Compare / head-to-head
GLM-5.2vsQwen3.8-Max
Qwen3.8-Max leads 7 of 7 shared benchmarks. GLM-5.2 is 1.1x cheaper per token. Both offer a 1M-token context window.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0 – 7
Qwen3.8-Max leads
Cheaper per token
GLM-5.2
1.1x cheaper, input + output
Larger context
Tie
both 1M tokens
Provider uptime (30d)
— · —
Z.ai · Qwen
GLM-5.2
Z.ai · released 2026-06-24
text
Qwen3.8-Max
Qwen · released 2026-08-02
textvision
Quality
Benchmark matrix
7 shared · 18 only GLM-5.2 · 1 only Qwen3.8-Max| Benchmark | GLM-5.2 | Qwen3.8-Max | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 7 | ||||
| GPQA Diamond | 91.9% ↗epoch | 92.6% ↗ | -0.7 pt | Qwen3.8-Max |
| FrontierMath Tier 4 v2 (Epoch AI run) | 29.3% ↗epoch | 46.3% ↗epoch | -17 pt | Qwen3.8-Max |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 59.2% ↗epoch | 74.7% ↗epoch | -15.5 pt | Qwen3.8-Max |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 86.4% ↗epoch | 99.4% ↗epoch | -13 pt | Qwen3.8-Max |
| SimpleQA Verified | 34.2% ↗epoch | 45.8% ↗epoch | -11.6 pt | Qwen3.8-Max |
| SWE-Bench Pro | 62.1% ↗ | 67.7% ↗ | -5.6 pt | Qwen3.8-Max |
| Terminal-Bench 2.1 | 81% ↗ | 86.6% ↗ | -5.6 pt | Qwen3.8-Max |
| Only GLM-5.2 reports · 18 | ||||
| AIME 2026 | 90% ↗matharena ⚠ | not reported | — | — |
| Agents' Last Exam (ALE-CLI) | 23.8% ↗ | not reported | — | — |
| AutomationBench v1.0.6 | 26.2% ↗ | not reported | — | — |
| CyberGym | 77.2% ↗ | not reported | — | — |
| DeepSWE v1.1 | 46.2% ↗ | not reported | — | — |
| ExploitBench | 24.4% ↗ | not reported | — | — |
| ExploitGym 2h | 29 ↗ | not reported | — | — |
| ExploitGym 6h | 39 ↗ | not reported | — | — |
| FrontierSWE | 67.5% ↗ | not reported | — | — |
| GDPval-AA v2 | 1508 ↗ | not reported | — | — |
| HLE (with tools) | 54.7% ↗ | not reported | — | — |
| NL2Repo | 48.9% ↗ | not reported | — | — |
| PostTrainBench | 31.7% ↗ | not reported | — | — |
| ProgramBench (Almost Solved) | 9.5% ↗ | not reported | — | — |
| SWE-bench Verified (Epoch AI run) | 78.7% ↗epoch | not reported | — | — |
| SWE-Marathon v1.1 | 19.4% ↗ | not reported | — | — |
| Terminal-Bench 3.0 | 4.6% ↗ | not reported | — | — |
| Toolathlon Verified | 59.9% ↗ | not reported | — | — |
| Only Qwen3.8-Max reports · 1 | ||||
| LMArena Elo | not reported | 1480.6 ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is GLM-5.2 minus Qwen3.8-Max in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | GLM-5.2 | Qwen3.8-Max | Edge |
|---|---|---|---|
| Context window | 1M tokens | 1M tokens | Tie |
| Max output | 131K tokens | 131K tokens | Tie |
| Input price / 1M | $1.4 ↗ | $1.65 ↗ | GLM-5.2 |
| Output price / 1M | $4.4 ↗ | $4.95 ↗ | GLM-5.2 |
| Cached input / 1M | $0.26 ↗ | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $5.8 | $6.6 | GLM-5.2 |
| Modalities | text | text · vision | Qwen3.8-Max |
| Released | 2026-06-24 | 2026-08-02 | — |
| Cited benchmark scores | 26 | 9 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
GLM-5.2 vs …
Models sharing the most benchmarksMore matchups
Qwen3.8-Max vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run GLM-5.2 and Qwen3.8-Max on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.