The Model Index
Up to four models

Qwen3.8-27B vs Claude Opus 4.5

On the index (GPT-4 = 100), Qwen3.8-27B scores 155 and Claude Opus 4.5 152. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Next to Qwen3.8-27B
Presets
Qwen3.8-27B
155139–171
WeightsOpen
ReleasedAug 2026
Price in / out$0.060 / $2.2
Context1.02M
Core tests taken3 of 9
Claude Opus 4.5
152136–168
WeightsClosed
ReleasedNov 2025
Price in / out$5.0 / $25
Context200K
Core tests taken5 of 9

Qwen3.8-27B and Claude Opus 4.5 are too close to call (3 points apart, within the uncertainty), and costs 17× less.

Test by testthird-party results

Qwen3.8-27BClaude Opus 4.5
0%25%50%75%100%REASONING & KNOWLEDGELiveBench Data AnalysisLiveBench Data AnalysisLiveBench IFLiveBench IFLiveBench LanguageLiveBench LanguageLiveBench ReasoningLiveBench ReasoningGPQA Diamond (Vals AI)GPQA Diamond (Vals AI)MMLU ProMMLU ProMMMU ProMMMU ProGeoBenchGeoBenchSimpleBenchSimpleBenchMATHSLiveBench MathematicsLiveBench MathematicsCODINGLiveBench Agentic CodingLiveBench Agentic CodingLiveBench CodingLiveBench CodingLiveCodeBenchLiveCodeBenchSWE-benchSWE-benchVibe Code Bench v1.1Vibe Code Bench v1.1AGENTSDTBenchDTBenchLMCALMCAPROFESSIONAL WORKLegalBenchLegalBenchMedCodeMedCodeMedScribeMedScribeMortgageTaxMortgageTaxTaxEval v2TaxEval v2
Every result as a table
TestQwen3.8-27BClaude Opus 4.5
Reasoning & knowledge
LiveBench Data Analysis76.6%74.4%
LiveBench IF72.7%62.5%
LiveBench Language74.4%81.3%
LiveBench Reasoning80.0%80.1%
GPQA Diamond (Vals AI)88.9%85.9%
MMLU Pro84.3%87.3%
MMMU Pro83.9%83.0%
GeoBench38.0%75.0%
SimpleBench60.2%62.0%
Maths
LiveBench Mathematics86.2%90.4%
Coding
LiveBench Agentic Coding61.4%39.7%
LiveBench Coding75.7%79.7%
LiveCodeBench84.0%83.7%
SWE-bench86.0%76.4%
Vibe Code Bench v1.164.8%20.6%
Agents
DTBench88.0%89.9%
LMCA41.4%44.5%
Professional work
LegalBench82.4%84.6%
MedCode28.7%49.2%
MedScribe83.9%85.3%
MortgageTax64.9%68.7%
TaxEval v270.9%74.9%
Task length · METR45 sec

Tests at least two of these models have taken. Bold rows are the core tests.

This page as a chartDownload PNG