Head to head
GLM-5 vs GLM-4.6
GLM-5 from Z.ai (Zhipu) against GLM-4.6 from Z.ai (Zhipu) — specification, price and every benchmark both makers have published, in one table.
At a glance
Benchmarks
GLM-5 leads
GLM-5 wins 1 of the 1 benchmarks both models report, GLM-4.6 wins 0, by a wide margin. The average gap across shared tests is 9.8 points.
Price
Not directly comparable
At least one of these does not have a published per-token price, so cost cannot be compared like for like. The open-weight model can be run on your own hardware instead.
What actually differs
- GLM-4.6 takes 205K tokens of context against 200K — 1.0× more room for long documents or a large codebase.
Scorecard
Which is better at what
Maths, coding, reasoning and the rest — one line each, averaged over the benchmarks both models actually report.
| Category | GLM-5 | GLM-4.6 | Better at this |
|---|---|---|---|
| ReasoningOnly one model reports this | — | — | Not comparable |
| MathsOnly one model reports this | — | — | Not comparable |
| CodingSWE-bench Verified | 77.8% | 68.0% | GLM-5+9.8 |
| KnowledgeNeither model reports this | — | — | Not comparable |
| MultimodalNeither model reports this | — | — | Not comparable |
| Instruction followingNeither model reports this | — | — | Not comparable |
| Human preferenceNeither model reports this | — | — | Not comparable |
| Categories wonOut of 1 comparable | 1 | 0 | GLM-5 |
Each category averages only the benchmarks every model here reports, so no one is credited for a test the other did not run. A category with no shared test is marked Not comparable rather than guessed at.
Side by side
GLM-5 and GLM-4.6, row by row
| Attribute | GLM-5Z.ai (Zhipu) | GLM-4.6Z.ai (Zhipu) |
|---|---|---|
| Specification | ||
| MakerWho built it | Z.ai (Zhipu) | Z.ai (Zhipu) |
| Released | 2026-02 | 2025-09 |
| ParametersTotal, and active per token for a mixture of experts | 744B total / 40B active | 357B total / 32B active |
| Architecture | MoE | MoE |
| Context windowHow much can go in at once | 200,000 tokens | 204,800 tokens |
| Max output | 128,000 tokens | 131,072 tokens |
| Input | Text | Text |
| ReasoningSpends extra tokens thinking before it answers | Not reported | Yes |
| Tool calling | Yes | Yes |
| Licence | Not stated | MIT |
| Open weightsCan you download and run it yourself | Yes | Yes |
| Price | ||
| Input priceUSD per million tokens in | Not reported | $0.60 |
| Output priceUSD per million tokens out | Not reported | $2.20 |
| Blended 3:1A 3-in-to-1-out million-token mix — a fairer single number than input price alone | Not reported | $1.00 |
| Price note | First-party API rate. | Open weights — this is a representative hosting rate, not a first-party price. Running it yourself costs only hardware. |
| Published benchmarks | ||
| GPQA Diamond198 graduate-level physics, chemistry and biology questions written to be Google-proof. PhD holders in the matching field score about 65%. | Not reported | |
| AIME 2025The American Invitational Mathematics Examination — 15 problems, integer answers, no partial credit. A standard test of multi-step maths reasoning. | Not reported | |
| SWE-bench Verified500 human-validated GitHub issues from real Python repositories. The model must produce a patch that makes the project's own tests pass. | ||
| Terminal-Bench 2.0The 2.0 task set of the terminal agent benchmark — the version most launches reported from late 2025 to spring 2026. Not comparable with 2.1 or 4.0. | Not reported | |
| LiveCodeBenchCompetitive-programming problems collected after each model's training cutoff, so contamination cannot inflate the score. | Not reported | |
| Links | Full page | Hugging Face · Full page |
| Row verified | 2026-10 | 2026-08 |
Where these numbers come from
Every score on this page is a published figure, taken from the model's own card, system card, technical report or release post, or from a public leaderboard. CorX Labs did not run these evaluations. Most are self-reported by the lab that built the model, which means they were produced under that lab's own choice of prompt, scaffold and number of attempts — so treat them as a starting point for a shortlist, not as a settled ranking.
A score someone other than the model's maker measured is marked Independent and names its measurer. Those are the stronger numbers on this page — an outside harness has no reason to flatter anyone — and there are not many of them.
Where a figure has not been published, the cell reads Not reported rather than an estimate. Nothing here is inferred, interpolated or guessed. Each model records the month its row was last checked. Full method and caveats.
Questions
GLM-5 or GLM-4.6?
Is GLM-5 better than GLM-4.6?
GLM-5 wins 1 of the 1 benchmarks both models report, GLM-4.6 wins 0, by a wide margin. The average gap across shared tests is 9.8 points.
Which is cheaper, GLM-5 or GLM-4.6?
At least one of these does not have a published per-token price, so cost cannot be compared like for like. The open-weight model can be run on your own hardware instead.
What is the difference between GLM-5 and GLM-4.6?
GLM-4.6 takes 205K tokens of context against 200K — 1.0× more room for long documents or a large codebase.
