grok-4.20-beta1: benchmark scores, price and ranking

grok-4.20-beta1 from xAI ranks #303 of 743 LLMs on the LLMs Tiger aggregate benchmark score (49.0), based on 2 benchmark results captured up to 2026-10-13.

Organisation: xAI
Type: Frontier model
Open weights: No
Aggregate rank: #303 of 743 (score 49.0)

Across the 2 benchmarks where at least ten models are scored, grok-4.20-beta1 is in the top 10% on 0 and in the top half on 1.

grok-4.20-beta1 benchmark results

grok-4.20-beta1 benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
LMArena Search Elo	1,189	#13 of 28	LMArena	2026-10-13
LMArena Text Elo	1,475	#19 of 28	LMArena	2026-10-05

About grok-4.20-beta1

grok-4.20-beta1 is a frontier model from xAI. No API price is listed for it yet. We hold 2 benchmark results for it across 1 area, and none is in the top tenth of its board.

Where grok-4.20-beta1 stands

On our aggregate score, grok-4.20-beta1 is #303 of 743 ranked models, around the middle of the table. Its score is 49.0; the scale is centred on 50, so it sits 1.0 points below the typical model. That beats 59% of the ranked field. Among the 26 ranked xAI models it is #16. The next one up is Grok-2-mini at 49.0. The next one down is grok-4.3 (high) at 48.9.

grok-4.20-beta1, benchmark by benchmark

LMArena Search Elo puts grok-4.20-beta1 at 1,189, #13 of 28. That beats 54% of the models tested, but 64 points short of claude-opus-4-6-search (1,253). The results either side are claude-sonnet-5-search (1,194) and claude-opus-4-5-search (1,180). It covers crowd-voted web-search answers. The board median is 1,176, so grok-4.20-beta1 is 13 points above it. Source: LMArena, captured 2026-10-13.

grok-4.20-beta1 lands below the middle on LMArena Text Elo: 1,475, #19 of 28, with 64% of the field scoring higher. gemini-4-argon-high leads at 1,525; the closest result above is gpt-5.2-chat-latest-20260210 at 1,476. It covers head-to-head chat preference (crowd votes). The board median is 1,478, so grok-4.20-beta1 is 2 points below it. Source: LMArena, captured 2026-10-05.

Strengths and weaknesses

General knowledge and chat: uneven, ahead of 43% of the field on average across 2 benchmarks. Its best board here is LMArena Search Elo (#13 of 28) and its weakest is LMArena Text Elo (#19 of 28).

Reading these numbers

The 2 scores on this page come from 1 source: LMArena (2). No official leaderboard supplied any of them, so treat them as third-party measurements. With 2 results the aggregate rank can move a lot when one new score arrives.

Models ranked nearby

#300 Grok-2-mini (49.0)
#301 Llama-3.1-Nemotron-70B-Instruct-HF (49.0)
#302 Qwen2.5-14B (49.0)
#304 qwen3.7-max-preview (49.0)
#305 internlm2_5-7b-chat (48.9)
#306 claude-sonnet-4-20250514 (48.9)