Noometry

Model comparison

Claude Opus 4.8 vs Llama 3.1-70B

Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 29.4 on the Noometry Index. Llama 3.1-70B costs 25× less per token, which makes it the better buy when Claude Opus 4.8's lead doesn't matter for your workload.

Last verified . 24 shared benchmarks.

Claude Opus 4.8 Anthropic

60.7

Rank #9 Confirmed

Llama 3.1-70B Meta

29.4

Rank #299 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Claude Opus 4.8 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 Claude Opus 4.8 leads 78.2 to 12.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.3% for Claude Opus 4.8 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 $5 / $25 for Claude Opus 4.8.
  • Claude Opus 4.8 accepts more context: 1M tokens versus 128K.
  • Llama 3.1-70B has downloadable open weights; the other is API-only.

Side by side

Claude Opus 4.8Llama 3.1-70B
ProviderAnthropicMeta
Noometry Index60.729.4
Released2026-05-282024-07-23
WeightsProprietaryOpen
Context window1M128K
Max output128K4K
Input $ / M tokens$5$0.40
Output $ / M tokens$25$0.40
Results tracked6535

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

Category by category

Coding Claude Opus 4.8 leads

Claude Opus 4.8: 60.2 (#9), Llama 3.1-70B: 29.8 (#292)

BenchmarkClaude Opus 4.8Llama 3.1-70B
WeirdML82.9%9%
LMArena Coding14911260
DeepSWE59%—
FrontierCode46.5%—
LMArena WebDev1556—
SciCode53.5%—
GSO47.1%—
BigCodeBench Instruct—46.1%
BigCodeBench Complete—54.8%
ALE-Bench1,564—

Agentic & Tool Use Claude Opus 4.8 leads

Claude Opus 4.8: 47.6 (#10), Llama 3.1-70B: 24.9 (#104)

BenchmarkClaude Opus 4.8Llama 3.1-70B
APEX-Agents48.9%—
OSWorld 2.020.6%—
Remote Labor Index8.3%—
TheAgentCompany—6.9%
τ²-bench Banking39.7%—
DeepResearch Bench50.2%—
PostTrainBench33.8%—
BALROG—27.9%
GBAEval70.9%—
GDP.pdf24%—
LMArena Search1204—
Vending-Bench 25,787—

Reasoning Claude Opus 4.8 leads

Claude Opus 4.8: 64.6 (#14), Llama 3.1-70B: 20.8 (#215)

BenchmarkClaude Opus 4.8Llama 3.1-70B
LMArena Hard Prompts14811241
DTBench94.9%60%
LMCA57.5%14.8%
Epoch Capabilities Index158.3125.91
ARC-AGI-272.1%—
SimpleBench64.8%—
Kagi LLM Benchmark88.8%—
NYT Connections (extended)91.1%—
ARC-AGI-192.5%—
CritPt20.9%—
Chess Puzzles34%—
EnigmaEval23.5%—
EBR-Bench28.6%—
Mystery Game Puzzles36%—
Surface Evolver Bench87.5%—
Bench to the Future 30.14—
ForecastBench59.9—

Math Claude Opus 4.8 leads

Claude Opus 4.8: 78.2 (#11), Llama 3.1-70B: 12.7 (#298)

BenchmarkClaude Opus 4.8Llama 3.1-70B
OTIS Mock AIME 2024-202598.3%3.6%
LMArena Math14871252
FrontierMath (Tiers 1-3)80%—
FrontierMath Tier 456.1%—
MathArena Final-Answer Competitions91.8%—
ProofBench69%—
Omni-MATH—21%
MATH Level 5—36.7%
FrontierMath (Feb 2025 set)47.2%—
FrontierMath Tier 4 (v1)31.3%—

Knowledge Claude Opus 4.8 leads

Claude Opus 4.8: 61.3 (#26), Llama 3.1-70B: 24.1 (#264)

BenchmarkClaude Opus 4.8Llama 3.1-70B
GPQA Diamond91%44.2%
LMArena Expert15011209
SimpleQA Verified53%—
MMLU-Pro—65.3%
GPQA (HELM)—42.6%
MMLU—80.1%

Multimodal Not comparable

Claude Opus 4.8: 43.2 (#20), Llama 3.1-70B: —

BenchmarkClaude Opus 4.8Llama 3.1-70B
LMArena Vision1295—
Blueprint-Bench 214.5%—
Furniture Assembly42.5%—
LMArena Document1475—

Multilingual Claude Opus 4.8 leads

Claude Opus 4.8: 55.4 (#31), Llama 3.1-70B: 38.9 (#220)

BenchmarkClaude Opus 4.8Llama 3.1-70B
LMArena Non-English14501219
LMArena Chinese15091215
LMArena French14821260
LMArena German14701222
LMArena Japanese14401132
LMArena Korean14321140
LMArena Russian14761234
LMArena Spanish14701253

Instruction Following Claude Opus 4.8 leads

Claude Opus 4.8: 77.6 (#22), Llama 3.1-70B: 65.5 (#218)

BenchmarkClaude Opus 4.8Llama 3.1-70B
LMArena Instruction Following14761231
IFEval—82.1%

Long Context Claude Opus 4.8 leads

Claude Opus 4.8: 45.4 (#37), Llama 3.1-70B: 37.6 (#208)

BenchmarkClaude Opus 4.8Llama 3.1-70B
LMArena Longer Query14821241

Writing & Preference Claude Opus 4.8 leads

Claude Opus 4.8: 72.1 (#17), Llama 3.1-70B: 35.6 (#262)

BenchmarkClaude Opus 4.8Llama 3.1-70B
LMArena Text14601261
LMArena Creative Writing14531232
EQ-Bench Creative Writing1840784
LMArena Multi-Turn14761256
WildBench—75.8%
EQ-Bench 41281—

Frequently asked questions

Is Claude Opus 4.8 better than Llama 3.1-70B?

Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 29.4 on the Noometry Index. Llama 3.1-70B costs 25× less per token, which makes it the better buy when Claude Opus 4.8's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 4.8 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 Opus 4.8 lists at $5 and $25.

Is Claude Opus 4.8 or Llama 3.1-70B better for coding?

Claude Opus 4.8 scores higher on coding benchmarks: 60.2 versus 29.8 in the Noometry coding category.

Which has the bigger context window?

Claude Opus 4.8 does, with 1M tokens against 128K.

How many benchmarks do Claude Opus 4.8 and Llama 3.1-70B share?

24 benchmarks have published results for both models. Claude Opus 4.8 has 65 scored results on Noometry and Llama 3.1-70B has 35.

Related comparisons

Go deeper