Text Synthesis on C3EBENCH
4.6Cloze ScoreQwen3-235B-A22B
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Qwen3-235B-A22BModel Category=Open Source LLMs2026.02 | 4.6 | 7.49 | 7.67 | 7.38 | |
| GPT-5.2-2025-11-20Model Category=Proprietary LLMs2026.02 | 4.53 | 7.89 | 7.5 | 7.37 | |
| Gemini-3 ProModel Category=Proprietary LLMs2026.02 | 4.44 | 7.79 | 7.18 | 7.51 | |
| Claude-4.5 SonnetModel Category=Proprietary LLMs2026.02 | 4.44 | 7.79 | 7.42 | 7.52 | |
| Grok-4Model Category=Proprietary LLMs2026.02 | 4.42 | 7.76 | 7.12 | 7.39 | |
| Qwen3-MaxModel Category=Proprietary LLMs2026.02 | 4.32 | 7.86 | 7.71 | 7.35 | |
| DeepSeek-v3.2Model Category=Proprietary LLMs2026.02 | 4.22 | 7.33 | 7.21 | 7.45 | |
| Kimi-K2-ThinkingModel Category=Proprietary LLMs2026.02 | 3.99 | 7.75 | 7.05 | 7.71 | |
| Qwen3-32BModel Category=Open Source LLMs2026.02 | 3.74 | 6.56 | 7.05 | 6.07 | |
| Qwen3-8BModel Category=Open Source LLMs2026.02 | 3.14 | 6.14 | 6.99 | 5.65 | |
| Llama-3.1-405BModel Category=Open Source LLMs2026.02 | 3.09 | 3.64 | 5.94 | 3.51 | |
| GLM-4.7Model Category=Proprietary LLMs2026.02 | 2.62 | 7.25 | 5.43 | 7.17 | |
| Llama-3.1-8BModel Category=Open Source LLMs2026.02 | 2.44 | 5.89 | 5.85 | 5.33 | |
| Hermes-3-Llama-70BModel Category=Open Source LLMs2026.02 | 1.88 | 5.55 | 4.19 | 5.28 |