Gemini Robotics-ER 1.6 Preview vs Trinity Large Thinking vs GLM-5V-Turbo
Trinity Large Thinking comes out ahead, 55 to 50 and 49 on our weighted score, and it is the cheaper option too.
GoogleGemini Robotics-ER 1.6 Preview
50/100- ECI—
- Price$1.00 / $5.00
- Context131K
- Our pick
Arcee AITrinity Large Thinking
55/100- ECI—
- Price$0.25 / $0.80
- Context524K
Z.ai (Zhipu)GLM-5V-Turbo
49/100- ECI—
- Price$1.20 / $4.00
- Context200K
Trinity Large Thinking is our pick
Trinity Large Thinking is the better all-round choice, scoring 55/100 against Gemini Robotics-ER 1.6 Preview (50) and GLM-5V-Turbo (49). It leads on price and context window. Gemini Robotics-ER 1.6 Preview wins on inputs & features. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceTrinity Large ThinkingTrinity Large Thinking $0.388 · GLM-5V-Turbo $1.90 · Gemini Robotics-ER 1.6 Preview $2.00 per 1M tokens (3:1 blend)
- Longest contextTrinity Large ThinkingTrinity Large Thinking 524,288 · GLM-5V-Turbo 200,000 · Gemini Robotics-ER 1.6 Preview 131,072 tokens
- Widest inputsGemini Robotics-ER 1.6 Preview and GLM-5V-TurboGemini Robotics-ER 1.6 Preview: Text, Images, Audio, Video · Trinity Large Thinking: Text · GLM-5V-Turbo: Text, Images, PDFs, Video
- Self-hostingTrinity Large ThinkingPublishes downloadable weights (OpenMDW-1.1)
| Measure | Weight | Gemini Robotics-ER 1.6 Preview | Trinity Large Thinking | GLM-5V-Turbo |
|---|---|---|---|---|
| Price | 50% | 36 | 69 | 37 |
| Inputs & features | 30% | 90 | 35 | 80 |
| Context window | 20% | 24 | 49 | 32 |
| Overall | 100% | 50/100 | 55/100 | 49/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Gemini Robotics-ER 1.6 PreviewGoogle | Trinity Large ThinkingArcee AI | GLM-5V-TurboZ.ai (Zhipu) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $1.00 | $0.25 (best) | $1.20 |
| Output | $5.00 | $0.80 (best) | $4.00 |
| Cached input | — | $0.06 (best) | $0.24 |
| Blended (3:1) | $2.00 | $0.388 (best) | $1.90 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 1 providers | Official Arcee API | Official Z.AI API |
| Limits | |||
| Context window | 131,072 tokens | 524,288 tokens (best) | 200,000 tokens |
| Max output | 65,536 tokens | 262,144 tokens (best) | 131,072 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | Yes |
| PDFs | No | No | Yes |
| Audio | Yes | No | No |
| Video | Yes | No | Yes |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Proprietary | OpenOpenMDW-1.1 | Proprietary |
| API model ID | — | trinity-large-thinking | glm-5v-turbo |
| API providers | 1 | 6 | 14 (best) |
| Released | Apr 14, 2026 | Apr 1, 2026 | Apr 1, 2026 |
| Knowledge cutoff | Jan 2025 | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Gemini Robotics-ER 1.6 Preview$20.00
- Trinity Large Thinking$4.10
- GLM-5V-Turbo$20.00
Which should you choose?
Which is better: Gemini Robotics-ER 1.6 Preview, Trinity Large Thinking or GLM-5V-Turbo?
Trinity Large Thinking is the better all-round choice, scoring 55/100 against Gemini Robotics-ER 1.6 Preview (50) and GLM-5V-Turbo (49). It leads on price and context window. Gemini Robotics-ER 1.6 Preview wins on inputs & features. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Gemini Robotics-ER 1.6 Preview, Trinity Large Thinking or GLM-5V-Turbo?
Trinity Large Thinking is cheaper at $0.25 input / $0.80 output per million tokens (official Arcee API price). GLM-5V-Turbo costs $1.20 input / $4.00 output per million tokens (official Z.AI API price); Gemini Robotics-ER 1.6 Preview costs $1.00 input / $5.00 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.388 per million tokens for Trinity Large Thinking versus $1.90 for GLM-5V-Turbo (4.9× as much) and $2.00 for Gemini Robotics-ER 1.6 Preview (5.2× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Gemini Robotics-ER 1.6 Preview has not been scored yet, Trinity Large Thinking has not been scored yet and GLM-5V-Turbo has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Gemini Robotics-ER 1.6 Preview, Trinity Large Thinking and GLM-5V-Turbo yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
Trinity Large Thinking has the largest context window at 524,288 tokens, against 200,000 for GLM-5V-Turbo and 131,072 for Gemini Robotics-ER 1.6 Preview. Maximum output per response: Gemini Robotics-ER 1.6 Preview up to 65,536, Trinity Large Thinking up to 262,144, GLM-5V-Turbo up to 131,072 tokens.
Which can read images, PDFs, audio or video?
Gemini Robotics-ER 1.6 Preview accepts text, images, audio and video; Trinity Large Thinking accepts text; GLM-5V-Turbo accepts text, images, PDFs and video. Gemini Robotics-ER 1.6 Preview handles the widest range of inputs.
Are any of these open source?
Trinity Large Thinking publishes its weights (OpenMDW-1.1) and can be self-hosted; Gemini Robotics-ER 1.6 Preview and GLM-5V-Turbo is proprietary.
Which is newer?
Gemini Robotics-ER 1.6 Preview is the newest, released Apr 14, 2026. Trinity Large Thinking came out Apr 1, 2026; GLM-5V-Turbo came out Apr 1, 2026. Knowledge cutoff: Gemini Robotics-ER 1.6 Preview Jan 2025.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Oct 4, 2026.
Related comparisons
- Gemini Robotics-ER 1.6 Preview vs DeepSeek V4 ProDeepSeek
- Gemini Robotics-ER 1.6 Preview vs Seed 2.1 ProByteDance Seed
- Gemini Robotics-ER 1.6 Preview vs Grok 4.20 (Non-Reasoning)xAI
- Trinity Large Thinking vs Mercury Edit 2Inception
- Trinity Large Thinking vs Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIA
- Trinity Large Thinking vs Step 3.7 FlashStepFun
