DeepSeek V3.2 — Benchmarks

ARC-AGI-2 is the second-generation ARC Prize puzzle set, rebuilt so that tasks solved by brute-force search or memorization were removed and every problem still requires inferring a novel rule from a handful of examples. It is markedly harder than the original ARC-AGI, and most models — open and closed alike — score near zero.

ARC-AGI tests fluid, abstract reasoning on small visual grid puzzles where each task follows a novel rule the model must infer from a few examples. It deliberately resists memorization and is one of the most-watched measures of general reasoning progress.

APEX-Agents (AI Productivity Index) is Mercor's evaluation of AI agents on long-horizon, multi-application professional-services work — investment-banking, management-consulting, and corporate-law style tasks — graded against expert-produced solutions. The score is Pass@1, the fraction solved correctly on the first attempt.

CL-bench, built by Tencent Hunyuan and Fudan University's NLP group, tests whether a model can learn new domain knowledge, rule systems and procedures purely from a long provided context — not from pretraining — and apply them correctly, across 1,899 tasks drawn from 500 scenarios. An LLM judge grades each task against dozens of fine-grained rubrics, and a task counts as solved only when every rubric passes.

CL-bench Life, a follow-up from the CL-bench authors, tests the same context-learning skill on messier real-life material — fragmented notes, casual conversations, and behavioral logs — across 405 human-curated context-task pairs. It uses the same rubric-based LLM-judge scoring as CL-bench, requiring every rubric on a task to pass for it to count as solved.

DTBench is a set of handcrafted, expert-validated multiple-choice questions on decision theory — Newcomb-like problems and related puzzles — built by the Conceptual Reasoning Index project with Anthropic. It tests whether a model can follow an abstract argument rather than recall a fact.

LMCA (Language Model Conceptual Argumentation) scores models on expert-rated arguments across philosophy, decision theory, and AI risk — domains where there is no empirical feedback loop to check an answer against. It is part of the Conceptual Reasoning Index, built with Anthropic by researchers Emery Cooper and Caspar Oesterheld.

SWE-bench Verified tests whether a model can resolve real GitHub issues from popular open-source Python projects, scored on the official swebench.com leaderboard as the percentage of human-validated issues actually fixed. It is the headline measure of practical, agentic software-engineering ability — where open-weight models like Qwen3-Coder, GLM-4.6, Kimi K2 and DeepSWE are now competitive with the frontier.

Terminal-Bench measures whether a model can complete real, end-to-end tasks in a command-line environment — running commands, editing files, and chaining steps — making it an agentic test of practical software skill.

SWE-bench Multilingual extends SWE-bench beyond Python to real GitHub issues across many programming languages, measuring whether a model can fix bugs in codebases written in Java, Go, Rust, TypeScript and more.

SWE-bench Bash Only runs the SWE-bench Verified issues through a minimal, single-tool bash agent — no specialised scaffolding — so the score reflects the model's own agentic coding ability rather than the harness around it. A cleaner, harder read on raw software-engineering skill.

SWE-bench Lite is a smaller, lower-cost subset of SWE-bench focused on self-contained bug fixes. It is the quickest of the SWE-bench boards to run and a common entry point for comparing coding agents.

ProofBench evaluates a model's ability to write and check rigorous mathematical proofs, rather than just produce a final numeric answer. It probes step-by-step logical correctness, which is a harder and more distinct skill than solving for a number.

MMLU-Pro is a harder, cleaned-up successor to MMLU with ten answer choices and more reasoning-heavy questions across 14 subjects, measuring broad knowledge and reasoning together.

Arena (arena.ai, formerly LMArena / Chatbot Arena) ranks models by millions of blind, head-to-head human votes on real prompts. The Arena Score shown here is a Bradley-Terry rating computed with Arena's default style control, so higher means people preferred that model's answers more often — it's a relative rating, not a percentage, so compare it only to other models on this board.