GPQA DiamondVerified
89.5%
GPQA Diamond (AA run)
Models / Zhipu
GLM-5.2
GLM · Released 2026-06-13
Highest-ranked open-source model on FrontierSWE, PostTrainBench, and SWE-Marathon. $1.40 / $4.40 per 1M tokens, MIT weights pending.
Long-horizon coding and autonomous agent model for project-scale engineering. The GLM pick when you need 1M context that stays usable across multi-day refactors, not just a large window.
Composite63
Context1M
Input / 1M$1.4
Output / 1M$4.4
Knowledge cutoffopen
Output speed88 t/s
Statussolid
Family profile
Best published score in each covered benchmark family.
74/100 avg
- Reasoning
- 90
- Coding
- 51
- Agentic
- 78
- Long context
- 78
4 tested benchmark families
Editor's note
GLM-5.2 is the strongest open-source coding model we track. Terminal-Bench 2.1 at 81.0 lands within 4 points of Claude Opus 4.8 (85.0), and the FrontierSWE gap to Opus is 1%. We keep the tool at solid until independent benchmarks beyond Z.ai's own reports land in the ledger. MIT weights are announced but not yet shipped — verify before pinning self-hosted workflows.Benchmark placements
Per-benchmark positions
Where GLM-5.2 places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.
| Benchmark | Family | Rank | Score | Source | Date |
|---|---|---|---|---|---|
| DeepSWE | Coding | #7/ 8 | 44 | DeepSWE leaderboard v1.1 | 2026-06-20 |
| Terminal-Bench | Agentic | #30/ 167 | 78 | Artificial Analysis | 2026-09-28 |
| Humanity's Last Exam | Reasoning | #37/ 186 | 41 | Artificial Analysis | 2026-09-28 |
| SciCode | Coding | #42/ 97 | 51 | Artificial Analysis | 2026-09-28 |
| GPQA Diamond | Reasoning | #51/ 184 | 90 | Artificial Analysis | 2026-09-28 |
| AA-LCR | Long context | #59/ 184 | 78 | Artificial Analysis | 2026-09-28 |
| AA output speed | Performance | #70/ 195 | Artificial Analysis | 2026-10-12 |
Family context
Strongest rows in each family
The three highest-scoring models with pages in each capability family. Where GLM-5.2 shows up, it's highlighted.
ReasoningGLM-5.2 · 90
- 196
- 295
- 395
Math
- 152
- 252
- 350
CodingGLM-5.2 · 51
- 174
- 273
- 370
AgenticGLM-5.2 · 78
- 191
- 289
- 389
Long contextGLM-5.2 · 78
- 189
- 286
- 385
Newest receipts
6 recentLast 120 days
Benchmark rows added to the public ledger for GLM-5.2 in the last 120 days. Older rows live in the full table below.
| Benchmark | Family | Score | Source | Days ago |
|---|---|---|---|---|
| AA output speed | Performance | 88 t/s | Artificial Analysis | 10 |
| AA-LCR | Long context | 78.33% | Artificial Analysis | 24 |
| GPQA Diamond | Reasoning | 89.5% | Artificial Analysis | 24 |
| Humanity's Last Exam | Reasoning | 41.1% | Artificial Analysis | 24 |
| SciCode | Coding | 51.2% | Artificial Analysis | 24 |
| Terminal-Bench | Agentic | 77.9% | Artificial Analysis | 24 |
Family coverage
Best score per family
A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.
Price vs. performance
Where GLM-5.2 sits on the scatter
Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.
AnthropicOpenAIGoogleAlibabaMetaZhipuxAIDeepSeekMiniMaxXiaomiMoonshotOtherMeituanMistralNVIDIACohere
Full benchmark ledger
Every catalog benchmark for GLM-5.2. Scores link to the original source; gaps mean no public row exists yet.
7 of 13 catalog benchmarks have a sourced row for GLM-5.2.
Reasoning
Humanity's Last ExamVerified
41.1%
HLE (AA run)
Coding
Agentic
Terminal-BenchVerified
77.9%
Terminal-Bench v2.1 (AA run)
Long context
AA-LCRVerified
78.33%
AA-LCR (AA run)
Performance
AA output speedVerified
88 t/s
Median output tokens/s (1k prompt, default provider)
Changelog
Version history
- Released GLM-5.2 with 1M context, 128K max output, two thinking modes, and long-horizon coding focus. MIT open weights announced for the following week.
Sources
Where the numbers come from
- GLM-5.2 docs· checked 2026-06-19
- Z.ai pricing· checked 2026-06-19
- Artificial Analysis — GLM-5.2 leading open weights· checked 2026-06-19
- Requesty API pricing· checked 2026-06-19
Questions this model page answers
Every answer below is assembled from the dated fields on this page. Nothing is written separately for search.
What is GLM-5.2?
GLM-5.2 is a Zhipu model: Highest-ranked open-source model on FrontierSWE, PostTrainBench, and SWE-Marathon. $1.40 / $4.40 per 1M tokens, MIT weights pending.
What is GLM-5.2 for?
Long-horizon coding and autonomous agent model for project-scale engineering. The GLM pick when you need 1M context that stays usable across multi-day refactors, not just a large window.
What does GLM-5.2 cost?
GLM-5.2 lists $1.4 input and $4.4 output per 1M tokens. Pricing last checked 2026-06-19.
How large is the GLM-5.2 context window?
GLM-5.2 publishes a 1M token context window.
What is the VerdictPal status of GLM-5.2?
GLM-5.2 carries Solid status on the model atlas.
The Pack · Editorial newsletter
Know when the rules move.
One short email when a university changes its AI rule for theses, or a research tool changes its pricing or privacy terms. No tracking, no third-party analytics. Unsubscribe in one click.