Noometry

Model comparison

Claude Sonnet 4.5 vs Llama 3.1-8B

Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 23.0 on the Noometry Index. Llama 3.1-8B costs 104× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

Last verified . 34 shared benchmarks.

Claude Sonnet 4.5 Anthropic

44.1

Rank #81 Confirmed

Llama 3.1-8B Meta

23.0

Rank #352 Confirmed

Summary

  • They share 34 benchmarks with published results for both. Claude Sonnet 4.5 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 Claude Sonnet 4.5 leads 48.4 to 8.0.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 77.8% for Claude Sonnet 4.5 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 $3 / $15 for Claude Sonnet 4.5.
  • Claude Sonnet 4.5 accepts more context: 200K tokens versus 128K.
  • Llama 3.1-8B has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 4.5Llama 3.1-8B
ProviderAnthropicMeta
Noometry Index44.123.0
Released2025-09-292024-07-23
WeightsProprietaryOpen
Context window200K128K
Max output64K4K
Input $ / M tokens$3$0.05
Output $ / M tokens$15$0.08
Results tracked7343

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 3.1-8B: 20.2 (#340)

BenchmarkClaude Sonnet 4.5Llama 3.1-8B
SciCode44.7%13.2%
WeirdML47.7%1.7%
LMArena Coding14891195
SWE-bench Verified71.3%—
SWE-bench Verified (bash only)71.4%—
LMArena WebDev1393—
SWE-bench Multilingual67%—
GSO14.7%—
BigCodeBench Instruct—32.8%
BigCodeBench Complete—40.5%
ALE-Bench796.15—
AlgoTune1.52—
HumanEval+—62.8%
MBPP+—55.6%

Agentic & Tool Use Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 38.3 (#32), Llama 3.1-8B: 22.5 (#131)

BenchmarkClaude Sonnet 4.5Llama 3.1-8B
Berkeley Function Calling Leaderboard73.2%25.8%
Terminal-Bench46.5%—
GDPval42.5%—
Remote Labor Index2.1%—
τ²-bench Airline72%—
τ²-bench Banking25.3%—
τ²-bench Retail72.4%—
τ²-bench Telecom84.9%—
Cybench60%—
DeepResearch Bench52.6%—
OSWorld62.9%—
BALROG—15.1%
LMArena Search1159—
METR Time Horizons67.4%—
Vending-Bench 23,839—

Reasoning Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 26.9 (#125), Llama 3.1-8B: 14.9 (#321)

BenchmarkClaude Sonnet 4.5Llama 3.1-8B
CritPt1.1%0%
Chess Puzzles12%0%
LMArena Hard Prompts14621175
DTBench83.2%50.9%
LMCA38.8%5.4%
Epoch Capabilities Index146.84116.57
ARC-AGI-213.6%—
SimpleBench54.3%—
Kagi LLM Benchmark57.9%—
NYT Connections (extended)37.3%—
ARC-AGI-163.7%—
EnigmaEval6%—
EBR-Bench2.4%—
Mystery Game Puzzles17%—
ForecastBench61.9—
PIQA—81.2%

Math Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 32.3 (#216), Llama 3.1-8B: 10.2 (#317)

BenchmarkClaude Sonnet 4.5Llama 3.1-8B
OTIS Mock AIME 2024-202577.8%1.7%
Omni-MATH55.3%13.7%
LMArena Math14491179
MATH Level 597.7%22.9%
FrontierMath (Tiers 1-3)23.9%—
FrontierMath Tier 42.4%—
ProofBench19%—
FrontierMath (Feb 2025 set)15.2%—
FrontierMath Tier 4 (v1)4.2%—
GSM8K—82.4%

Knowledge Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 48.4 (#76), Llama 3.1-8B: 8.0 (#307)

BenchmarkClaude Sonnet 4.5Llama 3.1-8B
GPQA Diamond82.3%27%
MMLU-Pro86.9%40.6%
GPQA (HELM)68.6%24.7%
LMArena Expert14821144
Humanity's Last Exam13.7%—
SimpleQA Verified30.7%—
Vectara Hallucination Rate12%—
BoolQ—82.8%
MMLU—56.1%

Multimodal Not comparable

Claude Sonnet 4.5: 34.8 (#89), Llama 3.1-8B: —

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

Multilingual Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 53.4 (#69), Llama 3.1-8B: 34.0 (#249)

BenchmarkClaude Sonnet 4.5Llama 3.1-8B
LMArena Non-English14251148
LMArena Chinese14591151
LMArena French14581177
LMArena German14271144
LMArena Japanese13901061
LMArena Korean14031053
LMArena Russian14371158
LMArena Spanish14571169

Instruction Following Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 75.0 (#78), Llama 3.1-8B: 58.9 (#258)

BenchmarkClaude Sonnet 4.5Llama 3.1-8B
IFEval85%74.3%
LMArena Instruction Following14591159

Long Context Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 45.2 (#46), Llama 3.1-8B: 35.8 (#238)

BenchmarkClaude Sonnet 4.5Llama 3.1-8B
LMArena Longer Query14761182

Writing & Preference Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 66.5 (#34), Llama 3.1-8B: 29.7 (#290)

BenchmarkClaude Sonnet 4.5Llama 3.1-8B
LMArena Text14391187
LMArena Creative Writing14421154
EQ-Bench Creative Writing1678713
WildBench85.4%68.7%
LMArena Multi-Turn14651172

Frequently asked questions

Is Claude Sonnet 4.5 better than Llama 3.1-8B?

Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 23.0 on the Noometry Index. Llama 3.1-8B costs 104× 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 3.1-8B?

Llama 3.1-8B is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.

Is Claude Sonnet 4.5 or Llama 3.1-8B better for coding?

Claude Sonnet 4.5 scores higher on coding benchmarks: 47.3 versus 20.2 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 3.1-8B share?

34 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Llama 3.1-8B has 43.

Related comparisons

Go deeper