New: Agent Index for knowledge work is live.Explore the index ↗
Compare models

Across the task benchmarks we track, Grok 4.7’s strongest relative results are in knowledge work, work automations, and terminal use. On GDPval-AA v2.1, it scores 1,718 Elo, ranking #8 among 38 models with reported results in our dataset.

Updated: Data as of:
Compare this model

Strongest results

Strongest results for Grok 4.7 in tracked evaluation cohorts
BenchmarkMeasuresScore
Agent Index ↗v1.2 PreviewOverall agent capability38.5 / 100#14 of 26
LiveBench: Research ↗2.0 / 2026-10-25Research reports86.4%#2 of 25
AA-Briefcase ↗1.1 / combined EloBusiness deliverables1,638 Elo#7 of 57
GDPval-AA ↗2.1Knowledge work1,718.42 Elo#8 of 38

Model details

Proprietary15 benchmarks
Specifications for Grok 4.7
ModelGrok 4.7
Agent Index v1.238.5 / 100 · Rank 14 · Preview
CreatorxAI (opens in a new tab)
AvailabilityProprietary
Context size500,000 tokens (opens in a new tab)
Max outputContext-limited (opens in a new tab)
Knowledge cutoffNot reported
LicenseNot reported

Pricing and performance

Per provider and reported configuration. Prices are USD per 1M tokens.

Provider offerings for Grok 4.7
Provider / configurationContexttokensInputUSD / 1M tokensOutputUSD / 1M tokensLatencyTTFT · secondsSpeedtokens / sec
SpaceXAI (opens in a new tab)
Grok 4.7 (xhigh)		500,000$2.00 (opens in a new tab)$6.00 (opens in a new tab)111.581 (opens in a new tab)87.436 (opens in a new tab)

Benchmark performance

Grok 4.7 in color, alongside leading models. Latest stored reports, best effort per report date.

Reported benchmarks

All published results in our dataset, with versions, evaluation settings, and sources.

All published benchmark reports for Grok 4.7
BenchmarkScoreEvaluation setupSource
AA-Briefcase1.1 / combined EloCombined Elo · Higher is better1,638 Eloselection: publisher default displayed configuration · Grok 4.7 (xhigh)Artificial Analysis (opens in a new tab)independent
AutomationBench-AA1.0.6 / AA private 657Objectives completed without guardrail violations · Higher is better65.6%reported precision decimals: 1 · result quality: reported · Grok 4.7 (xhigh); private held-out 657 tasks; 50 turns; objective completion with zero credit for any guardrail violation. · source model href: /models/grok-4-7 · task count: 657 · Tools enabled · turn cap: 50Artificial Analysis (opens in a new tab)independent
GDP.pdf100 tasks / All-pass / five attemptsAccuracy · Higher is better23.2%selection: best reported configuration per release · Grok 4.7 (high) · tools: benchmark-definedArtificial Analysis (opens in a new tab)independent
GDP.pdf100 tasks / All-pass / five attemptsAccuracy · Higher is better20%selection: publisher default displayed configuration · Grok 4.7 (xhigh)Artificial Analysis (opens in a new tab)independent
GDPval-AA2.1Elo · Higher is better1,718.42 EloGrok 4.7 (Xhigh); 220 tasks; Stirrup agent; pairwise EloArtificial Analysis (opens in a new tab)independent
GDPval-AA2.1Elo · Higher is better1,715.8 EloGrok 4.7 (High); 220 tasks; Stirrup agent; pairwise EloArtificial Analysis (opens in a new tab)independent
GDPval-AA2.1Elo · Higher is better1,591.4 EloGrok 4.7 (Low); 220 tasks; Stirrup agent; pairwise EloArtificial Analysis (opens in a new tab)independent
HLE-Diamond1,000 questions / no toolsAccuracy · Higher is better23.6%selection: best reported configuration per release · Grok 4.7 (High) · No toolsArtificial Analysis (opens in a new tab)independent
Humanity's Last ExamStable HLE — text-only subsetAccuracy · Higher is better43.1%xhigh effort; AA methodology: 2158 text-only questions; pass@1; no tools; GPT-5.6 Luna medium judge. · subset: text · No toolsArtificial Analysis (opens in a new tab)independent
LiveBench: Agentic2.0 / 2026-10-25Accuracy · Higher is better46.1%release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: agenticLiveBench ↗ (opens in a new tab)benchmark publisher · 2026-10-25
LiveBench: Browser Use2.0 / 2026-10-25Accuracy · Higher is better49.3%release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: browser-useLiveBench ↗ (opens in a new tab)benchmark publisher · 2026-10-25
LiveBench: Coding2.0 / 2026-10-25Accuracy · Higher is better84.5%release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: codingLiveBench ↗ (opens in a new tab)benchmark publisher · 2026-10-25
LiveBench: Data Analysis2.0 / 2026-10-25Accuracy · Higher is better76.9%release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: data-analysisLiveBench ↗ (opens in a new tab)benchmark publisher · 2026-10-25
LiveBench: Design2.0 / 2026-10-25Accuracy · Higher is better78%release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: designLiveBench ↗ (opens in a new tab)benchmark publisher · 2026-10-25
LiveBench: Reasoning2.0 / 2026-10-25Accuracy · Higher is better82.7%release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: reasoningLiveBench ↗ (opens in a new tab)benchmark publisher · 2026-10-25
LiveBench: Research2.0 / 2026-10-25Accuracy · Higher is better86.4%release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: researchLiveBench ↗ (opens in a new tab)benchmark publisher · 2026-10-25
Terminal-Bench4.0Task success · Higher is better37.6%Grok Build; effort=xhigh; 37.6% ± 3.5%Terminal-Bench ↗ (opens in a new tab)benchmark publisher
Terminal-Bench4.0 / mini-swe-agentTask success · Higher is better25.758%harness: mini-swe-agent · repeats: 3 · selection: best reported configuration per release · Grok 4.7 (Xhigh)Artificial Analysis (opens in a new tab)independent