xAI, proprietary
Grok 4.7
Grok 4.7 by xAI ranks 37th of 354 ranked models on the Noometry Index as of October 2026, with a score of 53.1. Its strongest category is coding, where it ranks 18th. API pricing starts at $2 per million input tokens and $6 per million output tokens, with a 500K-token context window.
Last verified
Specifications
- Noometry rank
- #37 of 354
- Index score
- 53.1
- Evidence
- Confirmed 39 results
- Provider
- xAI
- Released
- September 21, 2026
- Weights
- Proprietary
- Reasoning
- Yes
- Context window
- 500K
- Max output
- 500K
- Input price
- $2 / M
- Output price
- $6 / M
- Blended price
- $3 / M
- Output speed
- Not measured
- Value
- #157 of 219
- Knowledge cutoff
- May 2026
- Input
- text, image, pdf
Category scores
Each category score combines every public result we have in that category.
- Coding 58.0
- Agentic & Tool Use 36.7
- Reasoning 49.1
- Math 57.8
- Knowledge 62.8
- Multimodal 35.5
- Multilingual 50.8
- Instruction Following 74.1
- Long Context 43.1
- Writing & Preference 70.0
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 58.0 | #18 | 6 |
| Agentic & Tool Use | 36.7 | #37 | 2 |
| Reasoning | 49.1 | #40 | 7 |
| Math | 57.8 | #39 | 5 |
| Knowledge | 62.8 | #22 | 3 |
| Multimodal | 35.5 | #87 | 3 |
| Multilingual | 50.8 | #116 | 1 |
| Instruction Following | 74.1 | #105 | 1 |
| Long Context | 43.1 | #104 | 1 |
| Writing & Preference | 70.0 | #24 | 4 |
Strengths and weaknesses
Categories where Grok 4.7 places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Coding | 58.0 | +19.3 | #18 of 340, top 6% |
| Knowledge | 62.8 | +25.4 | #22 of 314, top 8% |
| Writing & Preference | 70.0 | +16.2 | #24 of 312, top 8% |
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Multimodal | 35.5 | −3.0 | #87 of 128, top 68% |
| Multilingual | 50.8 | +3.3 | #116 of 297, top 40% |
| Long Context | 43.1 | +2.2 | #104 of 296, top 36% |
Closest competitors
The models ranked just above and below Grok 4.7. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Gemini 3.6 Flash | #33 | 54.1 | $1.50 | — | Compare |
| GPT-5.2 | #34 | 54.1 | $4.81 | 15 | Compare |
| DeepSeek V4 Flash | #35 | 53.6 | $0.26 | 6 | Compare |
| GPT-6 Luna | #36 | 53.3 | $0.20 | — | Compare |
| DeepSeek V4.1 Flash | #38 | 52.8 | $0.26 | — | Compare |
| GPT-5.2 Pro | #39 | 52.3 | $57.75 | — | Compare |
| Gemini 3 Flash Preview | #40 | 52.3 | $1.13 | — | Compare |
| GLM-5.3-Flash | #41 | 51.8 | $0.24 | — | Compare |
Sponsored placements are available on pages like this one. Advertise on Noometry
Benchmark results
Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.
Coding
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| FrontierCode | 47.6% | #10 of 37, top 28% | Epoch AI | ||
| CursorBench | 43.9% | high | Epoch AI | ||
| CursorBench | 33.1% | low | Epoch AI | ||
| CursorBench | 41.6% | medium | Epoch AI | ||
| CursorBench | 46.3% | #5 of 14, top 36% | xhigh | Epoch AI | |
| LMArena WebDev | 1639 | #12 of 113, top 11% | xhigh | LMArena | 2026-10-08 |
| FrontierSWE | 29.5% | #10 of 18, top 56% | xhigh | Epoch AI | |
| SciCode | 57.8% | #14 of 121, top 12% | high | Epoch AI | |
| SciCode | 54.9% | low | Epoch AI | ||
| SciCode | 57.4% | xhigh | Epoch AI | ||
| LMArena Coding | 1427 | #113 of 294, top 39% | xhigh | LMArena | 2026-10-08 |
Agentic & Tool Use
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| APEX-Agents | 54.6% | #19 of 49, top 39% | Epoch AI | ||
| GDP.pdf | 22.8% | #17 of 36, top 48% | xhigh | Epoch AI | |
| Vending-Bench 2 | 10,537 | #6 of 60, top 10% | Epoch AI |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| NYT Connections (extended) | 76.8% | #41 of 91, top 46% | high reasoning | Lech Mazur benchmarks | |
| CritPt | 18% | #30 of 134, top 23% | high | Epoch AI | |
| CritPt | 13.4% | low | Epoch AI | ||
| CritPt | 17.7% | xhigh | Epoch AI | ||
| Chess Puzzles | 38% | #24 of 129, top 19% | xhigh | Epoch AI | 2026-09-22 |
| LMArena Hard Prompts | 1413 | #114 of 297, top 39% | xhigh | LMArena | 2026-10-08 |
