Compare models
Pick up to 4models. Specs render side-by-side. Share the URL — it's stateless.
Comparing agents instead? Switch to agent compare →
Alibaba | Alibaba | Alibaba | ||
|---|---|---|---|---|
| Vendor | Alibaba | Alibaba | Alibaba | |
| Family | Qwen | Qwen | Qwen | Gemini |
| Release date | 2026-04-22 | 2025-04-29 | 2026-05-20 | 2025-03-25 |
| Context window | 262,144 tokens | 128,000 tokens | 1,000,000 tokens | 2,000,000 tokens |
| Parameters | 27B (dense) | 235B | — | — |
| Modality | text, vision, video | text | text | text, vision, audio, video |
| License | Apache-2.0 | Apache-2.0 | proprietary | proprietary |
| Source | open weights | open weights | proprietary | proprietary |
| Description | Alibaba's first dense open-weight in the 3.6 family. Strong agentic-coding scores (77.2 SWE-bench Verified, matching Claude 4.5 Opus on Terminal-Bench 2.0). Supports 201 languages and multimodal text/image/video input. | Predecessor to the Qwen3.6 family. | Alibaba's flagship agent model — 1M-token context, extended-thinking mode, 56.6 on the Artificial Analysis Intelligence Index v4.0 (5th overall, #1 Chinese). 50.8% on Terminal-Bench Hard. Designed for long-horizon agent workloads (hundreds-to-thousands of steps). Closed-weight, $2.50/$7.50 per 1M tokens. | Predecessor to Gemini 3 Pro. |
| Links | ||||
| Benchmarks | ||||
| MMLU-Pro | 78.9% | — | 83.7% | 84.1% |
| GPQA-D | — | — | 83.0% | 84.0% |
| HumanEval | 91.5% | — | 93.9% | — |
| Aider | 70.2% | — | 78.4% | — |
| AIME-25 | — | — | 90.4% | — |
| LiveCB | — | — | 71.0% | — |
| MMMU | 70.3% | — | — | 72.4% |
Add a model
Max 4 models. Remove one to add another.