Explore global AI model ratings
Easily compare algorithm performance
List of Al models
Swipe left and right to view more
| MODEL NAME | PROVIDER | PARAMETERS |
SCORE |
RELEASE DATE |
COMPARE |
|---|---|---|---|---|---|
|
Gemini-3.1-Flash-Lite-Preview is Google’s lightweight preview model focused on practical capability under low cost, low latency, and high-throughput settings.
|
N/A | 4.9 | March 4, 2026 | ||
|
China Mobile’s latest closed-source model.
|
China Mobile | N/A | 3.9 | March 31, 2026 | |
|
MiniMax-M2.7 is MiniMax’s new-generation general-purpose large model. By building an Agent Harness system, it deeply participates in its own training and optimization process, can take on 30%–50% of the workload in some R&D scenarios, and achieves about a 30% improvement on internal evaluation benchmarks.
|
MiniMax | 230B | 5.3 | March 18, 2026 | |
|
gemma-4-31B-it is Google’s 31B-parameter open-source model for high-quality conversation, reasoning, and self-deployment by developers.
|
31B | 5.2 | April 3, 2026 | ||
|
The latest, highly anticipated and powerful next-generation LLM named GPT-5 that officially launched by OpenAI, version gpt-5.4.
|
OpenAI | N/A | 6.7 | March 5, 2026 | |
|
gemma-4-E4B-it is a lightweight open-source on-device model released by Google.
|
8B | 3.5 | April 3, 2026 | ||
|
Doubao-Seed-2-0-Pro-260215 is ByteDance’s latest high-performance proprietary general-purpose model.
|
ByteDance | N/A | 6.3 | February 15, 2026 | |
|
Step 3.5 Flash is StepFun’s newly released open-source model, performing well in agent scenarios and mathematical tasks, and capable of handling complex, long-chain tasks.
|
Step | 196B | 5.2 | February 2, 2026 | |
|
The latest, highly anticipated and powerful next-generation LLM named GPT-5 that officially launched by OpenAI, version gpt-5.4.
|
OpenAI | N/A | 5.4 | March 5, 2026 | |
|
Qwen3.6 is the next-generation open-source model in the Qwen family and an upgraded version of the Qwen3.5 series.
|
Alibaba | 27B | 5.2 | April 22, 2026 |
