MDL
G9v3-3B
AI9Stars
Verified against Artificial Analysis · Jul 27, 2026
Capability
43
percentile index
Price /M
$0 / $0
in / out
Context
—
Avg score
25.1
4 benchmarks
AA Intelligence
16.1
index
Weights
Closed
Released
Jul 23, 2026
About
G9v3-3B is a proprietary model in the G9v3 family from AI9Stars. Benchmarked on 4 evals, averaging 25.1.
Benchmark scores · 4
avg 25.1 — higher is betterPerformance & price
Price in / out$0 / $0 per 1M
Coding index9.9
Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →
History
full ledger →GPQA Diamondfirst seen at 43.8
yesterday
Humanity's Last Examfirst seen at 4
yesterday
SciCodefirst seen at 17.7
yesterday
AA Long-Context Reasoningfirst seen at 34.7
yesterday
Append-only ledger — every observed change to this model's numbers.
API providers
Artificial Analysis$0/M