Model comparison
Gemma 4 vs Qwen3.5-Plus
- Input
- $0.12 / 1M tokens
- Output
- $0.35 / 1M tokens
- Context
- 256K
- Released
- 2026-04-02
- Input
- $0.40
- Output
- $2.40
- Context
- 1M
- Released
- 2026-02-16
Qwen3.5-Plus scores higher on 4 of the 4 benchmarks both models report; Gemma 4 is cheaper on input tokens ($0.1 vs $0.4 per 1M, 3.3×); Qwen3.5-Plus has the larger context window (1M vs 256K); Gemma 4 ships open weights while Qwen3.5-Plus is API-only.
Specs and pricing side by side
| Spec | Gemma 4 | Qwen3.5-Plus |
|---|---|---|
| Maker | Alibaba (Qwen) | |
| Released | 2026-04-02 | 2026-02-16 |
| Context window | 256K | 1M |
| Max output | not published | 65,536 tokens |
| Input price | $0.12 / 1M tokens | $0.40 |
| Output price | $0.35 / 1M tokens | $2.40 |
| Parameters | 30.7B (31B dense flagship); family spans E2B/E4B on-device and 26B MoE (3.8B active) | Undisclosed (serves the Qwen3.5 397B-A17B family — 397B total / 17B active) |
| License | Apache 2.0 | Proprietary |
| Weights | Open weights | API only |
| Modalities | Text, Vision, Audio, Video | Text, Vision, Video |
| Knowledge cutoff | January 2025 | not published |
Benchmarks both models report
| Benchmark | Gemma 4 | Qwen3.5-Plus |
|---|---|---|
| AIME 2026 | 89.2% | 91.3% |
| GPQA Diamond | 84.3% | 88.4% |
| MMLU Pro | 85.2% | 87.8% |
| LiveCodeBench v6 | 80% | 83.6% |
Scores are as published by each maker or its cited source; harness, reasoning effort and date can differ between rows, so treat small gaps as ties. Sources are listed on each model page.
Which one should you pick?
Pick Gemma 4 if…
- Cost matters: input tokens cost 3.3× less ($0.1 vs $0.4 per 1M).
- You want to self-host or fine-tune (open weights, Apache 2.0).
- You need Audio input, which Qwen3.5-Plus lacks.
- Your use case is: self-hosted and on-premise LLM deployments where data must stay private.
Pick Qwen3.5-Plus if…
- You care about AIME 2026, GPQA Diamond, MMLU Pro (it scores higher on 4 shared benchmarks).
- You need the longer context (1M vs 256K).
- Your use case is: high-volume document and PDF understanding across very long contexts.
FAQ
Which is better, Gemma 4 or Qwen3.5-Plus?
Qwen3.5-Plus scores higher on 4 of the 4 benchmarks both models report; Gemma 4 is cheaper on input tokens ($0.1 vs $0.4 per 1M, 3.3×); Qwen3.5-Plus has the larger context window (1M vs 256K); Gemma 4 ships open weights while Qwen3.5-Plus is API-only. The better pick depends on whether you value benchmark scores, price per token, context length or openness for your workload.
How much cheaper is Gemma 4?
Gemma 4: $0.12 / 1M tokens input, $0.35 / 1M tokens output. Qwen3.5-Plus: $0.40 input, $2.40 output (list API prices as published by each maker).
What are the context windows of Gemma 4 and Qwen3.5-Plus?
Gemma 4 offers 256K; Qwen3.5-Plus offers 1M with up to 65,536 tokens output.
Is Gemma 4 newer than Qwen3.5-Plus?
Gemma 4 was released 2026-04-02; Qwen3.5-Plus was released 2026-02-16.