Grok 4.7 Benchmarks, Specifications & Availability
Explore Grok 4.7 from xAI: published specifications, source-linked vendor benchmarks, independent evaluator coverage and recorded pricing when available.
Compare Grok 4.7 with other models →Explore data coverage
Published specifications
- Provider
- xAI
- Access
- Proprietary
- License
- Proprietary
- Context window
- 500k
- Total parameters
- Not published
- Active parameters
- Not published
- Released
- 2026-09-21
- Modalities
- text, image
- Family
- Grok 4
Model card · Announcement · Website · OpenRouter
Model notes
API pricing $2/$6 per 1M in/out (below 200k). Reasoning: low/medium/high/xhigh. Grok 4.7 Fast is same model, 2x rates, Cursor/Grok Build only.
Pricing · OpenRouter
Dated cached OpenRouter rates in USD per 1M tokens. Open the dashboard for live enhancements. Per-metric endpoint minima can refer to different providers; they are not a guaranteed combined rate from one endpoint.
| Tier | Input / 1M | Output / 1M | Cached input / 1M | Cache write / 1M | Date & source |
|---|---|---|---|---|---|
| Default | [object Object] | [object Object] | [object Object] | — | 2026-10-03 · OpenRouter source |
Recorded pricing notes
OpenRouter; above 200k prompt tokens rates double. xAI first-party list is $2/$6 below 200k.; min-healthy endpoint minima 2026-10-01; time-window overrides apply on a winning provider; min-healthy endpoint minima 2026-10-01; time-window overrides apply on a winning provider; min-healthy endpoint minima 2026-10-02; time-window overrides apply on a winning provider; min-healthy endpoint minima 2026-10-03; time-window overrides apply on a winning provider
Official / vendor benchmarks
Default headline records. Own-vendor, peer-vendor and third-party provenance remain visible in evidence; configurations may differ.
| Benchmark / evaluator | Headline score | Evidence |
|---|---|---|
| AA Briefcase v1.1 | 1657unknown effort | All 1 recorded result & sources1657 · raw 1657 Elo Headline · unknown effort · Own vendor Source/record date: 2026-09-21 Elo https://x.ai/news/grok-4-7 |
| CursorBench 4.0 | 46.3%unknown effort | All 1 recorded result & sources46.3% · raw 46.3 % Headline · unknown effort · Own vendor Source/record date: 2026-09-21 https://x.ai/news/grok-4-7 |
| DeepSWE v1.1 | 71%high effort | All 1 recorded result & sources71% · raw 71 % Headline · high effort · Own vendor Source/record date: 2026-09-21 Official table marks high-effort with asterisk https://x.ai/news/grok-4-7 |
| EEBench | 64%unknown effort | All 1 recorded result & sources64% · raw 64 % Headline · unknown effort · Own vendor Source/record date: 2026-09-21 https://x.ai/news/grok-4-7 |
| GDPval | 1695xhigh effort | All 1 recorded result & sources1695 · raw 1695 Elo Headline · xhigh effort · Own vendor Source/record date: 2026-09-21 GDPval Elo from xAI announcement chart text (Grok 4.7 xhigh) https://x.ai/news/grok-4-7 |
| Harvey Legal Agent | 19.6%unknown effort | All 1 recorded result & sources19.6% · raw 19.6 % Headline · unknown effort · Own vendor Source/record date: 2026-09-21 https://x.ai/news/grok-4-7 |
| HealthBench Professional | 56.7%unknown effort | All 1 recorded result & sources56.7% · raw 56.7 % Headline · unknown effort · Own vendor Source/record date: 2026-09-21 https://x.ai/news/grok-4-7 |
| Terminal-Bench 4.0 | 38%unknown effort | All 1 recorded result & sources38% · raw 38 % Headline · unknown effort · Own vendor Source/record date: 2026-09-21 https://x.ai/news/grok-4-7 |
| FrontierCode 1.1 Main | 47.6%unknown effort | All 1 recorded result & sources47.6% · raw 47.6 % Headline · unknown effort · Own vendor Source/record date: 2026-09-21 Cognition FrontierCode 1.1 Main leaderboard JSON-LD ItemList: Grok 4.7 Score 47.6% (added Sep 21, 2026 changelog) https://cognition.com/frontiercode |
Independent evaluators
Evaluator harnesses are distinct from vendor measurements. Missing coverage is not a failed test.
