DeepSeek Chat

DeepSeek · deepseek/deepseek-chat

Provider	DeepSeek
Family	deepseek
Type	llm-chat
Status	active
Released	2025-12-01
Updated	2026-02-28

Reported benchmark scores

These scores carry one collection date for the whole card (2026-04) and a source list rather than a source per score, so they cannot be attributed individually. They are shown as reported and are not verified evidence. Benchmark pages carry the reviewed, dated evidence where it exists.

Benchmark	Catalogue standing	Score
Aider Polyglot Benchmark	unassessed	58.5
AlpacaEval	unassessed	42.8
Arena Elo — Coding	unassessed	1320.0
Arena Elo — Math	unassessed	1300.0
Arena Elo — Overall (Text)	unassessed	1310.0
BIG-Bench Hard	unassessed	64.1
BBQ (Bias Benchmark for QA)	unassessed	73.5
GPQA Diamond	unassessed	59.1
GSM8K	unassessed	89.3
HELM Safety	unassessed	78.2
HumanEval	unassessed	85.8
IFEval	unassessed	84.0
LiveCodeBench	unassessed	59.3
MATH-500	unassessed	89.2
MMLU-Pro	unassessed	75.5
MT-Bench	unassessed	8.8
MultiPL-E: C#	unassessed	76.2
MultiPL-E: Julia	unassessed	56.8
MultiPL-E: Kotlin (unconfirmed)	unassessed	67.5
MultiPL-E: Lua	unassessed	50.5
MultiPL-E: Perl	unassessed	45.2
MultiPL-E: PHP	unassessed	73.5
MultiPL-E: R	unassessed	52.5
MultiPL-E: Ruby	unassessed	60.5
MultiPL-E: Scala	unassessed	55.8
MultiPL-E: Swift	unassessed	60.2
MuSR	unassessed	29.8
SWE-bench Agent	unassessed	35.8
SWE-bench Verified	unassessed	42.5
τ-bench	unassessed	41.2
Terminal-Bench	unassessed	37.7
Terminal-Bench 2.0	unassessed	46.4
ToxiGen	unassessed	82.5
WildBench	unassessed	70.2

Data

This card as JSON · Edit on GitHub