Zhipu AIGLM 4.5V
GLM 4.5V is a Zhipu AI open-weights reasoning model, released 11 Aug 2025. Its best configuration ranks #356 of 785 on the BenchLeader Index at 50.9 ±2.3, in the upper half. The ± is the point: 293 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in reasoning (54) and lowest in multimodal (46). At $0.900 per million tokens blended it is mid-priced. Output speed of 45 tokens per second puts it in the slowest quarter, with a first token in 2.1 s. It has been measured at 3 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 22 Oct 2026.
- Blended price
- $0.900/M
- $0.600 in · $1.80 out
- Output speed
- 45 tok/s
- OpenRouter traffic, 7-day median; not yet measured by Artificial Analysis
- First answer
- 2.11 s
- Context
- 64k
- Full answer
- –
- Cost per run
- –
- Released
- 11 Aug 2025
- Overall index51
- Reasoning54
- Coding52
- Maths53
- Human preference52
- Multimodal46
Reasoning-effort configurations
The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Not stated” collects results from publishers that did not say which setting they used; for a reasoning model that is usually its thinking mode, but we do not assume it. Pick a setting here or at the top of the page to see its price, speed and category scores.
| Effort | Index | Rank | Speed | First answer | Chat reply cost | Categories |
|---|---|---|---|---|---|---|
| no reasoning | 38.5 | #711 | 63 tok/s | 3.40 s | $0.0008 | Agents & tools 40 · Composite 37 · Instruction following 33 · Knowledge 36 · Long context 23 · Multimodal 25 · Reasoning 41 |
| thinking | 40.2 | #661 | 59 tok/s | 37 s | $0.0008 | Agents & tools 38 · Composite 38 · Instruction following 38 · Knowledge 41 · Long context 23 · Multimodal 33 · Reasoning 41 |
| not statedbest | 50.9 | #356 | 45 tok/s | 2.11 s | $0.0008 | Coding 52 · Human preference 52 · Maths 53 · Multimodal 46 · Reasoning 54 |
How its index has moved
9 Sept 2026 to 21 Oct 2026- not stated
- thinking
- no reasoning
The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | no reasoning | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|
| Arena Hard Promptseffort not stated | – | – | 1373#194 | Arena (LMArena) | |
| GPQA Diamond (AA)not in index | 57.3%#393 | 68.4%#313 | – | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 3.5%#595 | 6.3%#398 | – | Artificial Analysis | |
| Kagi LLM Benchmarkeffort not stated | – | – | 59.8%#51 | Kagi LLM Benchmark | |
| CritPt | 0.0%#315 | 0.0%#315 | – | Artificial Analysis |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Coding | 1403#192 | Arena (LMArena) |
Agents & tools
| Benchmark | no reasoning | thinking | Source | Trend |
|---|---|---|---|---|
| Terminal-Bench Hard | 6.8%#249 | 5.3%#277 | Artificial Analysis | |
| τ²-Bench Telecom (AA)not in index | 19.6%#337 | 22.5%#311 | Artificial Analysis |
Maths
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Maths | 1361#194 | Arena (LMArena) |
Knowledge
| Benchmark | no reasoning | thinking | Source | Trend |
|---|---|---|---|---|
| AA-Omniscience | -55.6#437 | -46.3#357 | Artificial Analysis | |
| AA-Omniscience: accuracynot in index | 18.2%#341 | 20.8%#291 | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | 9.8%#427 | 15.2%#338 | Artificial Analysis |
Instruction following
| Benchmark | no reasoning | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|
| IFBench | 28.6%#371 | 34.2%#321 | – | Artificial Analysis | |
| Arena Instruction Followingnot in indexeffort not stated | – | – | 1338#201 | Arena (LMArena) |
Human preference
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Text | 1352#199 | Arena (LMArena) | |
| Arena Creative Writingnot in index | 1309#205 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1356#191 | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1341#214 | Arena (LMArena) |
Multimodal
| Benchmark | no reasoning | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|
| Arena Visioneffort not stated | – | – | 1154#115 | Arena (LMArena) | |
| MMMU-Pro | 42.8%#260 | 50.5%#240 | – | Artificial Analysis |
Long context
| Benchmark | no reasoning | thinking | Source | Trend |
|---|---|---|---|---|
| AA-LCR | 0.0%#493 | 0.0%#493 | Artificial Analysis |
Composite
| Benchmark | no reasoning | thinking | Source | Trend |
|---|---|---|---|---|
| AA Intelligence Index v4.3.2 | 6.7#510 | 7.6#466 | Artificial Analysis |
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| NovitaAI | 53 tok/s | 1.72 s | $0.600 | $1.80 | 66k | fp8 |
| Z.ai | 37 tok/s | 2.21 s | $0.600 | $1.80 | 66k | fp8 |
Price history
The price above, per 1M tokens, every day it changed.
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.110 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0008 | $0.0006 | 8.8 s |
| Summarize a 30-page report | 12,000 / 600 | $0.0083 | $0.0039 | 15.4 s |
| Code edit | 6,000 / 1,500 | $0.0063 | $0.0041 | 35.4 s |
| Agentic coding session | 60,000 / 4,000 | $0.043 | $0.021 | 1.5 min |
| Structured extraction | 2,000 / 200 | $0.0016 | $0.0008 | 6.6 s |
More from Zhipu AI
See also
Questions people ask
- What are GLM 4.5V's benchmark scores?
- As of 24 Oct 2026, GLM 4.5V scores 50.9 ±2.3 on the BenchLeader Index, strongest in reasoning (54) and weakest in multimodal (46). That rests on 6 independent benchmark results, and every score on this page links to its publisher.
- How does GLM 4.5V rank?
- GLM 4.5V is #356 of 785 ranked configurations on 24 Oct 2026. 293 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- How much does GLM 4.5V cost per 1M tokens?
- As of 24 Oct 2026, GLM 4.5V costs $0.600 per 1M input tokens and $1.80 per 1M output tokens, $0.900 blended (three input tokens per output token). The list price last changed on 24 Oct 2026.
- When was GLM 4.5V released?
- Zhipu AI released GLM 4.5V on 11 Aug 2025. BenchLeader has results for it at 3 reasoning-effort settings.
Data as of 24 Oct 2026. Compare these configurations.
Cite as: BenchLeader, “GLM 4.5V: benchmarks, pricing, speed and rank”, data as of 24 Oct 2026, https://www.benchleader.com/models/glm-4-5v.