Grok 4.7
xAIProprietaryReasoningReleased Sep 21, 2026Input: text, image, file
Overall score
—
Not enough evidence to rank yet
Context window
500K
500,000 tokens
Price per 1M tokens
$2.00 in · $6.00 out
✓ Verified on xAI's pricing page
Blended price
$3.00
3:1 input:output tokens
Output speed
—
Not measured yet
Category scores
Scores per capability area with the model's rank among ranked models in that category.
- 1Agentic & tool use75.6
- 2Knowledge72.4
- 3Coding65.2
- 4Reasoning#2558.9
- 5Math58.6
Benchmark results (18)
As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.
Agentic & tool use
| MazeBench | 1 | #13 of 42 |
| Terminal-Bench 4.0 | 38.00 | #13 of 18 |
| Hermes Index | 39.3 | #6 of 16 |
| Hermes Bench | 74.4 | #2 of 16 |
| CWE-bench v1 | 68.0 | #1 of 11 |
Coding
| DeepSWE | 71.0 | #16 of 50 |
| Bug Hunt Bench | 29.0 | #12 of 23 |
| FrontierSWE v2 | 29.5 | #11 of 20 |
| EEBench | 64.0 | #1 of 1 |
Reasoning
| ARC-AGI-2 | 61.4 | #23 of 41 |
| ARC-AGI-1 | 89.50 | #22 of 36 |
| ARC-AGI-3 | 1.8 | #9 of 22 |
| ARC-AGI-3 Provider Adapter | 7.02 | #6 of 8 |
Math
| FrontierMath v2 (Tiers 1-3) | 52.982 | #40 of 64 |
| FrontierMath v2 (Tier 4) | 17.073 | #38 of 51 |
Multimodal
| Design Arena Website | 1251 | #42 of 91 |
Knowledge
| HealthBench Professional | 56.7 | #14 of 16 |
Pricing by source
USD per 1M tokens.
| Source | Input | Output | Cached in |
|---|---|---|---|
| ✓ Official (xAI) checked Oct 17, 2026 · grok-4.7 | $2.00 | $6.00 | — |
| BenchLM list price | $2.00 | $6.00 | $0.50 |
| OpenRouter x-ai/grok-4.7 | $2.00 | $6.00 | $0.50 |
Prompts under 200K tokens.
xAI lists `grok-4.7` at $2.00 input, $0.50 cached input, and $6.00 output per million tokens below 200K prompt tokens. Prompts above 200K use the published $4.00 / $1.00 / $12.00 long-context tier; BenchLM stores the short-context rate.
Arena ratings
Human-preference ratings from LMArena. Best-rated variant shown.
| Text(xhigh) | 1401 | #153 · 11.6K votes |
| WebDev (coding)(xHigh) | 1637 | #18 · 5.3K votes |
| Vision(xHigh) | 1231 | #79 · 3.7K votes |
Speed
Measured by us through OpenRouter (median of trials).
Not measured yet.