Qwen3.8 27B vs GLM-5.2: Release Comparison
Comparison of the Qwen3.8 27B and GLM-5.2 releases: 4 and 2 models respectively, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across all 6 models.
- For intelligence, Qwen3.8 27B and GLM-5.2 tie at 34 (Qwen3.8 27B (xhigh) and GLM-5.2 (max)).
- For output speed, GLM-5.2 is fastest: GLM-5.2 (Non-reasoning) at 149 t/s, against Qwen3.8 27B (Non-reasoning) at 51 t/s for Qwen3.8 27B.
- For cost per task, Qwen3.8 27B is cheapest: Qwen3.8 27B (xhigh) at $0.82, against GLM-5.2 (max) at $0.96 for GLM-5.2.
Releases compared
Intelligence
Artificial Analysis Intelligence Index
Intelligence Index vs. Cost per Intelligence Index Task
Cost
Cost per Intelligence Index Task
Speed & Latency
Output Speed
Capability Scores
Capability Indices
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, Humanity's Last Exam, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, Humanity's Last Exam, AA-LCR v1.1, GDP.pdf, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, MLCR-AA, Humanity's Last Exam, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, Humanity's Last Exam, CritPt, GDPval-AA v2, AA-Briefcase, Terminal-Bench 4.0 · Higher is better
Incorporates 5 evaluations: AA-Omniscience, Humanity's Last Exam, GDPval-AA v2, AA-Briefcase, AA-LCR v1.1 · Higher is better
Further details
Input modality | Output modality | Weights | Provider Benchmarks | ||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GLM-5.2 (max) |  Z AI | 34 | 34 | 31 | 35 | 33 | 37 | 46 | $0.96 | $0.9 | $1.40 | $4.40 | $0.26 | $1,559 | 64k | 51k | 178M | 72 | 8.15s | 35.80s | 42.71s | 839.88s | 753B 40B active at inference time | 1M | Jun 2026 | - | Yes | Supports: text | Supports: text |    +16 | |||
| Qwen3.8 27B (xhigh) |  Alibaba | 34 | 35 | 37 | 35 | 35 | 34 | 43 | $0.82 | $0.4 | $0.50 | $3.00 | $0.05 | $1,170 | 67k | 48k | 198M | 44 | 3.99s | 49.25s | 60.57s | 1137.46s | 27B | 256k | Aug 2026 | - | Yes | Supports: text, image, and video | Supports: text |   +2 | |||
| Qwen3.8 27B (medium) | Alibaba | 28 | 29 | 35 | 28 | - | 25 | 31 | $0.90 | $0.4 | $0.50 | $3.00 | $0.05 | $977 | 52k | 32k | 113M | 50 | 3.84s | 43.92s | 53.95s | 984.69s | 27B | 256k | Aug 2026 | - | Yes | Supports: text, image, and video | Supports: text |  | |||
| Qwen3.8 27B (low) | Alibaba | 26 | 27 | 30 | 28 | - | 24 | 32 | $0.83 | $0.4 | $0.50 | $3.00 | $0.05 | $876 | 45k | 26k | 82M | 51 | 4.17s | 43.71s | 53.60s | 871.73s | 27B | 256k | Aug 2026 | - | Yes | Supports: text, image, and video | Supports: text | | |||
| GLM-5.2 (Non-reasoning) | Z AI | 22 | - | - | - | - | - | - | - | $0.9 | $1.40 | $4.40 | $0.26 | - | - | - | - | 149 | 1.76s | 1.76s | 5.13s | - | 753B 40B active at inference time | 1M | Jun 2026 | - | No | Supports: text | Supports: text |   +4 | |||
| Qwen3.8 27B (Non-reasoning) | Alibaba | 22 | - | - | - | - | - | - | - | $0.4 | $0.50 | $3.00 | $0.05 | - | - | - | - | 51 | 3.96s | 3.96s | 13.82s | - | 27B | 256k | Aug 2026 | - | No | Supports: text, image, and video | Supports: text | | |||