Xentir Media Source-backed AI & tech
LIVE INTELLIGENCE · part of the Xentir AI Index

GLM-4.6 vs GPT-5 nano

GLM-4.6 OPEN WEIGHTS · Z.ai (Zhipu AI),Tsinghua University, released 2025-09-30
GPT-5 nano · OpenAI, released 2025-08-07

“Epoch AI, 'AI Benchmarking Hub'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks' [online resource].” · epoch.ai/benchmarks · Licensed CC BY 4.0 · data last verified 2026-09-09 · Methodology · Data Sources

GLM-4.6 leads on more of the 3 benchmarks where both are measured — GLM-4.6 on 2, GPT-5 nano on 1. The remaining 6 of 9 tracked benchmarks cannot be compared: 5 have a result for only one of the two models, 1 for neither. Nothing on this page is estimated to fill those in.

Head-to-head

Measured on 3 of 9 tracked benchmarks for both models — GLM-4.6 leads on 2, GPT-5 nano leads on 1.

BenchmarkGLM-4.6 GPT-5 nanoLeads
Epoch Capabilities Index (ECI)140.8139.4GLM-4.6
SWE-bench VerifiedNot measuredNot measuredNot measured on both
GPQA DiamondNot measured0.694 (high)Comparison unavailable — GLM-4.6 has no published result
MATH Level 5Not measured0.952 (medium)Comparison unavailable — GLM-4.6 has no published result
OTIS Mock AIME 2024-2025Not measured0.811 (high)Comparison unavailable — GLM-4.6 has no published result
FrontierMath0.038 (zai-org)0.083 (high)GPT-5 nano
FrontierMath Tier 40.021 (zai-org)0.021 (medium)GLM-4.6
SimpleQA VerifiedNot measured0.117 (high)Comparison unavailable — GLM-4.6 has no published result
Chess PuzzlesNot measured0.270 (high)Comparison unavailable — GLM-4.6 has no published result
Benchmark results measure specific tasks and should not be treated as a universal measure of model quality. A model with no row here for a benchmark has not been measured on it — that is left blank, never estimated.

What remains uncertain

A missing result means Xentir has not found one published by the source it cites, not that the model performs badly. See Data Sources.

Reference price

Per 1M tokensGLM-4.6 GPT-5 nano
Output $0.40

List price as published by the vendor. Xentir does not verify negotiated or enterprise rates, and price is not a measure of capability — see Data Sources.

Full profiles

GLM-4.6 → · GPT-5 nano → · the full AI Model Rankings table