Grok 4.7 benchmarks
Grok 4.7 is a proprietary model from xAI, released 21 Sep 2026. It ranks 40th of 54 on our overall leaderboard and 14th of 53 for value. At A$4.32 per million tokens (blended), it costs about the same as the median model we track. It writes about 85 tokens a second, and answers start after 20 s on average, thinking included. None of the major cloud platforms offer it in an Australian region yet.
- CONTEXT WINDOW
- 500,000 tokens
- INPUT
- text, image
- WEIGHTS
- Proprietary
- RELEASED
- 21 Sep 2026
- OUTPUT SPEED
- 85 tok/s
- ANSWER STARTS AFTER
- 20 s (thinking included)
Grok 4.7 across our rankings.
Benchmark results.
Independent test scores are for the xhigh effort setting. “Among tracked” ranks Grok 4.7 against the 54 models on this site; LMArena ranks run across its full leaderboard.
| BENCHMARK | RESULT | AMONG TRACKED | SOURCE DETAIL |
|---|---|---|---|
| INDEPENDENT TESTS · ARTIFICIAL ANALYSIS | |||
| AA Intelligence Index | 46.4 | #12 of 54 | xhigh effort |
| Humanity’s Last Exam | 43.1% | #23 of 54 | xhigh effort |
| AA-LCR | 76.7% | #49 of 54 | xhigh effort |
| SciCode | 57.4% | #14 of 49 | xhigh effort |
| BLIND HUMAN VOTES · LMARENA | |||
| LMArena Text5,675 votes · ±8 | 1443 | #46 of 49 | #88 of 410 on LMArena · 30 Sep 2026 |
| LMArena WebDev3,062 votes · ±12 | 1636 | #13 of 52 | #15 of 137 on LMArena · 30 Sep 2026 |
| LMArena Agent10,109 sessions | #17 | #15 of 42 | #17 of 46 on LMArena · 30 Sep 2026 |
What Grok 4.7 costs in Australian dollars.
List prices converted at the snapshot’s RBA rate, excluding GST. Reasoning models are billed for their thinking as output tokens, so heavier settings cost more than the job estimates show.
| PER MILLION TOKENS | AUD | USD LIST |
|---|---|---|
| Input tokens | A$2.88 | US$2.00 |
| Output tokens | A$8.63 | US$6.00 |
| Blended (3 in : 1 out) | A$4.32 | US$3.00 |
| JOB | COST (AUD) | MEDIAN MODEL |
|---|---|---|
| Customer support replyPER 1,000 REPLIES | A$8.35 | ≈ A$8.20 |
| Summarise a 30-page documentPER 100 DOCUMENTS | A$6.45 | ≈ A$5.35 |
| Agentic coding taskPER 10 TASKS | A$5.01 | ≈ A$4.27 |
| SETTING | INTELLIGENCE | A$ / 1M | SPEED |
|---|---|---|---|
| xhigh effort | 46.4 | A$4.32 | 85 tok/s |
| high effort | 46.3 | A$4.32 | 83 tok/s |
Running Grok 4.7 in Australia.
None of the major cloud platforms offer it in an Australian region yet. How the platforms compare →
| PLATFORM | AVAILABILITY | DETAIL |
|---|---|---|
| AWS Bedrock · Sydney | NOT OFFERED | |
| AWS Bedrock · Melbourne | NOT OFFERED | |
| Azure · Australia East | NOT OFFERED | |
| Google Vertex AI · Sydney | NOT OFFERED |
Compare it with.
Grok 4.7, answered.
How much does Grok 4.7 cost in Australian dollars?
Grok 4.7 lists at US$2.00 per million input tokens and US$6.00 per million output tokens — A$2.88 and A$8.63 at A$1 = US$0.6949 (RBA, 1 Oct 2026), excluding GST. A typical customer support reply works out at about A$8.35 per 1,000 replies, before any reasoning tokens.
Can I use Grok 4.7 in Australia with data kept onshore?
None of the major cloud platforms offer it in an Australian region yet. Availability comes from the cloud providers’ own documentation; check your provider’s current terms before relying on it for data-residency obligations.
How fast is Grok 4.7?
Artificial Analysis measures Grok 4.7 at about 85 tok/s of output, with the answer starting after 20 s on average once thinking time is included (xhigh effort setting).
What is Grok 4.7’s context window?
xAI documents a context window of 500,000 tokens (500K). On AA-LCR, which tests reasoning across ~100,000-token document sets, it scores 76.7%.
Ratings: LMArena leaderboard dataset (CC BY 4.0), rescaled for the lens scores · leaderboards to 30 Sep 2026
Evaluations, prices and speed: Artificial Analysis (artificialanalysis.ai) · fetched 1 Oct 2026
Exchange rate: Reserve Bank of Australia, table F11.1 · A$1 = US$0.6949 on 1 Oct 2026 · prices exclude GST
Snapshot 2 Oct 2026 · updated weekly · How the rankings work →