Compare / head-to-head
DeepSeek V4 ProvsGLM-5.2
DeepSeek V4 Pro leads 5 of 9 shared benchmarks. DeepSeek V4 Pro is 4.4x 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
5 – 4
DeepSeek V4 Pro leads
Cheaper per token
DeepSeek V4 Pro
4.4x cheaper, input + output
Larger context
Tie
both 1M tokens
Provider uptime (30d)
100% · —
DeepSeek · Z.ai
DeepSeek V4 Pro
DeepSeek · released 2026-08-13
text
Quality
Benchmark matrix
9 shared · 2 only DeepSeek V4 Pro · 16 only GLM-5.2| Benchmark | DeepSeek V4 Pro | GLM-5.2 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 9 | ||||
| GPQA Diamond | 90.9% ↗epoch | 91.9% ↗epoch | -1 pt | GLM-5.2 |
| AIME 2026 | 96.7% ↗matharena ⚠ | 90% ↗matharena ⚠ | +6.7 pt | DeepSeek V4 Pro |
| DeepSWE v1.1 | 62.7% ↗ | 46.2% ↗ | +16.5 pt | DeepSeek V4 Pro |
| FrontierMath Tier 4 v2 (Epoch AI run) | 2.4% ↗epoch | 29.3% ↗epoch | -26.9 pt | GLM-5.2 |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 45.3% ↗epoch | 59.2% ↗epoch | -13.9 pt | GLM-5.2 |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 96.7% ↗epoch | 86.4% ↗epoch | +10.3 pt | DeepSeek V4 Pro |
| SimpleQA Verified | 47% ↗epoch | 34.2% ↗epoch | +12.8 pt | DeepSeek V4 Pro |
| SWE-bench Verified (Epoch AI run) | 77.6% ↗epoch | 78.7% ↗epoch | -1.1 pt | GLM-5.2 |
| Terminal-Bench 2.1 | 87.9% ↗ | 81% ↗ | +6.9 pt | DeepSeek V4 Pro |
| Only DeepSeek V4 Pro reports · 2 | ||||
| LMArena Elo | 1450.6 ↗ | not reported | — | — |
| Humanity's Last Exam (with tools) | 60% ↗ | not reported | — | — |
| Only GLM-5.2 reports · 16 | ||||
| Agents' Last Exam (ALE-CLI) | not reported | 23.8% ↗ | — | — |
| AutomationBench v1.0.6 | not reported | 26.2% ↗ | — | — |
| CyberGym | not reported | 77.2% ↗ | — | — |
| ExploitBench | not reported | 24.4% ↗ | — | — |
| ExploitGym 2h | not reported | 29 ↗ | — | — |
| ExploitGym 6h | not reported | 39 ↗ | — | — |
| FrontierSWE | not reported | 67.5% ↗ | — | — |
| GDPval-AA v2 | not reported | 1508 ↗ | — | — |
| HLE (with tools) | not reported | 54.7% ↗ | — | — |
| NL2Repo | not reported | 48.9% ↗ | — | — |
| PostTrainBench | not reported | 31.7% ↗ | — | — |
| ProgramBench (Almost Solved) | not reported | 9.5% ↗ | — | — |
| SWE-Bench Pro | not reported | 62.1% ↗ | — | — |
| SWE-Marathon v1.1 | not reported | 19.4% ↗ | — | — |
| Terminal-Bench 3.0 | not reported | 4.6% ↗ | — | — |
| Toolathlon Verified | not reported | 59.9% ↗ | — | — |
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 DeepSeek V4 Pro minus GLM-5.2 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 | DeepSeek V4 Pro | GLM-5.2 | Edge |
|---|---|---|---|
| Context window | 1M tokens | 1M tokens | Tie |
| Max output | 384K tokens | 131K tokens | DeepSeek V4 Pro |
| Input price / 1M | $0.435 ↗ | $1.4 ↗ | DeepSeek V4 Pro |
| Output price / 1M | $0.87 ↗ | $4.4 ↗ | DeepSeek V4 Pro |
| Cached input / 1M | $0.004 ↗ | $0.26 ↗ | DeepSeek V4 Pro |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $1.31 | $5.8 | DeepSeek V4 Pro |
| Modalities | text | text | Tie |
| Released | 2026-08-13 | 2026-06-24 | — |
| Cited benchmark scores | 11 | 26 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
DeepSeek V4 Pro vs …
Models sharing the most benchmarksMore matchups
GLM-5.2 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run DeepSeek V4 Pro and GLM-5.2 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.