MDL
DeepSeek V3.1
DeepSeek
Verified against Artificial Analysis · Jul 13, 2026
Capability
63
percentile index
Price /M
$0.56 / $1.68
in / out
Context
—
Avg score
44.9
10 benchmarks
AA Intelligence
21.0
index
Weights
Open
Released
Aug 21, 2025
About
DeepSeek V3.1 is a open-weights model in the DeepSeek family from DeepSeek. Benchmarked on 10 evals, averaging 44.9.
Benchmark scores · 10
avg 44.9 — higher is betterThe research behind this model
all papers mentioning it →SWE-Mutation: Can LLMs Generate Reliable Test Suites in Software Engineering?May 21, 2026Persona-Model Collapse in Emergent MisalignmentMay 13, 2026NSMQ Riddles: A Benchmark of Scientific and Mathematical Riddles for Quizzing Large Language ModelsMay 8, 2026How Does Thinking Mode Change LLM Moral Judgments? A Controlled Instant-vs-Thinking Comparison Across Five Frontier ModelsMay 6, 2026EQUITRIAGE: A Fairness Audit of Gender Bias in LLM-Based Emergency Department TriageMay 5, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.
Performance & price
Price in / out$0.56 / $1.68 per 1M
Blended price$0.84 / 1M
Math index49.7
Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →
History
full ledger →Capability over time
Append-only ledger — every observed change to this model's numbers.
API providers
Artificial Analysis$1.68/M