Model comparison

Gemma 3 4B vs Grok 4.20 (Non-Reasoning)

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 28.1 on the Noometry Index. Gemma 3 4B costs 31× 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. 20 shared benchmarks.

Gemma 3 4B

Google

28.1

Rank #326 Confirmed

Grok 4.20 (Non-Reasoning) xAI

48.6

Rank #54 Confirmed

Summary

They share 20 benchmarks with published results for both. Gemma 3 4B scores higher in 0 categories and Grok 4.20 (Non-Reasoning) in 9 categories; 9 gaps are clear of the uncertainty.
The widest gap is in knowledge, where Grok 4.20 (Non-Reasoning) leads 52.8 to 11.8.
The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 7.5% for Gemma 3 4B and 92.2% for Grok 4.20 (Non-Reasoning).
Gemma 3 4B is cheaper at $0.04 / $0.08 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 131K.
Gemma 3 4B has downloadable open weights; the other is API-only.

Side by side

Gemma 3 4B and Grok 4.20 (Non-Reasoning) specifications
	Gemma 3 4B	Grok 4.20 (Non-Reasoning)
Provider	Google	xAI
Noometry Index	28.1	48.6
Released	2025-03-12	2026-02-17
Weights	Open	Proprietary
Context window	131K	1M
Max output	4K	30K
Input $ / M tokens	$0.04	$1.25
Output $ / M tokens	$0.08	$2.50
Results tracked	22	46

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

Category by category

Coding Grok 4.20 (Non-Reasoning) leads

Gemma 3 4B: 35.9 (#215), Grok 4.20 (Non-Reasoning): 42.1 (#112)

Coding benchmarks
Benchmark	Gemma 3 4B	Grok 4.20 (Non-Reasoning)
LMArena Coding	1230	1459
LMArena WebDev	—	1375
WeirdML	—	52.3%
ALE-Bench	—	1,150

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

Gemma 3 4B: 20.9 (#142), Grok 4.20 (Non-Reasoning): 34.4 (#46)

Agentic & Tool Use benchmarks
Benchmark	Gemma 3 4B	Grok 4.20 (Non-Reasoning)
Terminal-Bench	—	57.3%
Berkeley Function Calling Leaderboard	19.6%	—
τ²-bench Banking	—	18%
LMArena Search	—	1189
Vending-Bench 2	—	4,663

Reasoning Grok 4.20 (Non-Reasoning) leads

Gemma 3 4B: 13.2 (#335), Grok 4.20 (Non-Reasoning): 52.3 (#32)

Reasoning benchmarks
Benchmark	Gemma 3 4B	Grok 4.20 (Non-Reasoning)
Kagi LLM Benchmark	25.2%	75%
Chess Puzzles	0%	24%
LMArena Hard Prompts	1253	1451
DTBench	50.9%	90.1%
LMCA	2.8%	38.7%
Epoch Capabilities Index	116.02	151.98
ARC-AGI-2	—	65.1%
NYT Connections (extended)	—	85.4%
ARC-AGI-1	—	89.5%
Thematic Generalization	—	63.8%
ForecastBench	—	61.4

Math Grok 4.20 (Non-Reasoning) leads

Gemma 3 4B: 16.8 (#292), Grok 4.20 (Non-Reasoning): 48.2 (#65)

Math benchmarks
Benchmark	Gemma 3 4B	Grok 4.20 (Non-Reasoning)
OTIS Mock AIME 2024-2025	7.5%	92.2%
LMArena Math	1239	1455
FrontierMath (Tiers 1-3)	—	44.9%
FrontierMath Tier 4	—	17.1%
ProofBench	—	14%

Knowledge Grok 4.20 (Non-Reasoning) leads

Gemma 3 4B: 11.8 (#299), Grok 4.20 (Non-Reasoning): 52.8 (#60)

Knowledge benchmarks
Benchmark	Gemma 3 4B	Grok 4.20 (Non-Reasoning)
GPQA Diamond	23.2%	89.3%
LMArena Expert	1223	1439
SimpleQA Verified	—	30.2%
Vectara Hallucination Rate	6.4%	—

Multimodal Not comparable

Gemma 3 4B: —, Grok 4.20 (Non-Reasoning): 33.3 (#98)

Multimodal benchmarks
Benchmark	Gemma 3 4B	Grok 4.20 (Non-Reasoning)
LMArena Vision	—	1263
Blueprint-Bench 2	—	0%
LMArena Document	—	1416

Multilingual Grok 4.20 (Non-Reasoning) leads

Gemma 3 4B: 42.5 (#194), Grok 4.20 (Non-Reasoning): 54.5 (#40)

Multilingual benchmarks
Benchmark	Gemma 3 4B	Grok 4.20 (Non-Reasoning)
LMArena Non-English	1273	1441
LMArena German	1281	1465
LMArena Russian	1294	1458
LMArena Chinese	—	1481
LMArena French	—	1476
LMArena Japanese	—	1449
LMArena Korean	—	1417
LMArena Spanish	—	1443

Instruction Following Grok 4.20 (Non-Reasoning) leads

Gemma 3 4B: 65.2 (#225), Grok 4.20 (Non-Reasoning): 74.8 (#83)

Instruction Following benchmarks
Benchmark	Gemma 3 4B	Grok 4.20 (Non-Reasoning)
LMArena Instruction Following	1239	1420

Long Context Grok 4.20 (Non-Reasoning) leads

Gemma 3 4B: 38.7 (#194), Grok 4.20 (Non-Reasoning): 45.5 (#34)

Long Context benchmarks
Benchmark	Gemma 3 4B	Grok 4.20 (Non-Reasoning)
LMArena Longer Query	1273	1437
CL-bench	—	22.2%
CL-bench Life	—	11.9%

Writing & Preference Grok 4.20 (Non-Reasoning) leads

Gemma 3 4B: 42.0 (#239), Grok 4.20 (Non-Reasoning): 65.7 (#44)

Writing & Preference benchmarks
Benchmark	Gemma 3 4B	Grok 4.20 (Non-Reasoning)
LMArena Text	1291	1451
LMArena Creative Writing	1271	1438
EQ-Bench Creative Writing	1068	1574
LMArena Multi-Turn	1255	1456

Frequently asked questions

Is Gemma 3 4B better than Grok 4.20 (Non-Reasoning)?

Which is cheaper, Gemma 3 4B or Grok 4.20 (Non-Reasoning)?

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.

Is Gemma 3 4B or Grok 4.20 (Non-Reasoning) better for coding?

Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 42.1 versus 35.9 in the Noometry coding category.

Which has the bigger context window?

Grok 4.20 (Non-Reasoning) does, with 1M tokens against 131K.

How many benchmarks do Gemma 3 4B and Grok 4.20 (Non-Reasoning) share?

20 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.