Model comparison

DeepSeek-R1 vs Grok 4.20 (Non-Reasoning)

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 42.3 on the Noometry Index. DeepSeek-R1 costs 1.7× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.

Last verified October 10, 2026. 27 shared benchmarks.

DeepSeek-R1

DeepSeek

42.3

Rank #115 Confirmed

Grok 4.20 (Non-Reasoning) xAI

48.6

Rank #54 Confirmed

Summary

They share 27 benchmarks with published results for both. DeepSeek-R1 scores higher in 1 category and Grok 4.20 (Non-Reasoning) in 8 categories; 8 gaps are clear of the uncertainty.
The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.3 to 18.6.
The biggest single-benchmark swing is ARC-AGI-1: 21.2% for DeepSeek-R1 and 89.5% for Grok 4.20 (Non-Reasoning).
DeepSeek-R1 is cheaper at $0.50 / $2.15 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 (Non-Reasoning).
Grok 4.20 (Non-Reasoning) accepts more context: 1M tokens versus 164K.

Side by side

DeepSeek-R1 and Grok 4.20 (Non-Reasoning) specifications
	DeepSeek-R1	Grok 4.20 (Non-Reasoning)
Provider	DeepSeek	xAI
Noometry Index	42.3	48.6
Released	2025-01-20	2026-02-17
Weights	Proprietary	Proprietary
Context window	164K	1M
Max output	64K	30K
Input $ / M tokens	$0.50	$1.25
Output $ / M tokens	$2.15	$2.50
Results tracked	52	46

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding DeepSeek-R1 leads

DeepSeek-R1: 46.3 (#68), Grok 4.20 (Non-Reasoning): 42.1 (#112)

Coding benchmarks
Benchmark	DeepSeek-R1	Grok 4.20 (Non-Reasoning)
WeirdML	41.6%	52.3%
LMArena Coding	1427	1459
ALE-Bench	804.12	1,150
Aider Polyglot	71.4%	—
LMArena WebDev	—	1375
SciCode	35.7%	—
LiveBench Coding	66.7%	—
AlgoTune	1.7	—

Agentic & Tool Use Grok 4.20 (Non-Reasoning) leads

DeepSeek-R1: 30.7 (#75), Grok 4.20 (Non-Reasoning): 34.4 (#46)

Agentic & Tool Use benchmarks
Benchmark	DeepSeek-R1	Grok 4.20 (Non-Reasoning)
Terminal-Bench	—	57.3%
τ²-bench Banking	—	18%
DeepResearch Bench	35.1%	—
BALROG	34.9%	—
LMArena Search	—	1189
METR Time Horizons	53.8%	—
Vending-Bench 2	—	4,663

Reasoning Grok 4.20 (Non-Reasoning) leads

DeepSeek-R1: 18.6 (#278), Grok 4.20 (Non-Reasoning): 52.3 (#32)

Reasoning benchmarks
Benchmark	DeepSeek-R1	Grok 4.20 (Non-Reasoning)
ARC-AGI-2	1.3%	65.1%
Kagi LLM Benchmark	69.4%	75%
ARC-AGI-1	21.2%	89.5%
LMArena Hard Prompts	1416	1451
Epoch Capabilities Index	141.29	151.98
ForecastBench	60	61.4
SimpleBench	40.8%	—
NYT Connections (extended)	—	85.4%
CritPt	1.1%	—
Chess Puzzles	—	24%
Thematic Generalization	—	63.8%
LiveBench Reasoning	83.2%	—
DTBench	—	90.1%
LiveBench Data Analysis	69.8%	—
LMCA	—	38.7%
LiveBench	71.6%	—

Math Grok 4.20 (Non-Reasoning) leads

DeepSeek-R1: 43.8 (#79), Grok 4.20 (Non-Reasoning): 48.2 (#65)

