Noometry

Model comparison

GLM-4.7-Flash vs Llama 3.1-70B

GLM-4.7-Flash is the stronger model overall, scoring 38.4 to 29.4 on the Noometry Index.

Last verified . 19 shared benchmarks.

GLM-4.7-Flash Z.ai (Zhipu)

38.4

Rank #175 Confirmed

Llama 3.1-70B Meta

29.4

Rank #299 Confirmed

Summary

  • They share 19 benchmarks with published results for both. GLM-4.7-Flash scores higher in 7 categories and Llama 3.1-70B in 1 category; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where GLM-4.7-Flash leads 34.4 to 12.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 58.3% for GLM-4.7-Flash and 3.6% for Llama 3.1-70B.
  • GLM-4.7-Flash is cheaper at $0.06 / $0.40 per million input/output tokens, against $0.40 / $0.40 for Llama 3.1-70B.
  • GLM-4.7-Flash accepts more context: 200K tokens versus 128K.

Side by side

GLM-4.7-FlashLlama 3.1-70B
ProviderZ.ai (Zhipu)Meta
Noometry Index38.429.4
Released2026-01-192024-07-23
WeightsOpenOpen
Context window200K128K
Max output131K4K
Input $ / M tokens$0.06$0.40
Output $ / M tokens$0.40$0.40
Results tracked2135

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

Category by category

Coding GLM-4.7-Flash leads

GLM-4.7-Flash: 40.0 (#133), Llama 3.1-70B: 29.8 (#292)

BenchmarkGLM-4.7-FlashLlama 3.1-70B
LMArena Coding13831260
WeirdML—9%
BigCodeBench Instruct—46.1%
BigCodeBench Complete—54.8%

Agentic & Tool Use Not comparable

GLM-4.7-Flash: —, Llama 3.1-70B: 24.9 (#104)

BenchmarkGLM-4.7-FlashLlama 3.1-70B
TheAgentCompany—6.9%
BALROG—27.9%

Reasoning Too close to call

GLM-4.7-Flash: 20.2 (#224), Llama 3.1-70B: 20.8 (#215)

BenchmarkGLM-4.7-FlashLlama 3.1-70B
LMArena Hard Prompts13561241
Chess Puzzles0%—
DTBench—60%
LMCA—14.8%
Epoch Capabilities Index—125.91

Math GLM-4.7-Flash leads

GLM-4.7-Flash: 34.4 (#159), Llama 3.1-70B: 12.7 (#298)

BenchmarkGLM-4.7-FlashLlama 3.1-70B
OTIS Mock AIME 2024-202558.3%3.6%
LMArena Math13541252
Omni-MATH—21%
MATH Level 5—36.7%

Knowledge GLM-4.7-Flash leads

GLM-4.7-Flash: 35.4 (#177), Llama 3.1-70B: 24.1 (#264)

BenchmarkGLM-4.7-FlashLlama 3.1-70B
GPQA Diamond60.5%44.2%
LMArena Expert13571209
MMLU-Pro—65.3%
Vectara Hallucination Rate9.3%—
GPQA (HELM)—42.6%
MMLU—80.1%

Multilingual GLM-4.7-Flash leads

GLM-4.7-Flash: 46.8 (#152), Llama 3.1-70B: 38.9 (#220)

BenchmarkGLM-4.7-FlashLlama 3.1-70B
LMArena Non-English13311219
LMArena Chinese14031215
LMArena French13321260
LMArena German13361222
LMArena Korean12841140
LMArena Russian13331234
LMArena Spanish13511253
LMArena Japanese—1132

Instruction Following GLM-4.7-Flash leads

GLM-4.7-Flash: 70.3 (#162), Llama 3.1-70B: 65.5 (#218)

BenchmarkGLM-4.7-FlashLlama 3.1-70B
LMArena Instruction Following13271231
IFEval—82.1%

Long Context GLM-4.7-Flash leads

GLM-4.7-Flash: 40.9 (#143), Llama 3.1-70B: 37.6 (#208)

BenchmarkGLM-4.7-FlashLlama 3.1-70B
LMArena Longer Query13451241

Writing & Preference GLM-4.7-Flash leads

GLM-4.7-Flash: 47.7 (#206), Llama 3.1-70B: 35.6 (#262)

BenchmarkGLM-4.7-FlashLlama 3.1-70B
LMArena Text13511261
LMArena Creative Writing12971232
EQ-Bench Creative Writing1125784
LMArena Multi-Turn13421256
WildBench—75.8%

Frequently asked questions

Is GLM-4.7-Flash better than Llama 3.1-70B?

GLM-4.7-Flash is the stronger model overall, scoring 38.4 to 29.4 on the Noometry Index.

Which is cheaper, GLM-4.7-Flash or Llama 3.1-70B?

GLM-4.7-Flash is cheaper. It lists at $0.06 per million input tokens and $0.40 per million output tokens; Llama 3.1-70B lists at $0.40 and $0.40.

Is GLM-4.7-Flash or Llama 3.1-70B better for coding?

GLM-4.7-Flash scores higher on coding benchmarks: 40.0 versus 29.8 in the Noometry coding category.

Which has the bigger context window?

GLM-4.7-Flash does, with 200K tokens against 128K.

How many benchmarks do GLM-4.7-Flash and Llama 3.1-70B share?

19 benchmarks have published results for both models. GLM-4.7-Flash has 21 scored results on Noometry and Llama 3.1-70B has 35.

Related comparisons

Go deeper