Enter opens the highlighted result. Esc closes.

GLM 4.7 vs Llama 3.1 70B Instruct

GLM 4.7 leads Llama 3.1 70B Instruct on the Artificial Analysis Intelligence Index, 22.2 to 6.6, and Llama 3.1 70B Instruct costs 3.9x less per output token ($0.56 vs $2.20 per million). Updated October 21, 2026; 40 benchmarks have a result for both.

Replace GLM 4.7 Replace Llama 3.1 70B Instruct
GLM 4.7Z.ai
Coding
55.1
Overall
22.2
Output $/M
$2.20
40
Llama 3.1 70B InstructMeta Llama
Coding
No data
Overall
6.6
Output $/M
$0.56
0
vs boards won of 40 shared

GLM 4.7 or Llama 3.1 70B Instruct: which to pick

Only GLM 4.7 has a coding score, 55.1 on the Vibe Coding Index; Llama 3.1 70B Instruct has none, so the two cannot be ranked on coding.

Pick Llama 3.1 70B Instruct for output tokens 3.9x cheaper ($0.56 vs $2.20 per million).

Model AGLM 4.7Z.ai55.1/1002 independent benchmarks$0.29 per solved taskModel BLlama 3.1 70B InstructMeta LlamaNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
40
GLM 4.7 only
40
Llama 3.1 70B Instruct only
7
Like-for-like categories
7 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
GLM 4.7 55.1 from 2 benchmarks, Llama 3.1 70B Instruct not benchmarked.
Widest category
Agentic work, 80.7 points apart on average over 1 shared benchmark.
Widest single gap
AA Math Index: GLM 4.7 95.0 against Llama 3.1 70B Instruct 4.0, 91.0 points apart on a 0 to 100 scale.
Output price
GLM 4.7 $2.20 against Llama 3.1 70B Instruct $0.56 per million output tokens, 3.9x apart.
Context window
GLM 4.7 takes 205K tokens, Llama 3.1 70B Instruct 131K.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryGLM 4.7BarsLlama 3.1 70B InstructTies
Coding40
Intelligence20
Agentic work10
Reasoning60
Math50
Knowledge50
General170
All shared boards400
CodingLike-for-likeSix of these boards feed the Vibe Coding Index40
Coding benchmarks for GLM 4.7 and Llama 3.1 70B Instruct
BenchmarkGLM 4.7Llama 3.1 70B InstructLeader
LMArena WebDev1435Not measuredOnly GLM 4.7 measured
AA Coding Index45.3Not measuredOnly GLM 4.7 measured
LiveCodeBench (Vals AI)82.2%Not measuredOnly GLM 4.7 measured
SWE-bench Verified (Vals AI)69.4%Not measuredOnly GLM 4.7 measured
LiveCodeBench (Artificial Analysis run)89.4%23.2%GLM 4.7
Terminal-Bench Hard (Artificial Analysis run)31.8%3.0%GLM 4.7
Terminal-Bench33.4%Not measuredOnly GLM 4.7 measured
WeirdMLNot measured9.0%Only Llama 3.1 70B Instruct measured
ALE-Bench399.5Not measuredOnly GLM 4.7 measured
LMArena Text: coding14541260GLM 4.7
LMArena Text: software and IT14531260GLM 4.7
LMArena WebDev: React1420Not measuredOnly GLM 4.7 measured
LMArena WebDev: HTML1447Not measuredOnly GLM 4.7 measured
Neither model has a result on the other 25 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for GLM 4.7 and Llama 3.1 70B Instruct
BenchmarkGLM 4.7Llama 3.1 70B InstructLeader
AA Intelligence Index22.26.6GLM 4.7
Epoch Capabilities Index143.6125.9GLM 4.7
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for GLM 4.7 and Llama 3.1 70B Instruct
BenchmarkGLM 4.7Llama 3.1 70B InstructLeader
Design Arena: agents building full-stack apps1050Not measuredOnly GLM 4.7 measured
Design Arena: agents building mobile apps1105Not measuredOnly GLM 4.7 measured
Design Arena: agents building Android apps1112Not measuredOnly GLM 4.7 measured
Design Arena: agents building Godot games1058Not measuredOnly GLM 4.7 measured
τ²-Bench Telecom95.9%15.2%GLM 4.7
BALROGNot measured27.9%Only Llama 3.1 70B Instruct measured
TheAgentCompanyNot measured6.9%Only Llama 3.1 70B Instruct measured
Vending-Bench 2$2,377Not measuredOnly GLM 4.7 measured
Neither model has a result on the other 31 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index60
Reasoning benchmarks for GLM 4.7 and Llama 3.1 70B Instruct
BenchmarkGLM 4.7Llama 3.1 70B InstructLeader
GPQA Diamond80.0%Not measuredOnly GLM 4.7 measured
GPQA Diamond (Artificial Analysis run)85.9%40.9%GLM 4.7
Humanity's Last Exam (Artificial Analysis run)27.4%4.5%GLM 4.7