| Mystery Game Puzzles | 29% | #28 of 74, top 38% | xhigh | Epoch AI | 2026-09-22 |
| DTBench | 96% | #15 of 151, top 10% | xhigh | Epoch AI | |
| LMCA | 49.4% | #23 of 125, top 19% | xhigh | Epoch AI | |
| Epoch Capabilities Index | 153.53 | #40 of 213, top 19% | Epoch AI | 2026-09-21 |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| FrontierMath (Tiers 1-3) | 53% | #45 of 81, top 56% | xhigh | Epoch AI | 2026-09-22 |
| FrontierMath Tier 4 | 17.1% | #47 of 63, top 75% | xhigh | Epoch AI | 2026-09-22 |
| OTIS Mock AIME 2024-2025 | 98.1% | #23 of 173, top 14% | xhigh | Epoch AI | 2026-09-22 |
| ProofBench | 34% | #40 of 77, top 52% | Epoch AI | ||
| LMArena Math | 1407 | #117 of 285, top 42% | xhigh | LMArena | 2026-10-08 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| GPQA Diamond | 92.7% | #20 of 186, top 11% | xhigh | Epoch AI | 2026-09-22 |
| SimpleQA Verified | 56% | #18 of 77, top 24% | xhigh | Epoch AI | 2026-09-22 |
| LMArena Expert | 1422 | #104 of 273, top 39% | xhigh | LMArena | 2026-10-08 |
Multimodal
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Vision | 1228 | #68 of 122, top 56% | xhigh | LMArena | 2026-10-09 |
| Blueprint-Bench 2 | 32.5% | #12 of 31, top 39% | Epoch AI | ||
| Furniture Assembly | 20.8% | #30 of 31, top 97% | xhigh | Epoch AI | 2026-09-24 |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1389 | #116 of 297, top 40% | xhigh | LMArena | 2026-10-08 |
| LMArena Chinese | 1455 | #100 of 285, top 36% | xhigh | LMArena | 2026-10-08 |
| LMArena French | 1455 | #62 of 223, top 28% | xhigh | LMArena | 2026-10-08 |
| LMArena Russian | 1397 | #107 of 283, top 38% | xhigh | LMArena | 2026-10-08 |
| LMArena Spanish | 1400 | #111 of 226, top 50% | xhigh | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Instruction Following | 1404 | #97 of 298, top 33% | xhigh | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1413 | #101 of 291, top 35% | xhigh | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1399 | #119 of 297, top 41% | xhigh | LMArena | 2026-10-08 |
| LMArena Creative Writing | 1391 | #93 of 295, top 32% | xhigh | LMArena | 2026-10-08 |
| EQ-Bench Creative Writing | 2007 | #8 of 115, top 7% | EQ-Bench | ||
| LMArena Multi-Turn | 1393 | #126 of 295, top 43% | xhigh | LMArena | 2026-10-08 |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| bedrock | $2 | $6 | $0.50 | 2026-10-10 |
| openrouter | $2 | $6 | $0.50 | 2026-10-10 |
| vertex | $2 | $6 | $0.50 | 2026-10-10 |
| xai | $2 | $6 | $0.50 | 2026-10-10 |
Compare Grok 4.7
- Grok 4.7 vs Grok 4.6
- Grok 4.7 vs GPT-6 Luna
- Grok 4.7 vs DeepSeek V4.1 Flash
- Grok 4.7 vs DeepSeek V4 Flash
- Grok 4.7 vs GPT-5.2 Pro
- Grok 4.7 vs GPT-5.2
- Grok 4.7 vs Gemini 3 Flash Preview
- Grok 4.7 vs GPT-6 Astra
- Grok 4.7 vs Claude Fable 5.1
- Grok 4.7 vs Gemini 3.8 Flash
- Grok 4.7 vs Kimi K3
- Grok 4.7 vs Qwen3.8 Max
- Grok 4.7 vs GLM-5.3
- Grok 4.7 vs Muse Spark 1.3
Other xAI models
- Grok 4.656.9
- Grok 4.555.0
- Grok 4.20 (Non-Reasoning)48.6
- Grok 448.1
- Grok 4.20 Multi-Agent46.2
- Grok 4.343.8
- Grok 4.141.5
- Grok 4.1 Fast41.4
Frequently asked questions
How good is Grok 4.7?
Grok 4.7 by xAI ranks 37th of 354 ranked models on the Noometry Index as of October 2026, with a score of 53.1. Its strongest category is coding, where it ranks 18th. API pricing starts at $2 per million input tokens and $6 per million output tokens, with a 500K-token context window.
How much does Grok 4.7 cost?
Grok 4.7 costs $2 per million input tokens and $6 per million output tokens on xAI's own API, with cached input at $0.50.
What is Grok 4.7's context window?
Grok 4.7 accepts up to 500K tokens of input and can write up to 500K tokens in one response.
Is Grok 4.7 open source?
No. Grok 4.7 is proprietary and available only through xAI's API and partner platforms.
What are Grok 4.7's strengths and weaknesses?
Relative to other ranked models, Grok 4.7 places best in coding, knowledge, writing & preference and lowest in multimodal, multilingual, long context.
What is Grok 4.7 best at?
Its best category is coding, where it ranks 18th on Noometry.