MMODELYST
Models/DeepSeek V3.1
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 better
MMLU-Pro
83.3
GPQA Diamond
73.5
LiveCodeBench
57.7
AIME
49.7
AA Long-Context Reasoning
45
IFBench
37.8
SciCode
36.7
τ²-bench
34.8
Terminal-Bench Hard
24.2
Humanity's Last Exam
6.3
Details
PublisherDeepSeek
FamilyDeepSeek
Parameters
License
WeightsOpen
ReleasedAug 21, 2025
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 →

Capability over time

Append-only ledger — every observed change to this model's numbers.

API providers
Artificial Analysis$1.68/M