| Gemini 3.1 Pro: A smarter model for your most complex tasks | | 92.6 | Gemini 3.1 Pro | 2026-02-19 |
| Introducing GPT-5.2 | | 89.6 | GPT-5.2 | 2025-12-11 |
| Claude Opus 4.1 | | 89.5 | Claude Opus 4.1 | 2025-08-05 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 88.5 | Qwen3.5-397B-A17B | 2026-02-16 |
| Gemma 4 Technical Report | ✓ Link | 88.4 | Gemma 4 31B | 2026-07-02 |
| Introducing Claude 4 | | 87.4 | Claude Opus 4 | 2025-05-22 |
| Qwen3 Technical Report | ✓ Link | 86.70 | Qwen3-235B-A22B (Base) | 2025-05-14 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 86.7 | Qwen3.5-122B-A10B | 2026-02-16 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 85.9 | Qwen3.5-27B | 2026-02-16 |
| Introducing Claude 4 | | 85.4 | Claude Sonnet 4 | 2025-05-22 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 85.2 | Qwen3.5-35B-A3B | 2026-02-16 |
| On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability | ✓ Link | 84.86 | Qwen3.8-Flash-Next-Base | 2026-08-31 |
| Qwen3 Technical Report | ✓ Link | 84.3 | Qwen3-235B-A22B (Thinking) | 2025-05-14 |
| Gemma 4 Technical Report | ✓ Link | 83.4 | Gemma 4 12B Unified | 2026-07-02 |
| Claude 3.7 Sonnet and Claude Code | | 83.2 | Claude 3.7 Sonnet | 2025-02-24 |
| DiffusionGemma Technical Report | ✓ Link | 81.5 | DiffusionGemma 26B A4B | 2026-07-31 |
| gpt-oss-120b & gpt-oss-20b Model Card | | 81.3 | gpt-oss-120b | 2025-08-08 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 81.2 | Qwen3.5-9B | 2026-02-16 |
| Qwen3 Technical Report | ✓ Link | 79.8 | Qwen3-235B-A22B (Non-thinking) | 2025-05-14 |
| ERNIE 5.0 Technical Report | | 78.94 | ERNIE 5.0-Base | 2026-02-04 |
| ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools | ✓ Link | 56.6 | GLM-4-9B-Chat | 2024-06-18 |
| LFM2 Technical Report | ✓ Link | 55.26 | LFM2-8B-A1B (0-shot) | 2025-11-28 |
| Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs | ✓ Link | 49.3 | Phi-4-Mini (5-shot) | 2025-02-24 |