| Benchmark / evaluator | Headline score | Evidence |
|---|---|---|
| Intelligence Index · Artificial Analysis | 46xhigh effort | All 3 recorded results & sources46 · raw 46 index Headline · xhigh effort · Independent evaluator Source/record date: 2026-10-03 Current AA model leaderboard; https://artificialanalysis.ai/models/grok-4-746 · raw 46 index Alternative · high effort · Independent evaluator Source/record date: 2026-10-03 Current AA model leaderboard; https://artificialanalysis.ai/models/grok-4-7-high42 · raw 42 index Alternative · low effort · Independent evaluator Source/record date: 2026-10-03 Current AA model leaderboard; https://artificialanalysis.ai/models/grok-4-7-low |
| Cost per Intelligence Index task · Artificial Analysis | $3.74xhigh effort | All 3 recorded results & sources$3.74 · raw 3.74 USD Headline · xhigh effort · Independent evaluator Source/record date: 2026-10-03 Current AA model leaderboard; https://artificialanalysis.ai/models/grok-4-7$2.73 · raw 2.73 USD Alternative · high effort · Independent evaluator Source/record date: 2026-10-03 Current AA model leaderboard; https://artificialanalysis.ai/models/grok-4-7-high$1.25 · raw 1.25 USD Alternative · low effort · Independent evaluator Source/record date: 2026-10-03 Current AA model leaderboard; https://artificialanalysis.ai/models/grok-4-7-low |
| Output speed · Artificial Analysis | 81 tok/sxhigh effort | All 3 recorded results & sources81 tok/s · raw 81 tok/s Headline · xhigh effort · Independent evaluator Source/record date: 2026-10-03 Current AA model leaderboard; Median output tokens/s; leaderboard rounds to whole tokens. https://artificialanalysis.ai/models/grok-4-778 tok/s · raw 78 tok/s Alternative · high effort · Independent evaluator Source/record date: 2026-10-03 Current AA model leaderboard; Median output tokens/s; leaderboard rounds to whole tokens. https://artificialanalysis.ai/models/grok-4-7-high78 tok/s · raw 78 tok/s Alternative · low effort · Independent evaluator Source/record date: 2026-10-03 Current AA model leaderboard; Median output tokens/s; leaderboard rounds to whole tokens. https://artificialanalysis.ai/models/grok-4-7-low |
| Coding Agent Index · Artificial Analysis | 56xhigh effort | All 1 recorded result & sources56 · raw 56 index Headline · xhigh effort · Independent evaluator Source/record date: 2026-09-21 Grok 4.7 (xhigh) with Grok Build harness https://artificialanalysis.ai/articles/benchmarking-grok-4-7 |
| AA-Briefcase Elo · Artificial Analysis | 1657unknown effort | All 1 recorded result & sources1657 · raw 1657 Elo Headline · unknown effort · Independent evaluator Source/record date: 2026-09-21 https://artificialanalysis.ai/articles/benchmarking-grok-4-7 |
| GDPval-AA Elo · Artificial Analysis | 1695unknown effort | All 1 recorded result & sources1695 · raw 1695 Elo Headline · unknown effort · Independent evaluator Source/record date: 2026-09-21 https://artificialanalysis.ai/articles/benchmarking-grok-4-7 |
| AA-Omniscience Index · Artificial Analysis | 32unknown effort | All 1 recorded result & sources32 · raw 32 index Headline · unknown effort · Independent evaluator Source/record date: 2026-09-21 https://artificialanalysis.ai/articles/benchmarking-grok-4-7 |
| Vals Index · Vals AI | 55%unknown effort | All 1 recorded result & sources55% · raw 54.95 % Headline · unknown effort · Independent evaluator Source/record date: 2026-10-03 Refreshed from current Vals leaderboard. Cost/test $12.12. https://www.vals.ai/benchmarks/vals_index |
