GLM-4.6 (Reasoning)
By Z AI · released 2025-09-30 (9 months) · snapshot 2026-07-17
- Intelligence index
- 28.70
- Cost to run the AA index
- $313
- Price per 1M tokens (in / out)
- $0.55 / $2.20
- End-to-end time
- 65.4s
Is GLM-4.6 (Reasoning) on the Pareto frontier, and what beats it?
Off the frontier
No. GPT-5.6 Luna (high) is at least as smart for the same money or less.
Next step up: GPT-5.6 Sol (low), smarter but dearer.
| # | Model | Creator | Intelligence | Total cost | E2E total | Open | Released | Frontier |
|---|---|---|---|---|---|---|---|---|
| 1 | GLM-4.6 (Reasoning) | Z AI | 28.70 | $313 | 65.4s | 2025-09-30 | ||
| 2 | GPT-5.6 Luna (high) | OpenAI | 46.10 | $275 | 9.51s | 2026-07-09 | Frontier | |
| 3 | GPT-5.6 Sol (low) | OpenAI | 49.40 | $353 | 13.4s | 2026-07-09 | Frontier |
Open in the picker Daily check URL: 200 on the frontier, 409 once beaten
GLM-4.6 (Reasoning) today
1 of 2 effort levels plotted. The remaining levels lack intelligence or benchmark cost data.
Intelligence: Artificial Analysis Intelligence Index. Cost: total cost to run that benchmark, so reasoning tokens count. API id: glm-4-6-reasoning.
Compare head to head
Suggested: what beats it, its effort levels, and frontier models near its price.
- GLM-4.6 (Reasoning) vs GPT-5.6 Luna (high)
- GLM-4.6 (Reasoning) vs GPT-5.6 Sol (low)
- GLM-4.6 (Reasoning) vs GLM-4.6 (Non-reasoning)
- GLM-4.6 (Reasoning) vs DeepSeek V4 Pro (Reasoning, Max Effort)
- GLM-4.6 (Reasoning) vs MiniMax-M3
- GLM-4.6 (Reasoning) vs GPT-5.6 Terra (medium)
- GLM-4.6 (Reasoning) vs Muse Spark 1.1 (xhigh)
- GLM-4.6 (Reasoning) vs GPT-5.6 Sol (medium)
- GLM-4.6 (Reasoning) vs Grok 4.5 (high)
What the GLM-4.6 release did to the frontier on 2025-09-30
1 of 2 effort levels reached the frontier at launch (GLM-4.6 (Reasoning)). Impact 1.78, #13 of 34 releases this past year.
Should you use GLM-4.6 (Reasoning)?
Should you use GLM-4.6 (Reasoning)?
Only when it fits your setup: GPT-5.6 Luna (high) is at least as smart for the same money or less, so GLM-4.6 (Reasoning) is off the value frontier today.
What is better and cheaper than GLM-4.6 (Reasoning)?
GPT-5.6 Luna (high) — at least as smart for the same money or less.
How much does GLM-4.6 (Reasoning) cost?
$0.55/$2.20 in/out per 1M tokens, and $313 to run the full Artificial Analysis Intelligence Index, the honest all-in number for reasoning models.
Is GLM-4.6 (Reasoning) on the Pareto frontier?
No: GPT-5.6 Luna (high) beats it on intelligence, cost, or both.
Frontier membership by axis pair
Other axis pairs where GLM-4.6 (Reasoning) is Pareto-optimal.
| Y axis | X axis | On the frontier |
|---|---|---|
| AA intelligence index | AA total cost to run (USD) | |
| AA intelligence index | End-to-end total seconds | |
| AA intelligence index | Output speed tokens/sec |
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/models/glm-4-6-reasoning · Markdown: /api/v1/models/glm-4-6-reasoning?format=md · llms.txt · agent skill