DeepSeek V4 Flash 0731 vs GLM-5.3-Flash vs Step 3.5 Flash
No independent capability benchmark covers every model here yet. The score uses inputs & features and context window.
Price in rating: Excluded · Include price
DeepSeek
DeepSeek V4 Flash 0731
47/100- ECI154.4
- Price$0.14 / $0.30
- Context1M
Z.ai (Zhipu)
GLM-5.3-Flash
80/100- ECI153.8
- Price$0.15 / $0.50
- Context1M
StepFun
Step 3.5 Flash
44/100- ECI—
- Price$0.10 / $0.30
- Context256K
Capability evidence is incomplete
There is not enough shared capability evidence to name an overall winner. The scores (GLM-5.3-Flash 80/100, DeepSeek V4 Flash 0731 47/100, Step 3.5 Flash 44/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. 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 · DeepSeek V4 Flash 0731 $0.18 · GLM-5.3-Flash $0.237 per 1M tokens (3:1 blend)
- Longest contextDeepSeek V4 Flash 0731 and GLM-5.3-FlashDeepSeek V4 Flash 0731 1,000,000 · GLM-5.3-Flash 1,000,000 · Step 3.5 Flash 256,000 tokens
- Widest inputsGLM-5.3-FlashDeepSeek V4 Flash 0731: Text · GLM-5.3-Flash: Text, Images, PDFs, Video · Step 3.5 Flash: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | DeepSeek V4 Flash 0731 | GLM-5.3-Flash | Step 3.5 Flash |
|---|---|---|---|---|
| Inputs & features | 60% | 35 | 90 | 45 |
| Context window | 40% | 64 | 64 | 43 |
| Specs only | 100% | 47/100 | 80/100 | 44/100 |
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 | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 154.4 (best) | 153.8 | — |
| ECI rank | #52 of 158 (best) | #53 of 158 | — |
| GPQA DiamondGraduate-level science questions | 91.0% (best) | 90.2% | — |
| FrontierMath Tiers 1–3Research-level mathematics | 57.5% (best) | 55.8% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 94.4% (best) | 93.9% | — |
| SimpleQA VerifiedShort factual questions | 33.6% | — | — |
| Price per million tokens | |||
| Input | $0.14 | $0.15 | $0.10 (best) |
| Output | $0.30 (best) | $0.50 | $0.30 (best) |
| Cached input | — | $0.03 | $0.02 (best) |
| Blended (3:1) | $0.18 | $0.237 | $0.15 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 65 providers | Official Z.AI API | Official StepFun (Global) API |
| Limits | |||
| Context window | 1,000,000 tokens (best) | 1,000,000 tokens (best) | 256,000 tokens |
| Max output | 384,000 tokens (best) | 131,072 tokens | 256,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | Yes | No |
| Audio | No | No | No |
| Video | No | Yes | No |
| Reasoning | Yes | Yeslow · high · max | Yeslow · high |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | Yes |
| Availability | |||
| Weights | OpenMIT | Open | Open |
| API model ID | — | glm-5.3-flash | step-3.5-flash |
| API providers | 66 | 124 (best) | 11 |
| Released | Jul 31, 2026 | Aug 26, 2026 | Jan 29, 2026 |
| Knowledge cutoff | May 2025 | — | 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.
DeepSeek V4 Flash 0731$2.00
GLM-5.3-Flash$2.50
Step 3.5 Flash$1.60
Which should you choose?
Which is better: DeepSeek V4 Flash 0731, GLM-5.3-Flash or Step 3.5 Flash?
There is not enough shared capability evidence to name an overall winner. The scores (GLM-5.3-Flash 80/100, DeepSeek V4 Flash 0731 47/100, Step 3.5 Flash 44/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, DeepSeek V4 Flash 0731, GLM-5.3-Flash or Step 3.5 Flash?
Step 3.5 Flash is cheaper at $0.10 input / $0.30 output per million tokens (official StepFun (Global) API price). DeepSeek V4 Flash 0731 costs $0.14 input / $0.30 output per million tokens (median across 65 API providers); 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 $0.18 for DeepSeek V4 Flash 0731 (1.2× 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. DeepSeek V4 Flash 0731 has an ECI of 154.4, GLM-5.3-Flash has an ECI of 153.8 and Step 3.5 Flash has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for DeepSeek V4 Flash 0731, GLM-5.3-Flash and Step 3.5 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?
DeepSeek V4 Flash 0731 and GLM-5.3-Flash have the largest context windows (1,000,000 and 1,000,000 tokens), against 256,000 for Step 3.5 Flash. Maximum output per response: DeepSeek V4 Flash 0731 up to 384,000, GLM-5.3-Flash up to 131,072, Step 3.5 Flash up to 256,000 tokens.
Which can read images, PDFs, audio or video?
DeepSeek V4 Flash 0731 accepts text; GLM-5.3-Flash accepts text, images, PDFs and video; Step 3.5 Flash accepts text. GLM-5.3-Flash handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (MIT), so you can self-host them.
Which is newer?
GLM-5.3-Flash is the newest, released Aug 26, 2026. DeepSeek V4 Flash 0731 came out Jul 31, 2026; Step 3.5 Flash came out Jan 29, 2026. Knowledge cutoff: DeepSeek V4 Flash 0731 May 2025, Step 3.5 Flash Jan 2025.
How do you decide the winner?
This rating uses inputs & features (60%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (40%, 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 Nov 18, 2026.