Models · Compare
Gemini 3.1 Pro vs Qwen3.5 Plus
Rows highlighted in warm gray are where the models differ. Numbers carry their as-of date and primary source.
Specs
| Field | A: Gemini 3.1 Pro | B: Qwen3.5 Plus |
|---|---|---|
| Released | 2026-02-19 | 2026-02-16 |
| Developer | Google DeepMind | Alibaba |
| Openness | Proprietary | Open |
| License | Proprietary | Apache-2.0 |
| OSI-approved | no | yes |
| Data released | no | no |
| Training code | no | no |
| Architecture | unknown | moe |
| Total params | — | 397B |
| Active params | — | 17B |
| Experts | — | — |
| Context window | 1.0M | 1.0M |
| Attention | unknown | unknown |
| Position enc. | unknown | rope-yarn |
| Pretraining tokens | — | — |
| Post-training | rlhf | sft, rlhf |
| Training hardware | — | — |
| $/M input | — | — |
| $/M output | — | — |
| Output tok/sec | — | — |
Benchmarks
Missing scores render as not reported; never inferred. Bold highlights the leader per benchmark.
General reasoning
Code
Context · A
Preview release of the Gemini 3.1 line, three months after Gemini 3 Pro. DeepMind highlighted complex reasoning and code generation that can ship animated SVGs and synthesize entire dashboards from a prompt. Broader rollout to Pro and Ultra subscribers followed May 4 2026.
Context · B
Flagship of the Qwen 3.5 generation. 397B MoE activating 17B per token with 512 experts. First Qwen open-weights model with native vision input. Per Alibaba's evals, the 397B-A17B outperforms the trillion-parameter Qwen3 Max on several reasoning and coding benchmarks while running roughly 19x faster at 256K context.