GPQA Diamond (Epoch AI run)83.3%44.2%GLM 4.7
SimpleBench47.7%Not measuredOnly GLM 4.7 measured
Chess puzzles21.0%Not measuredOnly GLM 4.7 measured
LMArena Text: hard prompts14431241GLM 4.7
LMArena Text: expert14241209GLM 4.7
LMArena Text: hard prompts in English14521261GLM 4.7
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index50
Math benchmarks for GLM 4.7 and Llama 3.1 70B Instruct
BenchmarkGLM 4.7Llama 3.1 70B InstructLeader
AIME93.3%Not measuredOnly GLM 4.7 measured
MGSM (Vals AI)88.2%Not measuredOnly GLM 4.7 measured
AA Math Index95.04.0GLM 4.7
AIME 2025 (Artificial Analysis run)95.0%4.0%GLM 4.7
OTIS Mock AIME83.3%3.6%GLM 4.7
ProofBench6.0%Not measuredOnly GLM 4.7 measured
MATH level 5Not measured36.7%Only Llama 3.1 70B Instruct measured
LMArena Text: math14241252GLM 4.7
LMArena Text: mathematical work14111253GLM 4.7
Neither model has a result on the other 4 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
Knowledge benchmarks for GLM 4.7 and Llama 3.1 70B Instruct
BenchmarkGLM 4.7Llama 3.1 70B InstructLeader
MMLU Pro82.7%Not measuredOnly GLM 4.7 measured
LegalBench (Vals AI)83.4%Not measuredOnly GLM 4.7 measured
CaseLaw (Vals AI)54.9%Not measuredOnly GLM 4.7 measured
CorpFin (Vals AI)46.4%Not measuredOnly GLM 4.7 measured
TaxEval (Vals AI)68.8%Not measuredOnly GLM 4.7 measured
MedQA (Vals AI)93.7%Not measuredOnly GLM 4.7 measured
MedCode (Vals AI)32.8%Not measuredOnly GLM 4.7 measured
MMLU Pro (Artificial Analysis run)85.6%67.6%GLM 4.7
SimpleQA Verified32.2%Not measuredOnly GLM 4.7 measured
MMLUNot measured80.1%Only Llama 3.1 70B Instruct measured
LMArena Text: science14571276GLM 4.7
LMArena Text: medicine and healthcare14691257GLM 4.7
LMArena Text: legal and government14441283GLM 4.7
LMArena Text: business and finance14291235GLM 4.7
Neither model has a result on the other 3 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for GLM 4.7 and Llama 3.1 70B Instruct
BenchmarkGLM 4.7Llama 3.1 70B InstructLeader
Design Arena: websites1226Not measuredOnly GLM 4.7 measured
Design Arena: UI components1199Not measuredOnly GLM 4.7 measured
Design Arena: game dev1189Not measuredOnly GLM 4.7 measured
Design Arena: data viz1195Not measuredOnly GLM 4.7 measured
Design Arena: 3D1191Not measuredOnly GLM 4.7 measured
Design Arena: all code categories1217Not measuredOnly GLM 4.7 measured
Design Arena: SVG1143Not measuredOnly GLM 4.7 measured
Design Arena: ASCII art1165Not measuredOnly GLM 4.7 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index170
General benchmarks for GLM 4.7 and Llama 3.1 70B Instruct
BenchmarkGLM 4.7Llama 3.1 70B InstructLeader
MedScribe (Vals AI)68.6%Not measuredOnly GLM 4.7 measured
IFBench67.9%34.4%GLM 4.7
Long context reasoning (AA-LCR)71.0%Not measuredOnly GLM 4.7 measured
DTBenchNot measured60.0%Only Llama 3.1 70B Instruct measured
LMCANot measured14.8%Only Llama 3.1 70B Instruct measured
CL-bench15.9%Not measuredOnly GLM 4.7 measured
CL-bench Life10.9%Not measuredOnly GLM 4.7 measured
LMArena Text14351261GLM 4.7
LMArena Text: instruction following14121231GLM 4.7
LMArena Text: creative writing14011232GLM 4.7
LMArena Text: English14531294GLM 4.7
LMArena Text: non-English14171219GLM 4.7
LMArena Text: Chinese14951215GLM 4.7
LMArena Text: German14261222GLM 4.7
LMArena Text: Japanese14391132GLM 4.7
LMArena Text: Korean13991140GLM 4.7
LMArena Text: French14321262GLM 4.7
LMArena Text: Spanish14341253GLM 4.7
LMArena Text: Russian14231234GLM 4.7
LMArena Text: Polish1435Not measuredOnly GLM 4.7 measured
LMArena Text: multi-turn14461256GLM 4.7
LMArena Text: longer queries14321241GLM 4.7
LMArena Text: writing and language14111236GLM 4.7
LMArena Text: entertainment and media14001230GLM 4.7
Neither model has a result on the other 22 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GLM 4.7 and Llama 3.1 70B Instruct
BenchmarkGLM 4.7Llama 3.1 70B InstructLeader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

