Gemma 4 31B IT vs LFM2 24B A2B vs Qwen3.5 4B
No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.
Price in rating: Included · Exclude price
Google
Gemma 4 31B IT
69/100- ECI144.1
- Price$0.142 / $0.40
- Context262K
Liquid AI
LFM2 24B A2B
60/100- ECI—
- Price$0.03 / $0.12
- Context33K
Alibaba (Qwen)
Qwen3.5 4B
80/100- ECI—
- Price$0.04 / $0.07
- Context262K
Capability evidence is incomplete
There is not enough shared capability evidence to name an overall winner. The scores (Qwen3.5 4B 80/100, Gemma 4 31B IT 69/100, LFM2 24B A2B 60/100) compare the available specifications and price. 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 · Gemma 4 31B IT $0.206 per 1M tokens (3:1 blend)
- Longest contextGemma 4 31B IT and Qwen3.5 4BGemma 4 31B IT 262,144 · Qwen3.5 4B 262,144 · LFM2 24B A2B 32,768 tokens
- Widest inputsQwen3.5 4BGemma 4 31B IT: Text, Images · LFM2 24B A2B: Text · Qwen3.5 4B: Text, Images, Video
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Gemma 4 31B IT | LFM2 24B A2B | Qwen3.5 4B |
|---|---|---|---|---|
| Price | 50% | 79 | 100 | 100 |
| Inputs & features | 30% | 70 | 25 | 70 |
| Context window | 20% | 43 | 11 | 43 |
| Specs & price only | 100% | 69/100 | 60/100 | 80/100 |
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) | 144.1 | — | — |
| ECI rank | #94 of 158 | — | — |
| GPQA DiamondGraduate-level science questions | 75.8% | — | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 73.3% (best) | — | 55.8% |
| SimpleQA VerifiedShort factual questions | 10.4% | — | — |
| Price per million tokens | |||
| Input | $0.142 | $0.03 (best) | $0.04 |
| Output | $0.40 | $0.12 | $0.07 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.206 | $0.052 | $0.048 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 42 providers | Median of 1 providers | Median of 3 providers |
| Limits | |||
| Context window | 262,144 tokens (best) | 32,768 tokens | 262,144 tokens (best) |
| Max output | 32,768 tokens | 32,768 tokens | 81,920 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | Yes |
| Reasoning | Yes | No | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Open | OpenLFM Open License v1.0 | OpenApache-2.0 |
| API model ID | gemma-4-31b-it | — | — |
| API providers | 52 (best) | 1 | 5 |
| Released | Apr 2, 2026 | Feb 24, 2026 | Mar 2, 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.
Gemma 4 31B IT$2.22
LFM2 24B A2B$0.54
Qwen3.5 4B$0.54
Which should you choose?
Which is better: Gemma 4 31B IT, LFM2 24B A2B or Qwen3.5 4B?
There is not enough shared capability evidence to name an overall winner. The scores (Qwen3.5 4B 80/100, Gemma 4 31B IT 69/100, LFM2 24B A2B 60/100) compare the available specifications and price. 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, Gemma 4 31B IT, LFM2 24B A2B 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); Gemma 4 31B IT costs $0.142 input / $0.40 output per million tokens (median across 42 API providers; free on Google). 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 $0.206 for Gemma 4 31B IT (4.3× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Gemma 4 31B IT has an ECI of 144.1, LFM2 24B A2B 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 Gemma 4 31B IT, LFM2 24B A2B and Qwen3.5 4B 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?
Gemma 4 31B IT and Qwen3.5 4B have the largest context windows (262,144 and 262,144 tokens), against 32,768 for LFM2 24B A2B. Maximum output per response: Gemma 4 31B IT up to 32,768, LFM2 24B A2B up to 32,768, Qwen3.5 4B up to 81,920 tokens.
Which can read images, PDFs, audio or video?
Gemma 4 31B IT accepts text and images; LFM2 24B A2B 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?
Yes, all three publish their weights (LFM Open License v1.0 and Apache-2.0), so you can self-host them.
Which is newer?
Gemma 4 31B IT is the newest, released Apr 2, 2026. Qwen3.5 4B came out Mar 2, 2026; LFM2 24B A2B came out Feb 24, 2026. Knowledge cutoff: Gemma 4 31B IT Jan 2025.
How do you decide the winner?
This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, 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.