MMODELYST
Models/Apertus 8B Instruct
MDL

Apertus 8B Instruct

Swiss AI Initiative

Verified against Artificial Analysis · Jul 13, 2026
Capability
23
percentile index
Price /M
$0.1 / $0.2
in / out
Context
Avg score
9.8
7 benchmarks
AA Intelligence
1.0
index
Weights
Closed
Released
Sep 2, 2025
About

Apertus 8B Instruct is a proprietary model in the Apertus family from Swiss AI Initiative. Benchmarked on 7 evals, averaging 9.8.

Benchmark scores · 7
avg 9.8 — higher is better
GPQA Diamond
25.6
IFBench
22.4
τ²-bench
11.4
Humanity's Last Exam
5
SciCode
4.1
Terminal-Bench Hard
0
AA Long-Context Reasoning
0
The research behind this model
all papers mentioning it →

Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.

Details
FamilyApertus
Parameters
License
WeightsClosed
ReleasedSep 2, 2025
Performance & price
Price in / out$0.1 / $0.2 per 1M
Blended price$0.125 / 1M

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$0.2/M