Models / GLM-4.5-Air (FP8)
GLM-4.5-Air (FP8)
Early evidence, 2 results from 1 source, on 1 use case. GLM-4.5-Air (FP8) is strongest at sticking to the facts; it is not on sale through OpenRouter, so it is here for reference.
Superseded. GLM-4.5-Air is Z.ai's newer model in this line, at $0.32 blended: see GLM-4.5-Air.
Results 16 Nov 2026 · 2 results · 1 source
- Price per million tokens
- Not available through OpenRouter
- Speed
- Not measured
- Intelligence Index
- Not measured
- Spring Prompt overall
- Not ranked yet
needs our benchmarks and two groups of results - Developer
- Z.ai, based in China
Weights not published - Released
- Not recorded
no launch date in our tracker or our sources
How good is it, and for what?
Each use case ranks the available models its benchmarks measured. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.
Product listingsTurning a sparse product feed and photos into listings that can go live
- CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is
- DeckBench: has not measured this model.
User surveysPlanning a user survey and reading its results without being misled
- SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending
- ROASBench: has not measured this model.
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls
- tau2-bench: has not measured this model.
- Berkeley Function Calling Leaderboard (BFCL) V4: has not measured this model.
- OpenHands Index: has not measured this model.
- Microsoft STATE-Bench: has not measured this model.
- Artificial Analysis: has not measured this model.
- Vending-Bench 2: has not measured this model.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects
- APEX-Agents: has not measured this model.
- GDP.pdf: has not measured this model.
- Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge
- Artificial Analysis: has not measured this model.
WritingWhat people prefer in blind comparisons, and judged writing quality
- Arena (formerly LMArena): has not measured this model.
- UGI Leaderboard: has not measured this model.
Sticking to the factsSummarising without inventing things, and factual answers
| Benchmark | GLM-4.5-Air (FP8) | Rank among available | Best available |
|---|---|---|---|
| Vectara Hallucination LeaderboardVectara: hallucination rate · reported | 9.3% | 34th of 72 | GPT-5.4 nano 3.1% |
- Arena (formerly LMArena): has not measured this model.
- SimpleQA Verified (Epoch AI): has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess)
- BulletBench: has not measured this model.
Nearest alternatives
- Z.ai's newer model in this lineGLM-4.5-Air$0.32 blended · Intelligence Index 11.1
- The most capable open-weights modelMiMo-V2.6-Pro$0.54 blended · Intelligence Index 46.3
Against GLM-4.5-Air (FP8). "Similar intelligence" means within 4 points or better.
Against the alternatives
The models you would most likely weigh it against: the leaders of the groups above.
Scroll sideways to see every alternative.
| GLM-4.5-Air (FP8) | Claude Fable 5.2 leads overall | GLM-5.3 Z.ai's best other model | Claude Opus 5.5 near the top overall | GPT-6.1 Sol near the top overall | |
|---|---|---|---|---|---|
| Price per million tokens | – | $16.00 | $2.15 | $8.00 | $4.00 |
| Tokens a second | – | – | 87 | 96 | 53 |
| Intelligence Index | – | – | 44.8 | 57.6 | 51.8 |
| Spring Prompt overall | – | 90 | 35 | 82 | 80 |
| Rank among available models, by use case | |||||
| Product listings | – | 5th | – | 13th | 2nd |
| Decks from an analysis | – | 4th | – | 7th | 5th |
| User surveys | – | 1st | – | 4th | 3rd |
| Marketing planning | – | 1st | 29th | 9th | – |
| Agents and tool use | – | – | 15th | 3rd | 6th |
| Professional work | – | – | 15th | 3rd | 9th |
| Reasoning and knowledge | – | – | 31st | 1st | 6th |
| Writing | – | – | 24th | 5th | 16th |
| Sticking to the facts | 64th of 140 | – | 51st | 3rd | 20th |
| Speed under pressure | – | 8th | 33rd | – | 3rd |
Shaded figures are better than GLM-4.5-Air (FP8)'s. A dash means no result.
Where it has been measured
Compared with the models available today (it is not on sale itself), mid-field on sticking to the facts, the one use case measured.
Not timed: Artificial Analysis, our source for speed, has not tested it
- Vectara Hallucination Leaderboard2 results
- BulletBenchNot measured
- CatalogBenchNot measured
- DeckBenchNot measured
- ROASBenchNot measured
- SurveyBenchNot measured
- APEX-AgentsNot measured
- Arena (formerly LMArena)Not measured
- Artificial AnalysisNot measured
- Berkeley Function Calling Leaderboard (BFCL) V4Not measured
- GDP.pdfNot measured
- Microsoft STATE-BenchNot measured
- OpenHands IndexNot measured
- Remote Labor IndexNot measured
- SimpleQA Verified (Epoch AI)Not measured
- tau2-benchNot measured
- UGI LeaderboardNot measured
- Vending-Bench 2Not measured
Every result
2 published results from 1 source, each in the source's own units, with the configuration that produced it.
Vectara Hallucination Leaderboard · reported by Vectara Hallucination Leaderboard · 2 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| Vectara: answer rate% of documents, higher is better | 98.1% | 81 of 108 | GLM-4.5-Air (FP8) | 22 Sep 2026 |
| Vectara: hallucination rate% of summaries, lower is better | 9.3% | 47 of 108 | GLM-4.5-Air (FP8) | 22 Sep 2026 |
Not shown: Not a quality score: a low rate usually means content filters were triggered, and hallucination rates are measured on answered documents only.
Test your own prompt.
Benchmarks aren't your task. Run your prompt on the models you could use, with every answer checked and costed.