MDL
Grok 4.20 0309 v2
xAI
Verified against Artificial Analysis · Jul 13, 2026
Capability
89
percentile index
Price /M
$2 / $6
in / out
Context
—
Avg score
62.7
7 benchmarks
AA Intelligence
37.0
index
Speed
173 tok/s
TTFT 18s
Released
Apr 7, 2026
About
Grok 4.20 0309 v2 is a proprietary model in the Grok family from xAI. Benchmarked on 7 evals, averaging 62.7.
Benchmark scores · 7
avg 62.7 — 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, 2026RefusalBench: Why Refusal Rate Misranks Frontier LLMs on Biological Research PromptsMay 20, 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
Output speed173 tok/s
Latency (TTFT)18s
Price in / out$2 / $6 per 1M
Blended price$3 / 1M
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$6/M