Noometry

Model comparison

Claude Sonnet 4.5 vs Llama 3.1-70B

Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 29.6 on the Noometry Index. Llama 3.1-70B costs 15× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

Last verified . 30 shared benchmarks.

Claude Sonnet 4.5 Anthropic

44.1

Rank #81 Confirmed

Llama 3.1-70B Meta

29.6

Rank #308 Confirmed

Summary

  • They share 30 benchmarks with published results for both. Claude Sonnet 4.5 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 writing & preference, where Claude Sonnet 4.5 leads 66.5 to 35.4.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 77.8% for Claude Sonnet 4.5 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 $3 / $15 for Claude Sonnet 4.5.
  • Claude Sonnet 4.5 accepts more context: 200K tokens versus 128K.
  • Llama 3.1-70B has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 4.5Llama 3.1-70B
ProviderAnthropicMeta
Noometry Index44.129.6
Released2025-09-292024-07-23
WeightsProprietaryOpen
Context window200K128K
Max output64K4K
Input $ / M tokens$3$0.40
Output $ / M tokens$15$0.40
Results tracked7335

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

Category by category

Coding Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 47.3 (#61), Llama 3.1-70B: 30.3 (#296)

BenchmarkClaude Sonnet 4.5Llama 3.1-70B
WeirdML47.7%9%
LMArena Coding14891260
SWE-bench Verified71.3%—
SWE-bench Verified (bash only)71.4%—
LMArena WebDev1393—
SWE-bench Multilingual67%—
SciCode44.7%—
GSO14.7%—
BigCodeBench Instruct—46.1%
BigCodeBench Complete—54.8%
ALE-Bench796.15—
AlgoTune1.52—

Agentic & Tool Use Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 38.3 (#32), Llama 3.1-70B: 25.1 (#112)

BenchmarkClaude Sonnet 4.5Llama 3.1-70B
Terminal-Bench46.5%—
Berkeley Function Calling Leaderboard73.2%—
GDPval42.5%—
Remote Labor Index2.1%—
TheAgentCompany—6.9%
τ²-bench Airline72%—
τ²-bench Banking25.3%—
τ²-bench Retail72.4%—
τ²-bench Telecom84.9%—
Cybench60%—
DeepResearch Bench52.6%—
OSWorld62.9%—
BALROG—27.9%
LMArena Search1159—
METR Time Horizons67.4%—
Vending-Bench 23,839—

Reasoning Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 26.9 (#125), Llama 3.1-70B: 21.6 (#220)

BenchmarkClaude Sonnet 4.5Llama 3.1-70B
LMArena Hard Prompts14621241
DTBench83.2%60%
LMCA38.8%14.8%
Epoch Capabilities Index146.84125.92
ARC-AGI-213.6%—
SimpleBench54.3%—
Kagi LLM Benchmark57.9%—
NYT Connections (extended)37.3%—
ARC-AGI-163.7%—
CritPt1.1%—
Chess Puzzles12%—
EnigmaEval6%—
EBR-Bench2.4%—
Mystery Game Puzzles17%—
ForecastBench61.9—

Math Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 32.3 (#216), Llama 3.1-70B: 13.5 (#304)

BenchmarkClaude Sonnet 4.5Llama 3.1-70B
OTIS Mock AIME 2024-202577.8%3.6%
Omni-MATH55.3%21%
LMArena Math14491252
MATH Level 597.7%36.7%
FrontierMath (Tiers 1-3)23.9%—
FrontierMath Tier 42.4%—
ProofBench19%—
FrontierMath (Feb 2025 set)15.2%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 48.4 (#76), Llama 3.1-70B: 24.2 (#269)

BenchmarkClaude Sonnet 4.5Llama 3.1-70B
GPQA Diamond82.3%44.2%
MMLU-Pro86.9%65.3%
GPQA (HELM)68.6%42.6%
LMArena Expert14821209
Humanity's Last Exam13.7%—
SimpleQA Verified30.7%—
Vectara Hallucination Rate12%—
MMLU—80.1%

Multimodal Not comparable

Claude Sonnet 4.5: 34.8 (#89), Llama 3.1-70B: —

BenchmarkClaude Sonnet 4.5Llama 3.1-70B
VPCT39.8%—
LMArena Document1450—

Multilingual Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 53.4 (#69), Llama 3.1-70B: 38.8 (#225)

BenchmarkClaude Sonnet 4.5Llama 3.1-70B
LMArena Non-English14251219
LMArena Chinese14591215
LMArena French14581261
LMArena German14271222
LMArena Japanese13901132
LMArena Korean14031140
LMArena Russian14371234
LMArena Spanish14571253

Instruction Following Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 75.0 (#78), Llama 3.1-70B: 65.3 (#223)

BenchmarkClaude Sonnet 4.5Llama 3.1-70B
IFEval85%82.1%
LMArena Instruction Following14591231

Long Context Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 45.2 (#46), Llama 3.1-70B: 37.6 (#214)

BenchmarkClaude Sonnet 4.5Llama 3.1-70B
LMArena Longer Query14761241

Writing & Preference Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 66.5 (#34), Llama 3.1-70B: 35.4 (#267)

BenchmarkClaude Sonnet 4.5Llama 3.1-70B
LMArena Text14391261
LMArena Creative Writing14421232
EQ-Bench Creative Writing1678784
WildBench85.4%75.8%
LMArena Multi-Turn14651256

Frequently asked questions

Is Claude Sonnet 4.5 better than Llama 3.1-70B?

Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 29.6 on the Noometry Index. Llama 3.1-70B costs 15× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

Which is cheaper, Claude Sonnet 4.5 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; Claude Sonnet 4.5 lists at $3 and $15.

Is Claude Sonnet 4.5 or Llama 3.1-70B better for coding?

Claude Sonnet 4.5 scores higher on coding benchmarks: 47.3 versus 30.3 in the Noometry coding category.

Which has the bigger context window?

Claude Sonnet 4.5 does, with 200K tokens against 128K.

How many benchmarks do Claude Sonnet 4.5 and Llama 3.1-70B share?

30 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Llama 3.1-70B has 35.

Related comparisons

Go deeper