Noometry

Model comparison

Claude Opus 4.8 vs Qwen2.5 72B Instruct

Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 31.9 on the Noometry Index. Qwen2.5 72B Instruct costs 4.1× 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 #13 Confirmed

Qwen2.5 72B Instruct Alibaba (Qwen)

31.9

Rank #267 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Claude Opus 4.8 scores higher in 9 categories and Qwen2.5 72B Instruct in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Opus 4.8 leads 78.4 to 19.3.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.3% for Claude Opus 4.8 and 8.1% for Qwen2.5 72B Instruct.
  • Qwen2.5 72B Instruct is cheaper at $1.40 / $5.60 per million input/output tokens, against $5 / $25 for Claude Opus 4.8.
  • Claude Opus 4.8 accepts more context: 1M tokens versus 131K.
  • Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.

Side by side

Claude Opus 4.8Qwen2.5 72B Instruct
ProviderAnthropicAlibaba (Qwen)
Noometry Index60.731.9
Released2026-05-282024-09
WeightsProprietaryOpen
Context window1M131K
Max output128K8K
Input $ / M tokens$5$1.40
Output $ / M tokens$25$5.60
Results tracked6543

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: 59.9 (#12), Qwen2.5 72B Instruct: 33.2 (#260)

BenchmarkClaude Opus 4.8Qwen2.5 72B Instruct
WeirdML82.9%16%
LMArena Coding14901292
DeepSWE59%—
FrontierCode46.5%—
LMArena WebDev1556—
SciCode53.5%—
GSO47.1%—
BigCodeBench Instruct—45.8%
BigCodeBench Complete—55.9%
ALE-Bench1,564—

Agentic & Tool Use Claude Opus 4.8 leads

Claude Opus 4.8: 47.6 (#11), Qwen2.5 72B Instruct: 22.1 (#133)

BenchmarkClaude Opus 4.8Qwen2.5 72B Instruct
APEX-Agents48.9%—
OSWorld 2.020.6%—
Remote Labor Index8.3%—
TheAgentCompany—5.7%
τ²-bench Banking39.7%—
DeepResearch Bench50.2%—
PostTrainBench33.8%—
BALROG—16.2%
GBAEval70.9%—
GDP.pdf24%—
LMArena Search1204—
METR Time Horizons—35.8%
Vending-Bench 25,787—

Reasoning Claude Opus 4.8 leads

Claude Opus 4.8: 64.7 (#16), Qwen2.5 72B Instruct: 22.3 (#199)

BenchmarkClaude Opus 4.8Qwen2.5 72B Instruct
LMArena Hard Prompts14821271
DTBench94.9%62.9%
LMCA57.5%13.4%
Epoch Capabilities Index158.21129
ForecastBench59.957.5
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—
BIG-Bench Hard—79.8%
HellaSwag—84.8%
PIQA—82.6%
WinoGrande—82.3%

Math Claude Opus 4.8 leads

Claude Opus 4.8: 78.4 (#13), Qwen2.5 72B Instruct: 19.3 (#287)

BenchmarkClaude Opus 4.8Qwen2.5 72B Instruct
OTIS Mock AIME 2024-202598.3%8.1%
LMArena Math14871283
FrontierMath (Tiers 1-3)80%—
FrontierMath Tier 456.1%—
MathArena Final-Answer Competitions91.8%—
ProofBench69%—
Omni-MATH—33%
MATH Level 5—63.2%
FrontierMath (Feb 2025 set)47.2%—
FrontierMath Tier 4 (v1)31.3%—

Knowledge Claude Opus 4.8 leads

Claude Opus 4.8: 61.3 (#29), Qwen2.5 72B Instruct: 27.0 (#253)

BenchmarkClaude Opus 4.8Qwen2.5 72B Instruct
GPQA Diamond91%49.1%
LMArena Expert15021245
SimpleQA Verified53%—
MMLU-Pro—63.1%
Confabulations—19.1%
GPQA (HELM)—42.6%
ARC (AI2) Challenge—94.5%
MMLU—85.3%
TriviaQA—71.9%

Multimodal Not comparable

Claude Opus 4.8: 42.9 (#26), Qwen2.5 72B Instruct: —

BenchmarkClaude Opus 4.8Qwen2.5 72B Instruct
LMArena Vision1294—
Blueprint-Bench 214.5%—
Furniture Assembly42.5%—
LMArena Document1475—

Multilingual Claude Opus 4.8 leads

Claude Opus 4.8: 55.2 (#33), Qwen2.5 72B Instruct: 41.0 (#213)

BenchmarkClaude Opus 4.8Qwen2.5 72B Instruct
LMArena Non-English14501252
LMArena Chinese15071272
LMArena French14811280
LMArena German14721234
LMArena Japanese14401180
LMArena Korean14321188
LMArena Russian14741264
LMArena Spanish14661256

Instruction Following Claude Opus 4.8 leads

Claude Opus 4.8: 77.4 (#24), Qwen2.5 72B Instruct: 65.5 (#221)

BenchmarkClaude Opus 4.8Qwen2.5 72B Instruct
LMArena Instruction Following14761254
IFEval—80.6%

Long Context Claude Opus 4.8 leads

Claude Opus 4.8: 45.4 (#35), Qwen2.5 72B Instruct: 38.9 (#188)

BenchmarkClaude Opus 4.8Qwen2.5 72B Instruct
LMArena Longer Query14831282

Writing & Preference Claude Opus 4.8 leads

Claude Opus 4.8: 72.0 (#16), Qwen2.5 72B Instruct: 46.7 (#215)

BenchmarkClaude Opus 4.8Qwen2.5 72B Instruct
LMArena Text14611269
LMArena Creative Writing14541221
LMArena Multi-Turn14761272
EQ-Bench Creative Writing1840—
WildBench—80.2%
EQ-Bench 41281—

Frequently asked questions

Is Claude Opus 4.8 better than Qwen2.5 72B Instruct?

Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 31.9 on the Noometry Index. Qwen2.5 72B Instruct costs 4.1× 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 Qwen2.5 72B Instruct?

Qwen2.5 72B Instruct is cheaper. It lists at $1.40 per million input tokens and $5.60 per million output tokens; Claude Opus 4.8 lists at $5 and $25.

Is Claude Opus 4.8 or Qwen2.5 72B Instruct better for coding?

Claude Opus 4.8 scores higher on coding benchmarks: 59.9 versus 33.2 in the Noometry coding category.

Which has the bigger context window?

Claude Opus 4.8 does, with 1M tokens against 131K.

How many benchmarks do Claude Opus 4.8 and Qwen2.5 72B Instruct share?

24 benchmarks have published results for both models. Claude Opus 4.8 has 65 scored results on Noometry and Qwen2.5 72B Instruct has 43.

Related comparisons

Go deeper