DeepSWE benchmarks coding agents on long-horizon software engineering tasks and publishes a leaderboard.
EQ-Bench
EQ-Bench publishes benchmarks for emotional intelligence, long-form writing, creative writing, and other model evaluations.

About EQ-Bench
EQ-Bench publishes leaderboards comparing language models on emotional and social intelligence, longform writing, creative writing and other evaluations. The main EQ-Bench 4 leaderboard assesses models in multi-turn roleplay chats with a simulated persona user, ranked by blind pairwise judging into Elo scores. The site provides rankings, scoring explanations, transcripts and links to papers and code.
Pricing is not clearly stated.
Key features
- Ranked EQ-Bench 4 leaderboard with Elo scores
- Persona based multi-turn roleplay scenarios
- Published transcripts with persona emotional state
- Explanations of six ability dimensions and scoring method
- Additional Spiral-Bench, writing, Judgemark, BuzzBench and DiploBench leaderboards
- Links to paper and GitHub repositories
EQ-Bench at a glance
- Website
- eqbench.com
- Category
- AI & Machine Learning › AI Data & Analytics
- Type
- Website
- Pricing
- Not confirmed. Check the site
- Platforms
- Web
- Details verified
- Oct 22, 2026 · Official source
- Open source
- Not stated
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
EQ-Bench alternatives
Tools and sites you could use instead, ranked by how closely they match.
SWE-bench publishes benchmark leaderboards for evaluating software engineering agents.
BlockSurvey creates privacy-first forms and surveys with end-to-end encrypted responses, plus AI-assisted question writing.
RankedAGI compares AI models using benchmarks including SWE Bench, Codeforces, LMSYS, and LiveBench.
MathArena evaluates language models using math benchmarks and publishes model results.
Kaggle Benchmarks lets users build, run, and share evaluations of AI models and agents.
Popular in AI Data & Analytics
Well-known listings from the same topic.
Tell us and an editor will check it.
Claim the listing and suggest updates yourself. An editor checks every claim first.











