Head to head
Qwen3-Coder-480B-A35B vs GLM-4.6
Qwen3-Coder-480B-A35B from Alibaba Qwen against GLM-4.6 from Z.ai (Zhipu) — specification, price and every benchmark both makers have published, in one table.
Benchmarks
Evenly split
Across the 2 benchmarks both models report, they are level — Qwen3-Coder-480B-A35B takes 1 and GLM-4.6 takes 1. Which one is better depends entirely on which test resembles your work.
Price
Qwen3-Coder-480B-A35B is cheaper
On a 3:1 input-to-output mix, Qwen3-Coder-480B-A35B costs $0.525 per million tokens against $1.00 for GLM-4.6 — about 1.9× less. Remember that a reasoning model bills its thinking as output, so cost per answer can diverge much further than cost per token.
What actually differs
- Qwen3-Coder-480B-A35B takes 262K tokens of context against 205K — 1.3× more room for long documents or a large codebase.
- GLM-4.6 is a reasoning model and the other is not, which usually means better maths and multi-step logic in exchange for higher latency and more billed output tokens.
Scorecard
Which is better at what
Maths, coding, reasoning and the rest — one line each, averaged over the benchmarks both models actually report.
| Category | Qwen3-Coder-480B-A35B | GLM-4.6 | Better at this |
|---|---|---|---|
| ReasoningOnly one model reports this | — | — | Not comparable |
| MathsOnly one model reports this | — | — | Not comparable |
| CodingSWE-bench Verified, LiveCodeBench | 68.8% | 75.4% | GLM-4.6+6.6 |
| 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 | 0 | 1 | GLM-4.6 |
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
Qwen3-Coder-480B-A35B and GLM-4.6, row by row
| Attribute | Qwen3-Coder-480B-A35BAlibaba Qwen | GLM-4.6Z.ai (Zhipu) |
|---|---|---|
| Specification | ||
| MakerWho built it | Alibaba Qwen | Z.ai (Zhipu) |
| Released | 2025-07 | 2025-09 |
| ParametersTotal, and active per token for a mixture of experts | 480B total / 35B active | 357B total / 32B active |
| Architecture | MoE | MoE |
| Context windowHow much can go in at once | 262,144 tokens | 204,800 tokens |
| Max output | 65,536 tokens | 131,072 tokens |
| Input | Text | Text |
| ReasoningSpends extra tokens thinking before it answers | No | Yes |
| Tool calling | Yes | Yes |
| Licence | Apache 2.0 | MIT |
| Open weightsCan you download and run it yourself | Yes | Yes |
| Price | ||
| Input priceUSD per million tokens in | $0.30 | $0.60 |
| Output priceUSD per million tokens out | $1.20 | $2.20 |
| Blended 3:1A 3-in-to-1-out million-token mix — a fairer single number than input price alone | $0.525Cheapest | $1.00 |
| Price note | Open weights — this is a representative hosting rate, not a first-party price. Running it yourself costs only hardware. | 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. | ||
| LiveCodeBenchCompetitive-programming problems collected after each model's training cutoff, so contamination cannot inflate the score. | ||
| Links | Hugging Face · Full page | Hugging Face · Full page |
| Row verified | 2026-08 | 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
Qwen3-Coder-480B-A35B or GLM-4.6?
Is Qwen3-Coder-480B-A35B better than GLM-4.6?
Across the 2 benchmarks both models report, they are level — Qwen3-Coder-480B-A35B takes 1 and GLM-4.6 takes 1. Which one is better depends entirely on which test resembles your work.
Which is cheaper, Qwen3-Coder-480B-A35B or GLM-4.6?
On a 3:1 input-to-output mix, Qwen3-Coder-480B-A35B costs $0.525 per million tokens against $1.00 for GLM-4.6 — about 1.9× less. Remember that a reasoning model bills its thinking as output, so cost per answer can diverge much further than cost per token.
What is the difference between Qwen3-Coder-480B-A35B and GLM-4.6?
Qwen3-Coder-480B-A35B takes 262K tokens of context against 205K — 1.3× more room for long documents or a large codebase. GLM-4.6 is a reasoning model and the other is not, which usually means better maths and multi-step logic in exchange for higher latency and more billed output tokens.
