LFM2 24B A2B vs Schematron V2 Turbo vs Qwen3.5 4B
Qwen3.5 4B comes out ahead, 78 to 58 and 55 on our weighted score, and it is the cheaper option too.
Liquid AILFM2 24B A2B
58/100- ECI—
- Price$0.03 / $0.12
- Context33K
Inference.net
Schematron V2 Turbo
55/100- ECI—
- Price$0.03 / $0.15
- Context128K
- Our pick
Alibaba (Qwen)Qwen3.5 4B
78/100- ECI—
- Price$0.04 / $0.07
- Context262K
Qwen3.5 4B is our pick
Qwen3.5 4B is the better all-round choice, scoring 78/100 against LFM2 24B A2B (58) and Schematron V2 Turbo (55). It leads on inputs & features and context window. 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 priceQwen3.5 4BQwen3.5 4B $0.048 · LFM2 24B A2B $0.052 · Schematron V2 Turbo $0.06 per 1M tokens (3:1 blend)
- Longest contextQwen3.5 4BQwen3.5 4B 262,144 · Schematron V2 Turbo 128,000 · LFM2 24B A2B 32,768 tokens
- Widest inputsQwen3.5 4BLFM2 24B A2B: Text · Schematron V2 Turbo: Text · Qwen3.5 4B: Text, Images, Video
- Self-hostingLFM2 24B A2B and Qwen3.5 4BPublishes downloadable weights (LFM Open License v1.0 and Apache-2.0)
| Measure | Weight | LFM2 24B A2B | Schematron V2 Turbo | Qwen3.5 4B |
|---|---|---|---|---|
| Price | 50% | 100 | 100 | 100 |
| Inputs & features | 30% | 25 | 0 | 70 |
| Context window | 20% | 0 | 24 | 37 |
| Overall | 100% | 58/100 | 55/100 | 78/100 |
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 | LFM2 24B A2BLiquid AI | Schematron V2 TurboInference.net | Qwen3.5 4BAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| OTIS Mock AIME 2024–2025Competition mathematics | — | — | 55.8% |
| Price per million tokens | |||
| Input | $0.03 (best) | $0.03 (best) | $0.04 |
| Output | $0.12 | $0.15 | $0.07 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.052 | $0.06 | $0.048 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 1 providers | Median of 5 providers | Median of 3 providers |
| Limits | |||
| Context window | 32,768 tokens | 128,000 tokens | 262,144 tokens (best) |
| Max output | 32,768 tokens | 8,192 tokens | 81,920 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | Yes |
| Reasoning | No | No | Yes |
| Tool calling | Yes | No | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | OpenLFM Open License v1.0 | Proprietary | OpenApache-2.0 |
| API model ID | — | — | — |
| API providers | 1 | 5 (best) | 5 (best) |
| Released | Feb 24, 2026 | Apr 16, 2026 | Mar 2, 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.
- LFM2 24B A2B$0.54
- Schematron V2 Turbo$0.60
- Qwen3.5 4B$0.54
Which should you choose?
Which is better: LFM2 24B A2B, Schematron V2 Turbo or Qwen3.5 4B?
Qwen3.5 4B is the better all-round choice, scoring 78/100 against LFM2 24B A2B (58) and Schematron V2 Turbo (55). It leads on inputs & features and context window. 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, LFM2 24B A2B, Schematron V2 Turbo or Qwen3.5 4B?
Qwen3.5 4B is cheaper at $0.04 input / $0.07 output per million tokens (median across 3 API providers). LFM2 24B A2B costs $0.03 input / $0.12 output per million tokens (median across 1 API provider); Schematron V2 Turbo costs $0.03 input / $0.15 output per million tokens (median across 5 API providers). At a typical mix of three input tokens to one output token, that is $0.048 per million tokens for Qwen3.5 4B versus $0.052 for LFM2 24B A2B (1.1× as much) and $0.06 for Schematron V2 Turbo (1.3× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. LFM2 24B A2B has not been scored yet, Schematron V2 Turbo has not been scored yet and Qwen3.5 4B has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for LFM2 24B A2B, Schematron V2 Turbo and Qwen3.5 4B yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Schematron V2 Turbo does not support tool calling, which most coding agents need.
Which has the bigger context window?
Qwen3.5 4B has the largest context window at 262,144 tokens, against 128,000 for Schematron V2 Turbo and 32,768 for LFM2 24B A2B. Maximum output per response: LFM2 24B A2B up to 32,768, Schematron V2 Turbo up to 8,192, Qwen3.5 4B up to 81,920 tokens.
Which can read images, PDFs, audio or video?
LFM2 24B A2B accepts text; Schematron V2 Turbo accepts text; Qwen3.5 4B accepts text, images and video. Qwen3.5 4B handles the widest range of inputs.
Are any of these open source?
LFM2 24B A2B and Qwen3.5 4B publishes its weights (LFM Open License v1.0 and Apache-2.0) and can be self-hosted; Schematron V2 Turbo is proprietary.
Which is newer?
Schematron V2 Turbo is the newest, released Apr 16, 2026. Qwen3.5 4B came out Mar 2, 2026; LFM2 24B A2B came out Feb 24, 2026.
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 Nov 2, 2026.
