GLM-4.5-Base
GLM-4.5-Base has too few ranked results yet to rate it on any capability.
Capability profile
Bars show the model's median result as a share of the leading model's, per capability.
No capability has enough ranked results to rate yet.
Price
No current price is tracked for this model. See the rate card
Evidence
50results on35benchmarks
- 50 cross-referenced
From 4 sources · latest Aug 24, 2026 · How verification works
GLM-4.5-Base benchmark results
50 results on 35 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
0 of 6 ranked benchmarks measured
- GPQA Diamond34.85Aug 24, 2026GPQA
0 of 10 ranked benchmarks measured
- 27.43Jun 5, 2026
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- Chinese SimpleQA (C-SimpleQA)70.10Jun 12, 2026C‑SimpleQA
- C-Eval86.90Jun 12, 2026C‑EVAL
- 76.27Jun 5, 2026
- 79.26Jun 5, 2026
- Chinese SimpleQA (C-SimpleQA)68.49Jun 5, 2026Chinese-simpleQA
- 86.46Jun 5, 2026
Show 42 more resultsHide 42 results
- 70.06Jun 5, 2026
- 96.32Jun 5, 2026
- 96.59Jun 5, 2026
- 86.20Jun 5, 2026
- 85.84Jun 5, 2026
- 89.33Jun 5, 2026
- CRUXEval-I (input prediction)68.51Jun 5, 2026CRUXEval-I
- CRUXEval-O (output prediction)67.75Jun 5, 2026CRUXEval-O
- 82.90Jun 5, 2026
- Global-MMLU-Lite85.81Jun 5, 2026MMLU Global Lite
- 33.50Jun 5, 2026
- 34.85Jun 5, 2026
- 90.06Jun 5, 2026
- 87.60Jun 5, 2026
- 85.37Jun 5, 2026
- 87.10Jun 5, 2026
- 90.17Jun 5, 2026
- 79.80Jun 5, 2026
- 78.16Jun 5, 2026
- 61.00Jun 5, 2026
- 62.60Jun 5, 2026
- 57.58Jun 5, 2026
- 81.60Jun 5, 2026
- 76.69Jun 5, 2026
- MBPP+ (EvalPlus-augmented)78.05Jun 5, 2026MBPP-plus
- 81.27Jun 5, 2026
- 87.73Jun 5, 2026
- 86.10Jun 5, 2026
- 86.50Jun 5, 2026
- 63.67Jun 5, 2026
- 65.78Jun 5, 2026
- 86.56Jun 5, 2026
- 49.60Jun 5, 2026
- 84.71Jun 5, 2026
- 85.09Jun 5, 2026
- 92.15Jun 5, 2026
- 16.12Jun 5, 2026
- 0.00Jun 5, 2026
- 29.26Jun 5, 2026
- 30.00Jun 5, 2026
- 49.64Jun 5, 2026
- 85.24Jun 5, 2026
GLM-4.5-Base: common questions
Who makes GLM-4.5-Base?
GLM-4.5-Base is made by Z.ai.
When was GLM-4.5-Base released?
GLM-4.5-Base's weights were first published on Hugging Face on Jul 20, 2025.
How many benchmarks has GLM-4.5-Base been tested on?
We track 50 results for GLM-4.5-Base on 35 benchmarks from 4 sources. The latest was recorded on Aug 24, 2026.
About this record
Where GLM-4.5-Base's numbers come from, and every name it appears under.
- Tracked since
- Jun 24, 2026
- Newest source mention
- Aug 24, 2026
Where the results come from
Verification: 50 scores · 0 independently verified · 50 vendor cross-reference. How these tiers are assigned
From 4 sources on 1 site. Hugging Face supplies all of them. Bars are coloured by trust tier.
- huggingface.co50