GLM 4.7$0.0017Fits in one request
Llama 3.1 70B Instruct$0.0008Fits in one request

Llama 3.1 70B Instruct costs less

Repository review

50K input + 3K output tokens

GLM 4.7$0.037Fits in one request
Llama 3.1 70B Instruct$0.030Fits in one request

Llama 3.1 70B Instruct costs less

Agent loop

200K input + 10K output tokens

GLM 4.7$0.142Exceeds the context window
Llama 3.1 70B Instruct$0.118Exceeds the context window

Llama 3.1 70B Instruct costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of GLM 4.7 and Llama 3.1 70B Instruct
SpecificationZ.ai GLM 4.7Meta Llama 3.1 70B Instruct
MakerZ.aiMeta Llama
WeightsOpen weightsOpen weights
ReleasedDecember 22, 2025July 23, 2024
Context window205K131K
Input $/Mtok$0.60$0.56
Output $/Mtok$2.20$0.56
Coding index55.1Not benchmarked
Independent measurements behind it20
Cost per solved task$0.29Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GLM 4.7 better than Llama 3.1 70B Instruct for coding?

Only GLM 4.7 has a coding score, 55.1 on the Vibe Coding Index; Llama 3.1 70B Instruct has none, so the two cannot be ranked on coding. Pick Llama 3.1 70B Instruct for output tokens 3.9x cheaper ($0.56 vs $2.20 per million).

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

GLM 4.7 costs $0.60 per million input tokens and $2.20 per million output tokens; Llama 3.1 70B Instruct costs $0.56 and $0.56. Cost per solved task is known for GLM 4.7 only.

Which has the bigger context window, GLM 4.7 or Llama 3.1 70B Instruct?

GLM 4.7, with 205K tokens against 131K.

How many benchmarks is the GLM 4.7 vs Llama 3.1 70B Instruct comparison based on?

40 benchmarks have a result for both models as of October 21, 2026. GLM 4.7's coding index rests on 2 independent benchmarks and Llama 3.1 70B Instruct's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next