI code, and mobile app code generation.

Tasks: 7
Registry verified flags: 5
Results: 337

Code & Software Engineering · 7 tasks

Sorted by result count, then name

#	Task	Canonical benchmark	Recorded model	Score	Results
01	Code Generation Generating code from natural language descriptions (HumanEval, MBPP). coding lineage →	LiveCodeBench date unknown	—	—	270
02	React Native Code Generation Evaluating AI models on generating correct, production-quality React Native implementations. Covers animation,…	Callstack Incubator React Native Evaluation Suite date unknown	Claude Opus 4.6 Result date unknown	84.36 requirement-satisfaction	40
03	Code Translation Converting code between programming languages.	TransCoder Evaluation on GeeksForGeeks Algorithmic Problems stale	Qwen2.5-Coder 32B Registry date: 2024-09-19 (unverified)	86.30 computational-accuracy	7
04	Bug Detection Identifying bugs and vulnerabilities in code.	Bugs2Fix: Learning to Rewrite Buggy Code stale	Qwen2.5-Coder 32B Registry date: 2024-09-19 (unverified)	76.8% accuracy	6
05	Code Completion Predicting the next tokens in code sequences.	Cross-File Code Completion Evaluation stale	Qwen2.5-Coder 32B Registry date: 2024-09-19 (unverified)	43.70 exact-match	6
06	Program Repair Automatically fixing bugs in code.	Defects4J: A Database of Real Faults in Java Programs stale	GPT-4o Registry date: 2024-04-18 (unverified)	82.00 correct-patches	5
07	Code Summarization Generating natural language descriptions of code.	CodeXGLUE Code-to-Text Python subset date unknown	CodeBERT Result date unknown	19.1% bleu	3

Fig 08 · Each row links to the task page with full history. Shaded rows mark independently verified state of the art; empty score cells mean no benchmark in the register yet clears our trust bar.

§ 09 · Capability area

Agents & Tool Use.

Tool calling, web and desktop agents, browser automation, long-horizon autonomy, multi-agent coordination, and agent safety.

Tasks: 9
Registry verified flags: 6
Results: 225

Agents & Tool Use · 9 tasks

Sorted by result count, then name

#	Task	Canonical benchmark	Recorded model	Score	Results
01	SWE-bench SWE-bench — resolving real GitHub issues from popular Python repositories — became the defining benchmark for… coding lineage →agentic lineage →	SWE-bench Verified — Agentic Leaderboard date unknown	Claude 3.5 Haiku Result date unknown	40.60 resolve-rate	81
02	Task agents AI agents are autonomous software systems that use artificial intelligence to achieve goals and complete tasks…	Collider-Bench simulation tasks date unknown	Claude Code (Haiku 4.5) Result date unknown	0.000 acc-tau-0-33	45
03	Web & Desktop Agents Web and desktop agents — AI systems that operate browsers and GUIs to complete real tasks — are benchmarked by…	OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments stale	Claude Computer Use Registry date: 2024-04-11 (unverified)	14.90 success-rate	39
04	Autonomous Coding Agent benchmarks where systems complete coding, terminal, repository, or developer-workflow tasks with minimal…	SWE-bench Verified (Agentic) date unknown	Claude Opus 4.5 Result date unknown	80.90 pct_resolved	23
05	Tool Use Benchmarks measuring AI agents ability to use tools and APIs to complete real-world tasks across domains like…	— date unknown	—	—	19
06	HCAST HCAST (Human-Calibrated Autonomy Software Tasks) is a 90-task benchmark from METR designed to measure AI auton…	Human-Calibrated Autonomy Software Tasks stale	Claude 3.5 Sonnet Registry date: 2025-04-01 (unverified)	18.00 success-rate	6
07	RE-Bench RE-Bench (Research Engineering Benchmark) from METR evaluates AI agents on 7 open-ended ML research engineerin…	Research Engineering Benchmark stale	Claude 3.7 Sonnet Registry date: 2025-04-01 (unverified)	0.290 normalized-score	5
08	Time Horizon Time horizon — how long an AI agent can work autonomously before requiring human correction — is arguably the…	METR Autonomy Evaluation: Time Horizon stale	Claude 3.7 Sonnet Registry date: 2025-04-01 (unverified)	14.00 task-horizon-minutes	5
09	Bioinformatics Agents LLM-agent benchmarks for computational biology — exploring datasets, running multi-step analyses, and interpre…	— date unknown	—	—	2

Fig 09 · Each row links to the task page with full history. Shaded rows mark independently verified state of the art; empty score cells mean no benchmark in the register yet clears our trust bar.

