The Model Index
Up to four models

Qwen3.8-27B vs GLM-5.2

On the index (GPT-4 = 100), Qwen3.8-27B scores 155 and GLM-5.2 154. 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
GLM-5.2
154138–169
WeightsOpen
ReleasedJun 2026
Price in / out$0.0070 / $6.8
Context1.05M
Core tests taken6 of 9

Qwen3.8-27B and GLM-5.2 are too close to call (2 points apart, within the uncertainty), ahead on 2 of 3 shared core tests, and costs 2.9× less.

Test by testthird-party results

Qwen3.8-27BGLM-5.2
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 ProSimpleBenchSimpleBenchMATHSLiveBench MathematicsLiveBench MathematicsSurface Evolver BenchSurface Evolver BenchCODINGLiveBench Agentic CodingLiveBench Agentic CodingLiveBench CodingLiveBench CodingCode MigrationCode MigrationLiveCodeBenchLiveCodeBenchProgramBenchProgramBenchSWE-benchSWE-benchVibe Code Bench v1.1Vibe Code Bench v1.1AGENTSAPEX-AgentsAPEX-AgentsSkillsBenchSkillsBenchDTBenchDTBenchLMCALMCAPROFESSIONAL WORKFinance Agent (v2)Finance Agent (v2)EMBEMBLegalBenchLegalBenchLegal Research BenchLegal Research BenchMedCodeMedCodeMedScribeMedScribeTaxEval v2TaxEval v2NOVEL PROBLEMSARC-AGI-2ARC-AGI-2ARC-AGI-1ARC-AGI-1
Every result as a table
TestQwen3.8-27BGLM-5.2
Reasoning & knowledge
LiveBench Data Analysis76.6%73.7%
LiveBench IF72.7%62.3%
LiveBench Language74.4%76.2%
LiveBench Reasoning80.0%78.6%
GPQA Diamond (Vals AI)88.9%85.6%
MMLU Pro84.3%86.7%
SimpleBench60.2%58.8%
Maths
LiveBench Mathematics86.2%89.8%
Surface Evolver Bench45.0%55.6%
Coding
LiveBench Agentic Coding61.4%51.8%
LiveBench Coding75.7%79.7%
Code Migration14.2%37.9%
LiveCodeBench84.0%69.5%
ProgramBench0.0%0.5%
SWE-bench86.0%82.8%
Vibe Code Bench v1.164.8%64.0%
Agents
APEX-Agents47.5%45.2%
SkillsBench38.1%45.1%
DTBench88.0%93.6%
LMCA41.4%45.8%
Professional work
Finance Agent (v2)48.5%49.7%
EMB59.7%61.5%
LegalBench82.4%84.1%
Legal Research Bench36.1%31.3%
MedCode28.7%40.8%
MedScribe83.9%83.5%
TaxEval v270.9%73.3%
Novel problems
ARC-AGI-242.4%22.8%
ARC-AGI-187.5%77.0%

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

This page as a chartDownload PNG