G
Grok 4.7
Tuned for creativity: a higher LiveBench design score than Gemini 4 Argon, but only 500K of context
Intelligence v5
34.3
Leaderboard rank
#13
Input / output
$2.00/$6.00
Blended 3:1
$3.00
Output speed
105 tok/s
Value
11 pts/$
Capability profile Normalised to the field maximum
Specifications
Vendor
xAI
Released
2026-09
Weights
Closed, API only
Context
500,000 tokens
Max output
Undisclosed
Parameters
Undisclosed
Input price
$2.00 / 1M
Output price
$6.00 / 1M
Cache hit
n/a
Output speed
105 tok/s
Intelligence
34.3（v5）
Benchmark scores
How it is measured →Ranked 13 · bars are scaled to the field maximum for that benchmark.
| Benchmarks | Score | Vs. best in field | Gap |
|---|---|---|---|
| AA Intelligence Index v5 Intelligence index | 34.3 | 57% | −25.7 pts |
| AA Intelligence Index v4.3.2 Intelligence index (legacy) | 46.4 | 81% | −11.2 pts |
| GPQA Diamond Graduate-level science reasoning | 92.7 | 96% | −3.7 pts |
| Terminal-Bench 4.0 Terminal-agent tasks | 25.8 | 38% | −41.4 pts |
| LiveBench Design Document generation (DOCX/PPT/PDF) | 78.0 | 90% | −8.9 pts |
| Vals Index | — | — | not indexed |
Assessment
The Grok line is consistently strong on creativity evaluations. Its 500K context is the smallest among top models, which limits long-document work. Pricing is low for this tier ($2/$6).
At the same price
The four models closest on blended price, side by side.
| Model | v5 | Blended | tok/s | Score gap |
|---|---|---|---|---|
| Qwen3.8 MaxAlibaba Qwen | 34.0 | $3.00 | 88 | -0.3 |
| GLM-5.3 Open weightsZ.ai | 32.0 | $2.15 | 77 | -2.3 |
| Claude Sonnet 5.5Anthropic | 54.5 | $4.00 | 135 | +20.2 |
| GPT-6.1 SolOpenAI | 54.6 | $4.00 | 77 | +20.3 |
Compare side by side
Line it up against other models on price, speed and every benchmark.
The comparison tool lines up to 4 models side by side with switchable normalisation — built for purchasing decisions.
Open the comparison tool → Back to leaderboard