Grok 4 (Fast Reasoning): benchmark scores, price and ranking

Grok 4 (Fast Reasoning) from xAI ranks #407 of 743 LLMs on the LLMs Tiger aggregate benchmark score (47.7), based on 1 benchmark results captured up to 2026-10-13.

Organisation: xAI
Type: Frontier model
Open weights: No
Cheapest API price: $3.00 in / $15.00 out per million tokens (via azure_ai, observed 2026-10-13T20:47Z)
Aggregate rank: #407 of 743 (score 47.7)

Across the 1 benchmark where at least ten models are scored, Grok 4 (Fast Reasoning) is in the top 10% on 0 and in the top half on 0.

Its cheapest listed input price, $3.00 per million tokens, is lower than that of 11% of the 427 models with a listed price.

Grok 4 (Fast Reasoning) benchmark results

Grok 4 (Fast Reasoning) benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
ARC-AGI-2	5.3%	#57 of 87	ARC Prize official leaderboard	2026-10-13

About Grok 4 (Fast Reasoning)

Grok 4 (Fast Reasoning) is a frontier model from xAI. The cheapest API listing we track charges $3.00 per million input tokens and $15.00 per million output tokens, through azure_ai. We hold 1 benchmark result for it across 1 area, and none is in the top tenth of its board.

Where Grok 4 (Fast Reasoning) stands

On our aggregate score, Grok 4 (Fast Reasoning) is #407 of 743 ranked models, around the middle of the table. Its score is 47.7; the scale is centred on 50, so it sits 2.3 points below the typical model. That beats 45% of the ranked field. Among the 26 ranked xAI models it is #20. The next one up is grok-4.20-multi-agent-beta-0309 at 48.6. The next one down is grok-4-1 at 47.5.

Grok 4 (Fast Reasoning), benchmark by benchmark

Grok 4 (Fast Reasoning) lands below the middle on ARC-AGI-2: 5.3%, #57 of 87, with 64% of the field scoring higher. GPT-6 Astra (max) leads at 95.0%; the closest result above is GPT-5.4 nano (xhigh) at 5.7%. It covers abstract reasoning, ARC Prize public eval set. The board median is 22.8%, so Grok 4 (Fast Reasoning) is 17.5 points below it. Source: ARC Prize official leaderboard, captured 2026-10-13.

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so Grok 4 (Fast Reasoning) costs more than the typical listing. Models that score within 1.5 points or better and cost less: Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), DeepSeek V4.1 Flash (high) ($0.010, 48.9), Qwen2.5-Coder-3B-Instruct ($0.010, 46.5). Similar scores cost more on claude-opus-4-5-20251101-high-32k ($5.00) and gpt-5.5-xhigh (codex-harness) ($5.00).

Reading these numbers

The 1 score on this page comes from 1 source: ARC Prize official leaderboard (1). 1 of them come from an official leaderboard and 0 from datasets or third-party runs. With 1 results the aggregate rank can move a lot when one new score arrives.

Models ranked nearby

#404 DeepSeek-V2-Chat (47.8)
#405 Muse Code + Muse Spark 1.3 (47.8)
#406 DeepSeek-V3.2 (47.7)
#408 Mistral-Small-24B-Base-2501 (47.7)
#409 Gemini 2.5 Pro (Thinking 32K) (47.7)
#410 GLM-4.7 (47.7)