GPQA DiamondVerified
80.5%
GPQA Diamond (AA run)
Models / Other
G9v3-39A5B
G9v3 · Released 2026-08-03
AI9Stars G9v3-39A5B. AA lists $0 / $0 per 1M tokens.
Open G9v3 MoE tracked on Artificial Analysis. Prefer sourced ledger rows; editorial depth is desk-pending.
Composite46
ContextUnlisted
Input / 1MFree
Output / 1MFree
Knowledge cutoffunpublished
Statuslightweight
Family profile
Best published score in each covered benchmark family.
54/100 avg
- Reasoning
- 81
- Coding
- 37
- Agentic
- 33
- Long context
- 65
4 tested benchmark families
Benchmark placements
Per-benchmark positions
Where G9v3-39A5B places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.
| Benchmark | Family | Rank | Score | Source | Date |
|---|---|---|---|---|---|
| SciCode | Coding | #87/ 97 | 37 | Artificial Analysis | 2026-09-28 |
| Terminal-Bench | Agentic | #126/ 167 | 33 | Artificial Analysis | 2026-09-28 |
| GPQA Diamond | Reasoning | #139/ 184 | 81 | Artificial Analysis | 2026-09-28 |
| Humanity's Last Exam | Reasoning | #139/ 186 | 18 | Artificial Analysis | 2026-09-28 |
| AA-LCR | Long context | #141/ 184 | 65 | Artificial Analysis | 2026-09-28 |
| AA output speed | Performance | #155/ 195 | Artificial Analysis | 2026-09-28 |
Family context
Strongest rows in each family
The three highest-scoring models with pages in each capability family. Where G9v3-39A5B shows up, it's highlighted.
ReasoningG9v3-39A5B · 81
- 196
- 295
- 395
Math
- 152
- 252
- 350
CodingG9v3-39A5B · 37
- 174
- 273
- 370
AgenticG9v3-39A5B · 33
- 191
- 289
- 389
Long contextG9v3-39A5B · 65
- 189
- 286
- 385
Newest receipts
6 recentLast 120 days
Benchmark rows added to the public ledger for G9v3-39A5B in the last 120 days. Older rows live in the full table below.
| Benchmark | Family | Score | Source | Days ago |
|---|---|---|---|---|
| AA-LCR | Long context | 65.33% | Artificial Analysis | 24 |
| AA output speed | Performance | 0 t/s | Artificial Analysis | 24 |
| GPQA Diamond | Reasoning | 80.5% | Artificial Analysis | 24 |
| Humanity's Last Exam | Reasoning | 17.5% | Artificial Analysis | 24 |
| SciCode | Coding | 36.8% | Artificial Analysis | 24 |
| Terminal-Bench | Agentic | 32.58% | Artificial Analysis | 24 |
Family coverage
Best score per family
A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.
Price vs. performance
Where G9v3-39A5B sits on the scatter
Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.
AnthropicOpenAIGoogleAlibabaMetaZhipuxAIDeepSeekMiniMaxXiaomiMoonshotOtherMeituanMistralNVIDIACohere
Full benchmark ledger
Every catalog benchmark for G9v3-39A5B. Scores link to the original source; gaps mean no public row exists yet.
6 of 13 catalog benchmarks have a sourced row for G9v3-39A5B.
Reasoning
Humanity's Last ExamVerified
17.5%
HLE (AA run)
Coding
SciCodeVerified
36.8%
SciCode (AA run)
Agentic
Terminal-BenchVerified
32.58%
Terminal-Bench v2.1 (AA run)
Long context
AA-LCRVerified
65.33%
AA-LCR (AA run)
Performance
AA output speedVerified
0 t/s
Median output tokens/s (1k prompt, default provider)
Sources
Where the numbers come from
- Artificial Analysis G9v3-39A5B· checked 2026-08-15
Questions this model page answers
Every answer below is assembled from the dated fields on this page. Nothing is written separately for search.
What is G9v3-39A5B?
G9v3-39A5B is a Other model: AI9Stars G9v3-39A5B. AA lists $0 / $0 per 1M tokens.
What is G9v3-39A5B for?
Open G9v3 MoE tracked on Artificial Analysis. Prefer sourced ledger rows; editorial depth is desk-pending.
What does G9v3-39A5B cost?
G9v3-39A5B lists Free input and Free output per 1M tokens. Pricing last checked 2026-08-15.
How large is the G9v3-39A5B context window?
G9v3-39A5B does not publish a context window on the sources checked for this page.
What is the VerdictPal status of G9v3-39A5B?
G9v3-39A5B carries Lightweight status on the model atlas.
The Pack · Editorial newsletter
Know when the rules move.
One short email when a university changes its AI rule for theses, or a research tool changes its pricing or privacy terms. No tracking, no third-party analytics. Unsubscribe in one click.