Math benchmarks
Benchmark	DeepSeek-R1	Grok 4.20 (Non-Reasoning)
OTIS Mock AIME 2024-2025	66.4%	92.2%
LMArena Math	1400	1455
FrontierMath (Tiers 1-3)	—	44.9%
FrontierMath Tier 4	—	17.1%
ProofBench	—	14%
Omni-MATH	42.4%	—
LiveBench Math	80.7%	—
MATH Level 5	96.6%	—

Knowledge Grok 4.20 (Non-Reasoning) leads

DeepSeek-R1: 44.5 (#87), Grok 4.20 (Non-Reasoning): 52.8 (#60)

Knowledge benchmarks
Benchmark	DeepSeek-R1	Grok 4.20 (Non-Reasoning)
GPQA Diamond	76.3%	89.3%
LMArena Expert	1394	1439
SimpleQA Verified	—	30.2%
MMLU-Pro	79.3%	—
Confabulations	12.7%	—
Vectara Hallucination Rate	11.3%	—
GPQA (HELM)	66.6%	—

Multimodal Not comparable

DeepSeek-R1: —, Grok 4.20 (Non-Reasoning): 33.3 (#98)

Multimodal benchmarks
Benchmark	DeepSeek-R1	Grok 4.20 (Non-Reasoning)
LMArena Vision	—	1263
Blueprint-Bench 2	—	0%
LMArena Document	—	1416

Multilingual Grok 4.20 (Non-Reasoning) leads

DeepSeek-R1: 52.4 (#85), Grok 4.20 (Non-Reasoning): 54.5 (#40)

Multilingual benchmarks
Benchmark	DeepSeek-R1	Grok 4.20 (Non-Reasoning)
LMArena Non-English	1412	1441
LMArena Chinese	1442	1481
LMArena French	1417	1476
LMArena German	1404	1465
LMArena Japanese	1391	1449
LMArena Korean	1360	1417
LMArena Russian	1423	1458
LMArena Spanish	1411	1443

Instruction Following Grok 4.20 (Non-Reasoning) leads

DeepSeek-R1: 72.0 (#143), Grok 4.20 (Non-Reasoning): 74.8 (#83)

Instruction Following benchmarks
Benchmark	DeepSeek-R1	Grok 4.20 (Non-Reasoning)
LMArena Instruction Following	1382	1420
LiveBench Instruction Following	80.5%	—
IFEval	78.4%	—

Long Context Too close to call

DeepSeek-R1: 45.4 (#36), Grok 4.20 (Non-Reasoning): 45.5 (#34)

Long Context benchmarks
Benchmark	DeepSeek-R1	Grok 4.20 (Non-Reasoning)
LMArena Longer Query	1391	1437
Fiction.LiveBench	75%	—
CL-bench	—	22.2%
CL-bench Life	—	11.9%

Writing & Preference Grok 4.20 (Non-Reasoning) leads

DeepSeek-R1: 61.4 (#88), Grok 4.20 (Non-Reasoning): 65.7 (#44)

Writing & Preference benchmarks
Benchmark	DeepSeek-R1	Grok 4.20 (Non-Reasoning)
LMArena Text	1428	1451
LMArena Creative Writing	1405	1438
EQ-Bench Creative Writing	1500	1574
LMArena Multi-Turn	1405	1456
Short-Story Creative Writing	83%	—
WildBench	82.8%	—
LiveBench Language	48.5%	—

Frequently asked questions

Is DeepSeek-R1 better than Grok 4.20 (Non-Reasoning)?

Which is cheaper, DeepSeek-R1 or Grok 4.20 (Non-Reasoning)?

DeepSeek-R1 is cheaper. It lists at $0.50 per million input tokens and $2.15 per million output tokens; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.

Is DeepSeek-R1 or Grok 4.20 (Non-Reasoning) better for coding?

DeepSeek-R1 scores higher on coding benchmarks: 46.3 versus 42.1 in the Noometry coding category.

Which has the bigger context window?

Grok 4.20 (Non-Reasoning) does, with 1M tokens against 164K.

How many benchmarks do DeepSeek-R1 and Grok 4.20 (Non-Reasoning) share?

27 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.