Humanity's Last ExamVerified
43.1%
HLE (AA run)
Models / xAI
Grok 4.7
Grok · Released 2026-09-21
xAI's 21 Sep 2026 Grok model for coding and knowledge work. API list starts at $2 / $6 per 1M tokens, 500k context. Text and image in, text out. No AA or Vals ledger row on this page as of 23 Sep 2026.
Current xAI line for agentic coding and knowledge work. Grok 4.6 stays on the atlas at the same starting list.
Composite57
Context500K
Input / 1M$2.0
Output / 1M$6.0
Knowledge cutoffunpublished
Output speed84 t/s
Statusflagship
Family profile
Best published score in each covered benchmark family.
59/100 avg
- Reasoning
- 43
- Coding
- 57
- Long context
- 77
3 tested benchmark families
Editor's note
Recorded from the 21 Sep 2026 launch post and the model docs (500k context, text and image in, text out). The launch post says consumer web and mobile come later; day-one surfaces named there are Cursor, Grok Build, the API, and gateways. Vendor benchmark tables stay off the ledger. Editorial depth still needs a desk pass.Benchmark placements
Per-benchmark positions
Where Grok 4.7 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 | #11/ 97 | 57 | Artificial Analysis | 2026-09-28 |
| Humanity's Last Exam | Reasoning | #24/ 186 | 43 | Artificial Analysis | 2026-09-28 |
| AA-LCR | Long context | #76/ 184 | 77 | Artificial Analysis | 2026-09-28 |
| AA output speed | Performance | #78/ 195 | Artificial Analysis | 2026-10-12 |
Family context
Strongest rows in each family
The three highest-scoring models with pages in each capability family. Where Grok 4.7 shows up, it's highlighted.
ReasoningGrok 4.7 · 43
- 196
- 295
- 395
Math
- 152
- 252
- 350
CodingGrok 4.7 · 57
- 174
- 273
- 370
Long contextGrok 4.7 · 77
- 189
- 286
- 385
Newest receipts
4 recentLast 120 days
Benchmark rows added to the public ledger for Grok 4.7 in the last 120 days. Older rows live in the full table below.
| Benchmark | Family | Score | Source | Days ago |
|---|---|---|---|---|
| AA output speed | Performance | 84 t/s | Artificial Analysis | 4 |
| AA-LCR | Long context | 76.67% | Artificial Analysis | 18 |
| Humanity's Last Exam | Reasoning | 43.1% | Artificial Analysis | 18 |
| SciCode | Coding | 57.4% | Artificial Analysis | 18 |
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 Grok 4.7 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 Grok 4.7. Scores link to the original source; gaps mean no public row exists yet.
4 of 13 catalog benchmarks have a sourced row for Grok 4.7.
Reasoning
Coding
SciCodeVerified
57.4%
SciCode (AA run)
Long context
AA-LCRVerified
76.67%
AA-LCR (AA run)
Performance
AA output speedVerified
84 t/s
Median output tokens/s (1k prompt, default provider)
Changelog
Version history
- Public on the Grok API, Cursor, and Grok Build. Regions: us-east-1, us-west-2, us-central-1.
Sources
Where the numbers come from
- xAI Grok 4.7 announcement· checked 2026-09-23
- xAI Grok 4.7 model docs· checked 2026-09-23
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 Grok 4.7?
Grok 4.7 is a xAI model: xAI's 21 Sep 2026 Grok model for coding and knowledge work. API list starts at $2 / $6 per 1M tokens, 500k context. Text and image in, text out. No AA or Vals ledger row on this page as of 23 Sep 2026.
What is Grok 4.7 for?
Current xAI line for agentic coding and knowledge work. Grok 4.6 stays on the atlas at the same starting list.
What does Grok 4.7 cost?
Grok 4.7 lists $2.0 input and $6.0 output per 1M tokens. Pricing last checked 2026-09-23.
How large is the Grok 4.7 context window?
Grok 4.7 publishes a 500K token context window.
What is the VerdictPal status of Grok 4.7?
Grok 4.7 carries Flagship 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.