Noometry

Model comparison

Claude Sonnet 5 vs Llama-3.3-70B-Instruct

Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 30.6 on the Noometry Index. Llama-3.3-70B-Instruct costs 26× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.

Last verified . 27 shared benchmarks.

Claude Sonnet 5 Anthropic

54.6

Rank #29 Confirmed

Llama-3.3-70B-Instruct Meta

30.6

Rank #291 Confirmed

Summary

  • They share 27 benchmarks with published results for both. Claude Sonnet 5 scores higher in 9 categories and Llama-3.3-70B-Instruct in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Sonnet 5 leads 66.2 to 15.3.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 94.7% for Claude Sonnet 5 and 5.1% for Llama-3.3-70B-Instruct.
  • Llama-3.3-70B-Instruct is cheaper at $0.10 / $0.32 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.
  • Claude Sonnet 5 accepts more context: 1M tokens versus 128K.
  • Llama-3.3-70B-Instruct has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 5Llama-3.3-70B-Instruct
ProviderAnthropicMeta
Noometry Index54.630.6
Released2026-06-292024-12-06
WeightsProprietaryOpen
Context window1M128K
Max output128K4K
Input $ / M tokens$2$0.10
Output $ / M tokens$10$0.32
Results tracked5143

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

Category by category

Coding Claude Sonnet 5 leads

Claude Sonnet 5: 55.5 (#26), Llama-3.3-70B-Instruct: 31.0 (#290)

BenchmarkClaude Sonnet 5Llama-3.3-70B-Instruct
SciCode54.3%26%
WeirdML68.8%14.4%
LMArena Coding14831268
DeepSWE53.8%—
FrontierCode42.7%—
CursorBench34.1%—
LMArena WebDev1541—
GSO37.3%—
BigCodeBench Instruct—46.9%
LiveBench Coding—36.6%
BigCodeBench Complete—57.5%
ALE-Bench1,463—

Agentic & Tool Use Claude Sonnet 5 leads

Claude Sonnet 5: 42.8 (#18), Llama-3.3-70B-Instruct: 25.8 (#105)

BenchmarkClaude Sonnet 5Llama-3.3-70B-Instruct
APEX-Agents54.5%—
Berkeley Function Calling Leaderboard—31.9%
BALROG—23%
GBAEval65.3%—
LMArena Search1194—
Vending-Bench 26,378—

Reasoning Claude Sonnet 5 leads

Claude Sonnet 5: 49.1 (#39), Llama-3.3-70B-Instruct: 14.1 (#327)

BenchmarkClaude Sonnet 5Llama-3.3-70B-Instruct
SimpleBench60.6%19.9%
CritPt16.9%0%
LMArena Hard Prompts14611257
DTBench92.5%59.5%
LMCA50%17.5%
Epoch Capabilities Index156.21127.33
ForecastBench61.158.6
NYT Connections (extended)75.1%—
Chess Puzzles35%—
LiveBench Reasoning—50.8%
Mystery Game Puzzles35%—
LiveBench Data Analysis—49.5%
Surface Evolver Bench60%—
Bench to the Future 30.14—
LiveBench—50.2%

Math Claude Sonnet 5 leads

Claude Sonnet 5: 66.2 (#27), Llama-3.3-70B-Instruct: 15.3 (#298)

BenchmarkClaude Sonnet 5Llama-3.3-70B-Instruct
OTIS Mock AIME 2024-202594.7%5.1%
LMArena Math14671267
FrontierMath (Tiers 1-3)65.6%—
FrontierMath Tier 429.3%—
ProofBench77%—
LiveBench Math—42.2%
MATH Level 5—41.6%

Knowledge Claude Sonnet 5 leads

Claude Sonnet 5: 55.6 (#47), Llama-3.3-70B-Instruct: 30.6 (#226)

BenchmarkClaude Sonnet 5Llama-3.3-70B-Instruct
GPQA Diamond90.5%47.4%
LMArena Expert14901225
SimpleQA Verified33.7%—
Confabulations—22.8%
Vectara Hallucination Rate—4.1%
MMLU—86.3%

Multimodal Not comparable

Claude Sonnet 5: 42.4 (#31), Llama-3.3-70B-Instruct: —

BenchmarkClaude Sonnet 5Llama-3.3-70B-Instruct
LMArena Vision1274—
Blueprint-Bench 224.9%—
LMArena Document1466—

Multilingual Claude Sonnet 5 leads

Claude Sonnet 5: 53.8 (#55), Llama-3.3-70B-Instruct: 39.9 (#220)

BenchmarkClaude Sonnet 5Llama-3.3-70B-Instruct
LMArena Non-English14311236
LMArena Chinese14771217
LMArena French14601281
LMArena German14401251
LMArena Japanese14221150
LMArena Korean14111143
LMArena Russian14511252
LMArena Spanish14371270

Instruction Following Claude Sonnet 5 leads

Claude Sonnet 5: 76.3 (#41), Llama-3.3-70B-Instruct: 71.1 (#157)

BenchmarkClaude Sonnet 5Llama-3.3-70B-Instruct
LMArena Instruction Following14521242
LiveBench Instruction Following—82.7%

Long Context Claude Sonnet 5 leads

Claude Sonnet 5: 44.8 (#55), Llama-3.3-70B-Instruct: 26.4 (#295)

BenchmarkClaude Sonnet 5Llama-3.3-70B-Instruct
LMArena Longer Query14631256
Fiction.LiveBench—33.3%

Writing & Preference Claude Sonnet 5 leads

Claude Sonnet 5: 69.2 (#25), Llama-3.3-70B-Instruct: 47.6 (#207)

BenchmarkClaude Sonnet 5Llama-3.3-70B-Instruct
LMArena Text14421274
LMArena Creative Writing14161250
LMArena Multi-Turn14541280
EQ-Bench Creative Writing1794—
EQ-Bench 41236—
LiveBench Language—39.2%

Frequently asked questions

Is Claude Sonnet 5 better than Llama-3.3-70B-Instruct?

Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 30.6 on the Noometry Index. Llama-3.3-70B-Instruct costs 26× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.

Which is cheaper, Claude Sonnet 5 or Llama-3.3-70B-Instruct?

Llama-3.3-70B-Instruct is cheaper. It lists at $0.10 per million input tokens and $0.32 per million output tokens; Claude Sonnet 5 lists at $2 and $10.

Is Claude Sonnet 5 or Llama-3.3-70B-Instruct better for coding?

Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 31.0 in the Noometry coding category.

Which has the bigger context window?

Claude Sonnet 5 does, with 1M tokens against 128K.

How many benchmarks do Claude Sonnet 5 and Llama-3.3-70B-Instruct share?

27 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and Llama-3.3-70B-Instruct has 43.

Related comparisons

Go deeper