| Bugs fixed /105 · Bug Hunt Bench | 28.8 fixesxhigh effort | All 4 recorded results & sources28.8 fixes · raw 28.8 fixes Headline · xhigh effort · Independent evaluator Source/record date: 2026-10-03 Harness: Grok Build CLI (ACP); effort xhigh; 4 runs; evaluation 2026-09-21. Best documented score for this effort in Oct 1 README. Headline: best documented model run. https://github.com/phuryn/bug-hunt-bench26.7 fixes · raw 26.7 fixes Alternative · medium effort · Independent evaluator Source/record date: 2026-10-03 Harness: Grok Build CLI (ACP); effort medium; 3 runs; evaluation 2026-09-21. Best documented score for this effort in Oct 1 README. https://github.com/phuryn/bug-hunt-bench19.3 fixes · raw 19.3 fixes Alternative · high effort · Independent evaluator Source/record date: 2026-10-03 Harness: Grok Build CLI (ACP); effort high; 3 runs; evaluation 2026-09-21. Best documented score for this effort in Oct 1 README. https://github.com/phuryn/bug-hunt-bench15.7 fixes · raw 15.7 fixes Alternative · low effort · Independent evaluator Source/record date: 2026-10-03 Harness: Grok Build CLI (ACP); effort low; 3 runs; evaluation 2026-09-21. Best documented score for this effort in Oct 1 README. https://github.com/phuryn/bug-hunt-bench |
| Vibe Code Bench v1.1 · Vals AI | 86.2%unknown effort | All 1 recorded result & sources86.2% · raw 86.17 % Headline · unknown effort · Independent evaluator Source/record date: 2026-10-03 Refreshed from current Vals leaderboard. Harness: OpenHands. Cost/test $15.83. https://www.vals.ai/benchmarks/vibe-code |
| CUDA board % of roofline · KernelBench (community board) | 22%unknown effort | All 1 recorded result & sources22% · raw 22 % Headline · unknown effort · Independent evaluator Source/record date: 2026-09-23 CUDA 4/4; Mega 6.38× https://kernelbench.com/models/grok-4.7 |
| Money gain · Andon Labs | $10036.83unknown effort | All 1 recorded result & sources$10036.83 · raw 10036.83 $ Headline · unknown effort · Independent evaluator Source/record date: 2026-10-03 Vending-Bench 2 net gain = final_value in the page public vb2 data module minus $500 starting balance. Full 66-model source checked. https://andonlabs.com/evals/vending-bench-2 |
| Blueprint Bench · Andon Labs | 32.5%unknown effort | All 1 recorded result & sources32.5% · raw 32.5 % Headline · unknown effort · Independent evaluator Source/record date: 2026-10-03 Blueprint-Bench 2 connectivity similarity; published fractional score multiplied by 100. https://andonlabs.com/evals/blueprint-bench-2 |
| Average Score · WeirdML v3 | 7.5%xhigh effort | All 1 recorded result & sources7.5% · raw 7.53 % Headline · xhigh effort · Independent evaluator Source/record date: 2026-10-02 WeirdML variant Grok 4.7 (xhigh); harness codex_cli 0.156.0; values from prepared data JSON; raw 0.075274; official 80/20 aggregate (area 500k-50M tokens + final best) https://htihle.github.io/weirdml.html |
| Final Best Score · WeirdML v3 | 16.7%xhigh effort | All 1 recorded result & sources16.7% · raw 16.68 % Headline · xhigh effort · Independent evaluator Source/record date: 2026-10-02 WeirdML variant Grok 4.7 (xhigh); harness codex_cli 0.156.0; values from prepared data JSON; raw 0.166814; mean final best effective score https://htihle.github.io/weirdml.html |
| Cost / Run · WeirdML v3 | $26.01xhigh effort | All 1 recorded result & sources$26.01 · raw 26.01 USD Headline · xhigh effort · Independent evaluator Source/record date: 2026-10-02 WeirdML variant Grok 4.7 (xhigh); harness codex_cli 0.156.0; values from prepared data JSON; mean API cost per run, same task weighting as scores https://htihle.github.io/weirdml.html |
Read how we select and source scores or the comparison guide.