MDL
Grok 4 Fast
xAI
Verified against Artificial Analysis · Jul 13, 2026
Capability
82
percentile index
Price /M
$0.2 / $0.5
in / out
Context
—
Avg score
60.4
10 benchmarks
AA Intelligence
27.4
index
Weights
Closed
Released
Sep 19, 2025
About
Grok 4 Fast is a proprietary model in the Grok family from xAI. Benchmarked on 10 evals, averaging 60.4.
Benchmark scores · 10
avg 60.4 — higher is betterThe research behind this model
all papers mentioning it →When AI Takes Sides on Questions of Faith: Persistent Asymmetries in AI-Mediated Faith GuidanceMay 21, 2026Evaluating Commercial AI Chatbots as News IntermediariesMay 21, 2026RefusalBench: Why Refusal Rate Misranks Frontier LLMs on Biological Research PromptsMay 20, 2026FORGE: Self-Evolving Agent Memory With No Weight Updates via Population BroadcastMay 15, 2026LLM-Based Persuasion Enables Guardrail Override in Frontier LLMsMay 13, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.
Performance & price
Price in / out$0.2 / $0.5 per 1M
Blended price$0.275 / 1M
Math index89.7
Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →
History
full ledger →Capability over time
Append-only ledger — every observed change to this model's numbers.
API providers
Artificial Analysis$0.5/M