Qwen3.5 Flash vs Reka Edge vs Schematron V2 Small
No independent capability benchmark covers every model here yet. The score uses inputs & features and context window.
Price in rating: Excluded · Include price
Alibaba (Qwen)
Qwen3.5 Flash
74/100- ECI143.9
- Price$0.10 / $0.40
- Context1M
Reka AI
Reka Edge
36/100- ECI—
- Price$0.102 / $0.102
- Context16K
Inference.net
Schematron V2 Small
13/100- ECI—
- Price$0.05 / $0.23
- Context128K
Capability evidence is incomplete
There is not enough shared capability evidence to name an overall winner. The scores (Qwen3.5 Flash 74/100, Reka Edge 36/100, Schematron V2 Small 13/100) 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 priceSchematron V2 SmallSchematron V2 Small $0.095 · Reka Edge $0.102 · Qwen3.5 Flash $0.175 per 1M tokens (3:1 blend)
- Longest contextQwen3.5 FlashQwen3.5 Flash 1,000,000 · Schematron V2 Small 128,000 · Reka Edge 16,384 tokens
- Widest inputsQwen3.5 Flash and Reka EdgeQwen3.5 Flash: Text, Images, Video · Reka Edge: Text, Images, Video · Schematron V2 Small: Text
- Self-hostingReka EdgePublishes downloadable weights
| Measure | Weight | Qwen3.5 Flash | Reka Edge | Schematron V2 Small |
|---|---|---|---|---|
| Inputs & features | 60% | 80 | 60 | 0 |
| Context window | 40% | 64 | 0 | 32 |
| Specs only | 100% | 74/100 | 36/100 | 13/100 |
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 | Schematron V2 SmallInference.net | ||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 143.9 | — | — |
| ECI rank | #97 of 158 | — | — |
| GPQA DiamondGraduate-level science questions | 82.3% | — | — |
| FrontierMath Tiers 1–3Research-level mathematics | 18.3% | — | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 84.4% | — | — |
| SimpleQA VerifiedShort factual questions | 20.3% | — | — |
| Price per million tokens | |||
| Input | $0.10 | $0.102 | $0.05 (best) |
| Output | $0.40 | $0.102 (best) | $0.23 |
| Cached input | $0.01 | — | — |
| Blended (3:1) | $0.175 | $0.102 | $0.095 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Alibaba API | Median of 4 providers | Median of 5 providers |
| Limits | |||
| Context window | 1,000,000 tokens (best) | 16,384 tokens | 128,000 tokens |
| Max output | 65,536 tokens (best) | 14,745 tokens | 4,096 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | Yes | Yes | No |
| Reasoning | Yes | No | No |
| Tool calling | Yes | Yes | No |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Proprietary | Open | Proprietary |
| API model ID | qwen3.5-flash | — | — |
| API providers | 10 (best) | 4 | 5 |
| Released | Feb 23, 2026 | Mar 11, 2026 | Apr 16, 2026 |
| Knowledge cutoff | — | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
Qwen3.5 Flash$1.80
Reka Edge$1.23
- Schematron V2 Small$0.96
Which should you choose?
Which is better: Qwen3.5 Flash, Reka Edge or Schematron V2 Small?
There is not enough shared capability evidence to name an overall winner. The scores (Qwen3.5 Flash 74/100, Reka Edge 36/100, Schematron V2 Small 13/100) 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, Qwen3.5 Flash, Reka Edge or Schematron V2 Small?
Schematron V2 Small is cheaper at $0.05 input / $0.23 output per million tokens (median across 5 API providers). Reka Edge costs $0.102 input / $0.102 output per million tokens (median across 4 API providers); Qwen3.5 Flash costs $0.10 input / $0.40 output per million tokens (official Alibaba API price). At a typical mix of three input tokens to one output token, that is $0.095 per million tokens for Schematron V2 Small versus $0.102 for Reka Edge (1.1× as much) and $0.175 for Qwen3.5 Flash (1.8× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Qwen3.5 Flash has an ECI of 143.9, Reka Edge has not been scored yet and Schematron V2 Small has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Qwen3.5 Flash, Reka Edge and Schematron V2 Small yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Schematron V2 Small does not support tool calling, which most coding agents need.
Which has the bigger context window?
Qwen3.5 Flash has the largest context window at 1,000,000 tokens, against 128,000 for Schematron V2 Small and 16,384 for Reka Edge. Maximum output per response: Qwen3.5 Flash up to 65,536, Reka Edge up to 14,745, Schematron V2 Small up to 4,096 tokens.
Which can read images, PDFs, audio or video?
Qwen3.5 Flash accepts text, images and video; Reka Edge accepts text, images and video; Schematron V2 Small accepts text. Qwen3.5 Flash handles the widest range of inputs.
Are any of these open source?
Reka Edge publishes its weights and can be self-hosted; Qwen3.5 Flash and Schematron V2 Small is proprietary.
Which is newer?
Schematron V2 Small is the newest, released Apr 16, 2026. Reka Edge came out Mar 11, 2026; Qwen3.5 Flash came out Feb 23, 2026.
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.