Noometry

Model comparison

Grok 4.20 (Non-Reasoning) vs Llama 3.1-8B

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 23.0 on the Noometry Index. Llama 3.1-8B costs 27× 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 . 25 shared benchmarks.

Grok 4.20 (Non-Reasoning) xAI

48.6

Rank #54 Confirmed

Llama 3.1-8B Meta

23.0

Rank #352 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 9 categories and Llama 3.1-8B in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Grok 4.20 (Non-Reasoning) leads 52.8 to 8.0.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 92.2% for Grok 4.20 (Non-Reasoning) and 1.7% for Llama 3.1-8B.
  • Llama 3.1-8B is cheaper at $0.05 / $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 128K.
  • Llama 3.1-8B has downloadable open weights; the other is API-only.

Side by side

Grok 4.20 (Non-Reasoning)Llama 3.1-8B
ProviderxAIMeta
Noometry Index48.623.0
Released2026-02-172024-07-23
WeightsProprietaryOpen
Context window1M128K
Max output30K4K
Input $ / M tokens$1.25$0.05
Output $ / M tokens$2.50$0.08
Results tracked4643

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

Category by category

Coding Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 42.1 (#112), Llama 3.1-8B: 20.2 (#340)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 3.1-8B
WeirdML52.3%1.7%
LMArena Coding14591195
LMArena WebDev1375—
SciCode—13.2%
BigCodeBench Instruct—32.8%
BigCodeBench Complete—40.5%
ALE-Bench1,150—
HumanEval+—62.8%
MBPP+—55.6%

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

Grok 4.20 (Non-Reasoning): 34.4 (#46), Llama 3.1-8B: 22.5 (#131)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 3.1-8B
Terminal-Bench57.3%—
Berkeley Function Calling Leaderboard—25.8%
τ²-bench Banking18%—
BALROG—15.1%
LMArena Search1189—
Vending-Bench 24,663—

Reasoning Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 52.3 (#32), Llama 3.1-8B: 14.9 (#321)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 3.1-8B
Chess Puzzles24%0%
LMArena Hard Prompts14511175
DTBench90.1%50.9%
LMCA38.7%5.4%
Epoch Capabilities Index151.98116.57
ARC-AGI-265.1%—
Kagi LLM Benchmark75%—
NYT Connections (extended)85.4%—
ARC-AGI-189.5%—
CritPt—0%
Thematic Generalization63.8%—
ForecastBench61.4—
PIQA—81.2%

Math Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 48.2 (#65), Llama 3.1-8B: 10.2 (#317)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 3.1-8B
OTIS Mock AIME 2024-202592.2%1.7%
LMArena Math14551179
FrontierMath (Tiers 1-3)44.9%—
FrontierMath Tier 417.1%—
ProofBench14%—
Omni-MATH—13.7%
MATH Level 5—22.9%
GSM8K—82.4%

Knowledge Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 52.8 (#60), Llama 3.1-8B: 8.0 (#307)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 3.1-8B
GPQA Diamond89.3%27%
LMArena Expert14391144
SimpleQA Verified30.2%—
MMLU-Pro—40.6%
GPQA (HELM)—24.7%
BoolQ—82.8%
MMLU—56.1%

Multimodal Not comparable

Grok 4.20 (Non-Reasoning): 33.3 (#98), Llama 3.1-8B: —

BenchmarkGrok 4.20 (Non-Reasoning)Llama 3.1-8B
LMArena Vision1263—
Blueprint-Bench 20%—
LMArena Document1416—

Multilingual Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 54.5 (#40), Llama 3.1-8B: 34.0 (#249)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 3.1-8B
LMArena Non-English14411148
LMArena Chinese14811151
LMArena French14761177
LMArena German14651144
LMArena Japanese14491061
LMArena Korean14171053
LMArena Russian14581158
LMArena Spanish14431169

Instruction Following Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 74.8 (#83), Llama 3.1-8B: 58.9 (#258)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 3.1-8B
LMArena Instruction Following14201159
IFEval—74.3%

Long Context Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 45.5 (#34), Llama 3.1-8B: 35.8 (#238)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 3.1-8B
LMArena Longer Query14371182
CL-bench22.2%—
CL-bench Life11.9%—

Writing & Preference Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 65.7 (#44), Llama 3.1-8B: 29.7 (#290)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 3.1-8B
LMArena Text14511187
LMArena Creative Writing14381154
EQ-Bench Creative Writing1574713
LMArena Multi-Turn14561172
WildBench—68.7%

Frequently asked questions

Is Grok 4.20 (Non-Reasoning) better than Llama 3.1-8B?

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 23.0 on the Noometry Index. Llama 3.1-8B costs 27× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.

Which is cheaper, Grok 4.20 (Non-Reasoning) or Llama 3.1-8B?

Llama 3.1-8B is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.

Is Grok 4.20 (Non-Reasoning) or Llama 3.1-8B better for coding?

Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 42.1 versus 20.2 in the Noometry coding category.

Which has the bigger context window?

Grok 4.20 (Non-Reasoning) does, with 1M tokens against 128K.

How many benchmarks do Grok 4.20 (Non-Reasoning) and Llama 3.1-8B share?

25 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Llama 3.1-8B has 43.

Related comparisons

Go deeper