MDL
DeepSeek V3.1 Terminus
DeepSeek
Verified against Artificial Analysis · Jul 13, 2026
Capability
81
percentile index
Price /M
$1.635 / $2.75
in / out
Context
163.8K
tokens
Avg score
57.9
10 benchmarks
AA Intelligence
30.4
index
Weights
Open
Released
Sep 22, 2025
About
DeepSeek V3.1 Terminus is a open-weights model in the DeepSeek family from DeepSeek. Benchmarked on 10 evals, averaging 57.9.
Benchmark scores · 10
avg 57.9 — 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$1.635 / $2.75 per 1M
Blended price$1.91 / 1M
Coding index43.5
Math index89.7
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$2.75/M