# Grok 4.7 Benchmark Scores & Performance

> Grok 4.7 by xAI has 17 source-displayable benchmark rows but no public overall score. It remains unranked.

Canonical page: https://benchlm.ai/models/grok-4-7

Last updated: September 21, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | xAI |
| Source Type | Proprietary |
| Reasoning Type | Reasoning |
| Context Window | 500K |
| Official model card | [xAI Grok 4.7 model documentation](https://docs.x.ai/developers/grok-4-7) |
| Overall Score | Coming soon |
| Overall Rank | Unranked |

## Family & Coverage

- Family: Grok 4.7
- Variant: base
- Benchmarks covered: 17 of 447
- Related earlier model: [Grok 4.6](/models/grok-4-6)
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AA Briefcase](/benchmarks/aabriefcaseelo) | 1657 |
| [Terminal-Bench 4.0](/benchmarks/terminal-bench-4) | 38.00% |
| [AA Harvey LAB](/benchmarks/aaharveylab) | 19.6% |
| [GDPval-AA](/benchmarks/gdpvalaanormalized) | 59.8% |
| [Terminal-Bench 2.1 (Vals)](/benchmarks/valsterminalbench21) | 76.0% |

## Coding Benchmarks

| Benchmark | Score |
|-----------|-------|
| [CursorBench 4.0](/benchmarks/cursorbench40) | 46.3% |
| [DeepSWE](/benchmarks/deepswe) | 71.0% |
| [EEBench](/benchmarks/eebench) | 64.0% |
| [AA-SciCode](/benchmarks/aascicode) | 57.4% |

## Reasoning Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AA-LCR](/benchmarks/lcr) | 76.7% |
| [CritPt](/benchmarks/critpt) | 17.7% |

## Knowledge Benchmarks

| Benchmark | Score |
|-----------|-------|
| [HealthBench Professional](/benchmarks/healthbenchprofessional) | 56.7% |
| [Artificial Analysis Intelligence Index](/benchmarks/artificialanalysis) | 46.5% |
| [AA-HLE](/benchmarks/aahle) | 43.1% |
| [AA-Omniscience Index](/benchmarks/aaomniscienceindex) | 32.0% |
| [AA-Omniscience Accuracy](/benchmarks/omniscienceaccuracy) | 47.4% |
| [AA-Omniscience Hallucination Rate](/benchmarks/omnisciencehallucinationrate) | 29.3% |

## Other xAI Models

- [Grok 4.6](/models/grok-4-6) - Score: 69.82
- [Grok 4.5](/models/grok-4-5) - Score: 68.05
- [Grok 4.20](/models/grok-4-20-beta) - Score: 67.57
- [Grok 4.3](/models/grok-4-3) - Score: 59.84
- [Grok 4.1](/models/grok-4-1) - Score: 58.15
- [Grok 4.1 Fast (Reasoning)](/models/grok-4-1-fast-reasoning) - Score: 54.95
- [Grok 4](/models/grok-4) - Score: 53.58
- [Grok 3 [Beta]](/models/grok-3-beta) - Score: 52.11
- [Grok 4 Fast (Reasoning)](/models/grok-4-fast-reasoning) - Score: 51.3
- [Grok 4.1 Fast](/models/grok-4-1-fast) - Score: 47.33
- [Grok 3 Mini](/models/grok-3-mini) - Score: 47.14
- [Grok Code Fast 1](/models/grok-code-fast-1) - Score: 33.94
- [Grok Voice Transcribe 2.0](/models/grok-voice-transcribe-2) - Score: not computed
- [Grok Build 0.1](/models/grok-build-0-1) - Score: not computed
- [Grok TTS](/models/grok-tts) - Score: not computed
- [Grok 4.20 Multi-agent](/models/grok-4-20-multi-agent-beta) - Score: not computed
- [Grok Realtime](/models/grok-realtime) - Score: not computed
- [Grok Voice Think Fast 1.0](/models/grok-voice-think-fast-1-0) - Score: not computed
- [Grok Voice Think Fast 2.0](/models/grok-voice-think-fast-2-0) - Score: not computed