§ 10 · Capability area

Structured Data & Forecasting.

Tables, tabular classification and regression, time-series forecasting, anomaly detection, recommender systems, graph learning, and optimization.

Tasks: 6
Registry verified flags: 3
Results: 19

Structured Data & Forecasting · 6 tasks

Sorted by result count, then name

#	Task	Canonical benchmark	Recorded model	Score	Results
01	Node Classification Node classification — assigning labels to vertices in a graph using both node features and neighborhood struct…	Cora Citation Network stale	ACNet Registry date: 2019-04-07 (unverified)	83.5% accuracy	6
02	Tabular Classification Tabular classification — predicting discrete labels from structured rows and columns — remains the one domain…	OpenML-CC18 stale	AutoGluon-Tabular Registry date: 2025-06-01 (unverified)	88.5% accuracy	5
03	Link Prediction Link prediction — inferring missing or future edges in a graph — underpins knowledge graph completion, drug-ta…	Open Graph Benchmark - ogbl-collab date unknown	BUDDY Result date unknown	65.94 hits_at_50	3
04	Molecular Property Prediction Molecular property prediction — estimating toxicity, solubility, binding affinity, or other properties from mo…	Open Graph Benchmark - ogbg-molhiv date unknown	DGN Result date unknown	79.70 roc_auc	3
05	Tabular Regression Tabular regression — predicting continuous values from structured data — powers everything from house-price es…	California Housing date unknown	LightGBM Result date unknown	0.433 rmse	2
06	Tabular Machine Learning Classification and regression on tabular data. Benchmarked on TabArena (Elo over 51 datasets); gradient-booste…	— date unknown	—	—	0

Fig 10 · Each row links to the task page with full history. Shaded rows mark independently verified state of the art; empty score cells mean no benchmark in the register yet clears our trust bar.

§ 11 · Capability area

Robotics, Control & RL.

Game playing, continuous control, manipulation, navigation, embodied instruction following, VLA models, drones, and autonomous driving.

Tasks: 2
Registry verified flags: 0
Results: 21

Robotics, Control & RL · 2 tasks

Sorted by result count, then name

#	Task	Canonical benchmark	Recorded model	Score	Results
01	Atari Games Atari games became the canonical RL benchmark when DeepMind's DQN (2013) learned to play Breakout from raw pix…	Arcade Learning Environment (Atari 2600) legacylegacy Classic RL benchmark. Keep separate from modern embodied, VLA, robotics manipulation, and navigation tasks.	Agent57 Result date unknown	4731.3 human-normalized-score	12
02	Continuous Control Continuous control — learning smooth motor commands in simulated physics — was transformed by MuJoCo and the O…	Multi-Joint dynamics with Contact submetricdate unknownambiguous MuJoCo control is a narrow simulation slice. Split from robotics manipulation, navigation, and VLA evaluations.	BRO Result date unknown	941.0 average-return	9

Fig 11 · Each row links to the task page with full history. Shaded rows mark independently verified state of the art; empty score cells mean no benchmark in the register yet clears our trust bar.

§ 12 · Capability area

Science, Medicine & Industry.

A domain layer for medical imaging, clinical text, drug discovery, protein modeling, industrial inspection, remote sensing, climate, legal, finance, and compliance AI.

Tasks: 3
Registry verified flags: 3
Results: 110

Science, Medicine & Industry · 3 tasks

Sorted by result count, then name

#	Task	Canonical benchmark	Recorded model	Score	Results
01	Disease Classification Diagnosing diseases from medical images or data.	Autism Brain Imaging Data Exchange I claim-onlystaleambiguous High ABIDE accuracy claims are leakage-risk until subject-level split, site-held-out validation, preprocessing, confound control, and external validation are verified.	ChebGAT-GCN Registry date: 2025-11-27 (unverified)	74.8% accuracy	57
02	Anomaly Detection Detecting defects and anomalies in manufacturing (MVTec AD, VisA).	MVTec Anomaly Detection Dataset submetricstaleambiguous MVTec AD rows must split image-level classification, pixel-level localization, zero/few/full-shot, and AUROC/AUPRO metric scopes.	AnomalyGPT Registry date: 2023-08-29 (unverified)	97.40 auroc	27
03	Medical Image Segmentation Segmenting organs and abnormalities in medical images.	Automated Cardiac Diagnosis Challenge stale	LightM-UNet Registry date: 2024-03-04 (unverified)	90.49 mean-dsc	26

Fig 12 · Each row links to the task page with full history. Shaded rows mark independently verified state of the art; empty score cells mean no benchmark in the register yet clears our trust bar.

