Zhipu AIGLM-5V-Turbo
Best configuration ranks #145 of 610 on the BenchLeader Index at 57.2 ±2.8. Last measured 8 Sept 2026. Released 1 Apr 2026.
- Blended price
- $9.25/M
- $5.00 in · $22.00 out
- Output speed
- 17 tok/s
- First answer
- 11 s
- Context
- 200k
- Overall index57
- Reasoning62
- Coding52
- Agents & tools62
- Knowledge55
- Instruction following61
- Human preference62
- Multimodal59
- Long context62
- Composite59
Benchmark results
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 | default | Source | Trend |
|---|---|---|---|
| LMArena Hard Prompts | 1453#91 | LMArena | |
| GPQA Diamond (AA)not in index | 80.9%#181 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 17.1%#179 | Artificial Analysis |
Coding
| Benchmark | default | Source | Trend |
|---|---|---|---|
| LMArena Coding | 1490#77 | LMArena | |
| LMArena WebDev | 1400#69 | LMArena |
Agents & tools
| Benchmark | default | Source | Trend |
|---|---|---|---|
| Terminal-Bench Hard | 32.6%#95 | Artificial Analysis | |
| τ²-Bench Telecom (AA)not in index | 98.5%#4 | Artificial Analysis |
Knowledge
| Benchmark | default | Source | Trend |
|---|---|---|---|
| AA-Omniscience | -19.3#180 | Artificial Analysis |
Instruction following
| Benchmark | default | Source | Trend |
|---|---|---|---|
| IFBench | 61.1%#120 | Artificial Analysis |
Human preference
| Benchmark | default | Source | Trend |
|---|---|---|---|
| LMArena Text | 1433#89 | LMArena |
Multimodal
| Benchmark | default | Source | Trend |
|---|---|---|---|
| LMArena Vision | 1263#39 | LMArena | |
| MMMU-Pro | 72.8%#100 | Artificial Analysis |
Long context
| Benchmark | default | Source | Trend |
|---|---|---|---|
| AA-LCR | 70.3%#157 | Artificial Analysis |
Composite
| Benchmark | default | Source | Trend |
|---|---|---|---|
| AA Intelligence Index | 23.5#130 | 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 |
|---|---|---|---|---|---|---|
| Z.ai | 17 tok/s | 11 s | $1.20 | $4.00 | 203k | fp8 |
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 $1.20 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0086 | $0.0075 | 28.9 s |
| Summarise a 30-page report | 12,000 / 600 | $0.073 | $0.039 | 46.5 s |
| Code edit | 6,000 / 1,500 | $0.063 | $0.046 | 1.7 min |
| Agentic coding session | 60,000 / 4,000 | $0.388 | $0.217 | 4.1 min |
| Structured extraction | 2,000 / 200 | $0.014 | $0.0087 | 23.0 s |
See also
Data as of 9 Sept 2026. Compare with another model.