Noometry

Model comparison

Grok 4.20 (Non-Reasoning) vs Llama 3.1-70B

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 29.6 on the Noometry Index. Llama 3.1-70B costs 3.9× 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 . 24 shared benchmarks.

Grok 4.20 (Non-Reasoning) xAI

48.6

Rank #54 Confirmed

Llama 3.1-70B Meta

29.6

Rank #308 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 9 categories and Llama 3.1-70B in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Grok 4.20 (Non-Reasoning) leads 48.2 to 13.5.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 92.2% for Grok 4.20 (Non-Reasoning) and 3.6% for Llama 3.1-70B.
  • Llama 3.1-70B is cheaper at $0.40 / $0.40 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 3.1-70B has downloadable open weights; the other is API-only.

Side by side

Grok 4.20 (Non-Reasoning)Llama 3.1-70B
ProviderxAIMeta
Noometry Index48.629.6
Released2026-02-172024-07-23
WeightsProprietaryOpen
Context window1M128K
Max output30K4K
Input $ / M tokens$1.25$0.40
Output $ / M tokens$2.50$0.40
Results tracked4635

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 3.1-70B: 30.3 (#296)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 3.1-70B
WeirdML52.3%9%
LMArena Coding14591260
LMArena WebDev1375—
BigCodeBench Instruct—46.1%
BigCodeBench Complete—54.8%
ALE-Bench1,150—

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

Grok 4.20 (Non-Reasoning): 34.4 (#46), Llama 3.1-70B: 25.1 (#112)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 3.1-70B
Terminal-Bench57.3%—
TheAgentCompany—6.9%
τ²-bench Banking18%—
BALROG—27.9%
LMArena Search1189—
Vending-Bench 24,663—

Reasoning Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 52.3 (#32), Llama 3.1-70B: 21.6 (#220)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 3.1-70B
LMArena Hard Prompts14511241
DTBench90.1%60%
LMCA38.7%14.8%
Epoch Capabilities Index151.98125.92
ARC-AGI-265.1%—
Kagi LLM Benchmark75%—
NYT Connections (extended)85.4%—
ARC-AGI-189.5%—
Chess Puzzles24%—
Thematic Generalization63.8%—
ForecastBench61.4—

Math Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 48.2 (#65), Llama 3.1-70B: 13.5 (#304)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 3.1-70B
OTIS Mock AIME 2024-202592.2%3.6%
LMArena Math14551252
FrontierMath (Tiers 1-3)44.9%—
FrontierMath Tier 417.1%—
ProofBench14%—
Omni-MATH—21%
MATH Level 5—36.7%

Knowledge Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 52.8 (#60), Llama 3.1-70B: 24.2 (#269)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 3.1-70B
GPQA Diamond89.3%44.2%
LMArena Expert14391209
SimpleQA Verified30.2%—
MMLU-Pro—65.3%
GPQA (HELM)—42.6%
MMLU—80.1%

Multimodal Not comparable

Grok 4.20 (Non-Reasoning): 33.3 (#98), Llama 3.1-70B: —

BenchmarkGrok 4.20 (Non-Reasoning)Llama 3.1-70B
LMArena Vision1263—
Blueprint-Bench 20%—
LMArena Document1416—

Multilingual Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 54.5 (#40), Llama 3.1-70B: 38.8 (#225)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 3.1-70B
LMArena Non-English14411219
LMArena Chinese14811215
LMArena French14761261
LMArena German14651222
LMArena Japanese14491132
LMArena Korean14171140
LMArena Russian14581234
LMArena Spanish14431253

Instruction Following Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 74.8 (#83), Llama 3.1-70B: 65.3 (#223)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 3.1-70B
LMArena Instruction Following14201231
IFEval—82.1%

Long Context Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 45.5 (#34), Llama 3.1-70B: 37.6 (#214)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 3.1-70B
LMArena Longer Query14371241
CL-bench22.2%—
CL-bench Life11.9%—

Writing & Preference Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 65.7 (#44), Llama 3.1-70B: 35.4 (#267)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 3.1-70B
LMArena Text14511261
LMArena Creative Writing14381232
EQ-Bench Creative Writing1574784
LMArena Multi-Turn14561256
WildBench—75.8%

Frequently asked questions

Is Grok 4.20 (Non-Reasoning) better than Llama 3.1-70B?

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 29.6 on the Noometry Index. Llama 3.1-70B costs 3.9× 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 3.1-70B?

Llama 3.1-70B is cheaper. It lists at $0.40 per million input tokens and $0.40 per million output tokens; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.

Is Grok 4.20 (Non-Reasoning) or Llama 3.1-70B better for coding?

Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 42.1 versus 30.3 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 3.1-70B share?

24 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Llama 3.1-70B has 35.

Related comparisons

Go deeper