§ 13

Trust grades

What the letters mean.

Benchmarks are not equally believable. Some are held out behind a private evaluator; some ship their test set as part of the training corpus. We grade the canonical dataset of every task on a four-point scale and show the letter next to the score.

Reproduced · dated · code

The full path is visible: a public checkpoint, a frozen commit, a declared environment, and a score we (or a signed reproducer) ran against a held-out test set. Contamination controlled, metric direction declared, date stamped.

Partial reproduction

Known weaknesses — evaluator overlap, public answer keys, a missing seed — but the submission otherwise checks out. Cite with caution; we preserve the caveat alongside the number.

Claim-only

The authors say so. We have not reproduced it and cannot yet. Shown in the register for completeness, but do not treat as state of the art.

Contested or retracted

The benchmark is considered unreliable: documented contamination, split leakage, or a score withdrawn by its authors. The row remains visible — leaderboards that silently forget are worse than leaderboards that argue in public.

A dataset can be regraded in public at any time; the history is preserved on the benchmark page. We publish the regrade, we don't erase the prior.

§ 14 · Standing columns

Capability buckets, not benchmarks.

HuggingFace pipeline-tag categories. These group concrete tasks thematically; they are not themselves measurable. Use them to navigate to the real rankings.

Standing column

Any-to-Any (Omni)

True omni: any modality in (text + image + audio + video) AND generate multiple modalities out (including speech, not just text). Narrowest open-weights category — Qwen3-Omni · Vita · Mini-Omni. Proprietary: GPT-4o · Gemini 3 · Sesame CSM.

Standing column

Image + Text → Text (VLMs)

Vision-Language Models that read images and produce text answers.

Standing column

Image + Text → Image

Image editing and inpainting conditioned on text prompts.

Text-to-Image (when added) →

Standing column

Image + Text → Video

Animate a still image guided by a text prompt.

Text-to-Video →

Standing column

Audio + Text → Text (Speech LLMs)

Multimodal LLMs that listen and respond in text.

Standing column

Audio → Audio

Speech translation, voice conversion, audio enhancement.

Standing column

Video → Video

Video editing, style transfer, super-resolution.

Text-to-Video →

Standing column

Image → 3D

Generate a 3D mesh or NeRF from one or more images.

Text-to-3D →

Standing column

Text → 3D

Generate a 3D asset from a text prompt.

Image-to-3D →

Standing column

Text → Audio

Music, sound effects, environmental audio from text.

Standing column

Image → Video

Animate a still image into a short clip.

Text-to-Video →

Standing column

Unconditional Image Generation

Generative image models without text conditioning (DCGAN, StyleGAN era).

Text-to-Image →

Fig 14 · Standing columns exist to aid navigation, not to be ranked. Follow any link to the underlying task's leaderboard.

§ 15

Methodology

Why this register can be trusted.

Most leaderboards are a ledger of claims. Authors submit a number, a banner appears; the number stands until the next banner appears. Codesota is different in three ordinary ways.

First, every submission carries code. Not a repo link alone — a frozen commit, a declared environment, a recorded seed. If it does not run, the row does not publish.

Second, every benchmark has a metric direction. Higher-is-better and lower-is-better are declared on the dataset; no ambiguity reaches the reader.

Third, every score carries a date. When a model regresses — and they do — the record is preserved. The table never silently forgets.

Full methodology →Read the issue Missing a task? Propose it.

Every AI capability,mapped to benchmark evidence.

The register, by the numbers.

Three different questions.

Start with the problem

Then inspect the evidence

Check if the benchmark still matters

Nine stable capability areas.

Language & Knowledge.

Vision & Documents.

Audio & Speech.

Multimodal Media.

Code & Software Engineering.

Agents & Tool Use.

Structured Data & Forecasting.

Robotics, Control & RL.

Science, Medicine & Industry.

What the letters mean.

Capability buckets, not benchmarks.

Any-to-Any (Omni)

Image + Text → Text (VLMs)

Image + Text → Image

Image + Text → Video

Audio + Text → Text (Speech LLMs)

Audio → Audio

Video → Video

Image → 3D

Text → 3D

Text → Audio

Image → Video

Unconditional Image Generation

Why this register can be trusted.

Every AI capability,
mapped to benchmark evidence.