grok-4.20-beta-0309-reasoning: benchmark scores, price and ranking

grok-4.20-beta-0309-reasoning from xAI ranks #332 of 743 LLMs on the LLMs Tiger aggregate benchmark score (48.7), based on 3 benchmark results captured up to 2026-10-13.

Organisation: xAI
Type: Preview release
Open weights: No
Cheapest API price: $1.25 in / $2.50 out per million tokens (via xai, observed 2026-10-13T20:47Z)
Aggregate rank: #332 of 743 (score 48.7)

Relative to other models, grok-4.20-beta-0309-reasoning is strongest on LMArena Document Elo (#16 of 18) and weakest on LMArena Vision Elo (#20 of 22).

Across the 3 benchmarks where at least ten models are scored, grok-4.20-beta-0309-reasoning is in the top 10% on 0 and in the top half on 0.

Its cheapest listed input price, $1.25 per million tokens, is lower than that of 26% of the 427 models with a listed price.

grok-4.20-beta-0309-reasoning benchmark results

grok-4.20-beta-0309-reasoning benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
LMArena Document Elo	1,416	#16 of 18	LMArena	2026-10-13
LMArena Text Elo	1,472	#25 of 28	LMArena	2026-10-05
LMArena Vision Elo	1,255	#20 of 22	LMArena	2026-10-05

About grok-4.20-beta-0309-reasoning

grok-4.20-beta-0309-reasoning is a preview release from xAI. The cheapest API listing we track charges $1.25 per million input tokens and $2.50 per million output tokens, through xai. We hold 3 benchmark results for it across 1 area, and none is in the top tenth of its board.

Where grok-4.20-beta-0309-reasoning stands

On our aggregate score, grok-4.20-beta-0309-reasoning is #332 of 743 ranked models, around the middle of the table. Its score is 48.7; the scale is centred on 50, so it sits 1.3 points below the typical model. That beats 55% of the ranked field. Among the 26 ranked xAI models it is #18. The next one up is grok-4.3 (high) at 48.9. The next one down is grok-4.20-multi-agent-beta-0309 at 48.6.

grok-4.20-beta-0309-reasoning, benchmark by benchmark

LMArena Document Elo is a weak spot. grok-4.20-beta-0309-reasoning scores 1,416, #16 of 18, behind 83% of the models measured. The leader, Claude Fable 5.1 (max), reaches 1,513. It covers crowd-voted questions about documents. The board median is 1,440, so grok-4.20-beta-0309-reasoning is 24 points below it. Source: LMArena, captured 2026-10-13.

LMArena Text Elo is a weak spot. grok-4.20-beta-0309-reasoning scores 1,472, #25 of 28, behind 86% of the models measured. The leader, gemini-4-argon-high, reaches 1,525. It covers head-to-head chat preference (crowd votes). The board median is 1,478, so grok-4.20-beta-0309-reasoning is 6 points below it. Source: LMArena, captured 2026-10-05.

LMArena Vision Elo is a weak spot. grok-4.20-beta-0309-reasoning scores 1,255, #20 of 22, behind 86% of the models measured. The leader, Gemini 3.7 Flash (high), reaches 1,296. It covers crowd-voted image understanding. The board median is 1,279, so grok-4.20-beta-0309-reasoning is 24 points below it. Source: LMArena, captured 2026-10-05.

Strengths and weaknesses

General knowledge and chat: weak, ahead of 10% of the field on average across 3 benchmarks. Its best board here is LMArena Document Elo (#16 of 18) and its weakest is LMArena Vision Elo (#20 of 22).

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so grok-4.20-beta-0309-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), DeepSeek V4 Flash 0731 (max) ($0.016, 53.1). Similar scores cost more on Codex Mini (Latest) ($1.50) and Magistral Medium ($1.50).

Reading these numbers

The 3 scores on this page come from 1 source: LMArena (3). No official leaderboard supplied any of them, so treat them as third-party measurements. With 3 results the aggregate rank can move a lot when one new score arrives.

Models ranked nearby

#329 Amazon.nova Premier v1:0 (48.7)
#330 MiniMax-M2 (48.7)
#331 gemini-1.5-flash-exp-0827 (48.7)
#333 qwen3-4b-instruct-2507 (48.7)
#334 DeepSWE-Preview (48.6)
#335 chatgpt-4o-latest (2025-02-15) (48.6)