GPT-6 Luna vs Step 3.5 Flash vs GLM-5.3-Flash
Too close to call on our weighted score (GLM-5.3-Flash 79, GPT-6 Luna 78, Step 3.5 Flash 62). The right pick depends on what you value most.
OpenAIGPT-6 Luna
78/100- ECI—
- Price$0.10 / $0.50
- Context1.05M
StepFunStep 3.5 Flash
62/100- ECI—
- Price$0.10 / $0.30
- Context256K
Z.ai (Zhipu)GLM-5.3-Flash
79/100- ECI151.9
- Price$0.15 / $0.50
- Context1M
Too close to call
It is close. Our weighted score puts them within 1 points (GLM-5.3-Flash 79/100, GPT-6 Luna 78/100, Step 3.5 Flash 62/100), so choose by what matters most for your work: Step 3.5 Flash on price and GPT-6 Luna for long inputs. 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 priceStep 3.5 FlashStep 3.5 Flash $0.15 · GPT-6 Luna $0.20 · GLM-5.3-Flash $0.237 per 1M tokens (3:1 blend)
- Longest contextGPT-6 LunaGPT-6 Luna 1,050,000 · GLM-5.3-Flash 1,000,000 · Step 3.5 Flash 256,000 tokens
- Widest inputsGLM-5.3-FlashGPT-6 Luna: Text, Images, PDFs · Step 3.5 Flash: Text · GLM-5.3-Flash: Text, Images, PDFs, Video
- Self-hostingStep 3.5 Flash and GLM-5.3-FlashPublishes downloadable weights
| Measure | Weight | GPT-6 Luna | Step 3.5 Flash | GLM-5.3-Flash |
|---|---|---|---|---|
| Price | 50% | 83 | 89 | 79 |
| Inputs & features | 30% | 80 | 35 | 90 |
| Context window | 20% | 61 | 36 | 60 |
| Overall | 100% | 78/100 | 62/100 | 79/100 |
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 | GPT-6 LunaOpenAI | Step 3.5 FlashStepFun | GLM-5.3-FlashZ.ai (Zhipu) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | 151.9 |
| ECI rank | — | — | #42 of 148 |
| GPQA DiamondGraduate-level science questions | 90.5% (best) | — | 90.2% |
| FrontierMath Tiers 1–3Research-level mathematics | 79.0% (best) | — | 55.8% |
| OTIS Mock AIME 2024–2025Competition mathematics | 98.9% (best) | — | 93.9% |
| SimpleQA VerifiedShort factual questions | 41.4% | — | — |
| Price per million tokens | |||
| Input | $0.10 (best) | $0.10 (best) | $0.15 |
| Output | $0.50 | $0.30 (best) | $0.50 |
| Cached input | $0.01 (best) | $0.02 | $0.03 |
| Blended (3:1) | $0.20 | $0.15 (best) | $0.237 |
| Long-context rate | Over 272K: $0.20 / $0.75 | Same rate | Same rate |
| Price source | Official OpenAI API | Official StepFun (Global) API | Official Z.AI API |
| Limits | |||
| Context window | 1,050,000 tokens (best) | 256,000 tokens | 1,000,000 tokens |
| Max output | 128,000 tokens | 256,000 tokens (best) | 131,072 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | Yes |
| PDFs | Yes | No | Yes |
| Audio | No | No | No |
| Video | No | No | Yes |
| Reasoning | Yeslow · medium · high · xhigh · max | Yeslow · high | Yeslow · high · max |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | Yes |
| Availability | |||
| Weights | Proprietary | Open | Open |
| API model ID | gpt-6-luna | step-3.5-flash | glm-5.3-flash |
| API providers | 24 | 8 | 65 (best) |
| Released | Sep 22, 2026 | Jan 29, 2026 | Aug 26, 2026 |
| Knowledge cutoff | May 18, 2026 | 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.
- GPT-6 Luna$2.00
- Step 3.5 Flash$1.60
- GLM-5.3-Flash$2.50
Which should you choose?
Which is better: GPT-6 Luna, Step 3.5 Flash or GLM-5.3-Flash?
It is close. Our weighted score puts them within 1 points (GLM-5.3-Flash 79/100, GPT-6 Luna 78/100, Step 3.5 Flash 62/100), so choose by what matters most for your work: Step 3.5 Flash on price and GPT-6 Luna for long inputs. 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, GPT-6 Luna, Step 3.5 Flash or GLM-5.3-Flash?
Step 3.5 Flash is cheaper at $0.10 input / $0.30 output per million tokens (official StepFun (Global) API price). GPT-6 Luna costs $0.10 input / $0.50 output per million tokens (official OpenAI API price); GLM-5.3-Flash costs $0.15 input / $0.50 output per million tokens (official Z.AI API price). At a typical mix of three input tokens to one output token, that is $0.15 per million tokens for Step 3.5 Flash versus $0.20 for GPT-6 Luna (1.3× as much) and $0.237 for GLM-5.3-Flash (1.6× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. GPT-6 Luna has not been scored yet, Step 3.5 Flash has not been scored yet and GLM-5.3-Flash has an ECI of 151.9.
Which is better for coding?
There are no published SWE-bench Verified results for GPT-6 Luna, Step 3.5 Flash and GLM-5.3-Flash 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?
GPT-6 Luna has the largest context window at 1,050,000 tokens, against 1,000,000 for GLM-5.3-Flash and 256,000 for Step 3.5 Flash. Maximum output per response: GPT-6 Luna up to 128,000, Step 3.5 Flash up to 256,000, GLM-5.3-Flash up to 131,072 tokens.
Which can read images, PDFs, audio or video?
GPT-6 Luna accepts text, images and PDFs; Step 3.5 Flash accepts text; GLM-5.3-Flash accepts text, images, PDFs and video. GLM-5.3-Flash handles the widest range of inputs.
Are any of these open source?
Step 3.5 Flash and GLM-5.3-Flash publishes its weights and can be self-hosted; GPT-6 Luna is proprietary.
Which is newer?
GPT-6 Luna is the newest, released Sep 22, 2026. GLM-5.3-Flash came out Aug 26, 2026; Step 3.5 Flash came out Jan 29, 2026. Knowledge cutoff: GPT-6 Luna May 18, 2026, Step 3.5 Flash 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.
