| OpenAI | GPT-6 Astra | 96.0% | Source for GPT-6 Astra on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 10005 |
| Microsoft AI | MAI-Thinking-1 | 84.2% | Source for MAI-Thinking-1 on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 70003 |
| Alibaba (Tongyi) | Qwen3.8-Max | 92.6% | Source for Qwen3.8-Max on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 130008 |
| Google (DeepMind) | Gemma 4 26B A4B Instruct (thinking mode) | 82.3% | Source for Gemma 4 26B A4B Instruct (thinking mode) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 35001 |
| Google (DeepMind) | Gemma 4 31B Instruct (thinking mode) | 84.3% | Source for Gemma 4 31B Instruct (thinking mode) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 35002 |
| Google (DeepMind) | Gemma 4 E2B Instruct (thinking mode) | 43.4% | Source for Gemma 4 E2B Instruct (thinking mode) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 35003 |
| Google (DeepMind) | Gemma 4 E4B Instruct (thinking mode) | 58.6% | Source for Gemma 4 E4B Instruct (thinking mode) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 35004 |
| Google (DeepMind) | Gemma 4 12B Instruct (thinking mode) | 78.8% | Source for Gemma 4 12B Instruct (thinking mode) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 35005 |
| Moonshot AI | Kimi K3 (max) | 93.5% | Source for Kimi K3 (max) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 120003 |
| Thinking Machines Lab | Inkling (effort=0.99) | 87.2% | Source for Inkling (effort=0.99) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 160001 |
| OpenAI | GPT-5.6 Luna | 92.3% | Source for GPT-5.6 Luna on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 10009 |
| OpenAI | GPT-5.6 Sol | 94.6% | Source for GPT-5.6 Sol on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 10010 |
| OpenAI | GPT-5.6 Terra | 92.9% | Source for GPT-5.6 Terra on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 10011 |
| Z.ai | GLM-5.2 | 91.2% | Source for GLM-5.2 on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 150004 |
| NVIDIA | NVIDIA Nemotron 3 Ultra 550B-A55B (no-tools) | 87.0% | Source for NVIDIA Nemotron 3 Ultra 550B-A55B (no-tools) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 60003 |
| Alibaba (Tongyi) | Qwen3.7-Plus | 90.3% | Source for Qwen3.7-Plus on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 130007 |
| Microsoft AI | MAI-Code-1-Flash | 84.6% | Source for MAI-Code-1-Flash on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 70002 |
| Anthropic | Claude Opus 4.8 (adaptive thinking, max) | 93.6% | Source for Claude Opus 4.8 (adaptive thinking, max) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 20011 |
| Alibaba (Tongyi) | Qwen3.7-Max | 92.4% | Source for Qwen3.7-Max on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 130006 |
| DeepSeek AI | DeepSeek-V4-Flash (max) | 88.1% | Source for DeepSeek-V4-Flash (max) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 110001 |
| DeepSeek AI | DeepSeek-V4-Pro (max) | 90.1% | Source for DeepSeek-V4-Pro (max) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 110002 |
| OpenAI | GPT-5.5 (xhigh) | 93.6% | Source for GPT-5.5 (xhigh) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 10008 |
| Moonshot AI | Kimi K2.6 (thinking) | 90.5% | Source for Kimi K2.6 (thinking) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 120002 |
| Anthropic | Claude Opus 4.7 (adaptive thinking, max) | 94.2% | Source for Claude Opus 4.7 (adaptive thinking, max) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 20010 |
| Z.ai | GLM-5.1 | 86.2% | Source for GLM-5.1 on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 150003 |
| Mistral AI | Mistral Small 4 (none) | 59.1% | Source for Mistral Small 4 (none) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 90004 |
| Mistral AI | Mistral Small 4 (high) | 71.2% | Source for Mistral Small 4 (high) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 90004 |
| NVIDIA | NVIDIA Nemotron 3 Super 120B-A12B (no-tools) | 79.2% | Source for NVIDIA Nemotron 3 Super 120B-A12B (no-tools) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 60002 |
| NVIDIA | NVIDIA Nemotron 3 Super 120B-A12B (tools enabled) | 82.7% | Source for NVIDIA Nemotron 3 Super 120B-A12B (tools enabled) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 60002 |
| OpenAI | GPT-5.4 (xhigh) | 92.8% | Source for GPT-5.4 (xhigh) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 10007 |
| Google (DeepMind) | Gemini 3.1 Pro (High) | 94.3% | Source for Gemini 3.1 Pro (High) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 30005 |
| Alibaba (Tongyi) | Qwen3.5-397B-A17B | 88.4% | Source for Qwen3.5-397B-A17B on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 130003 |
| Anthropic | Claude Sonnet 4.6 (adaptive thinking, max) | 89.9% | Source for Claude Sonnet 4.6 (adaptive thinking, max) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 20009 |
| Z.ai | GLM-5 (thinking) | 86.0% | Source for GLM-5 (thinking) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 150002 |
| Anthropic | Claude Opus 4.6 (adaptive thinking, max) | 91.3% | Source for Claude Opus 4.6 (adaptive thinking, max) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 20008 |
| Moonshot AI | Kimi K2.5 (thinking) | 87.6% | Source for Kimi K2.5 (thinking) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 120001 |
| Alibaba (Tongyi) | Qwen3-Max-Thinking | 87.4% | Source for Qwen3-Max-Thinking on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 130002 |
| Z.ai | GLM-4.7 | 85.7% | Source for GLM-4.7 on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 150001 |
| Google (DeepMind) | Gemini 3 Flash | 90.4% | Source for Gemini 3 Flash on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 30009 |
| NVIDIA | NVIDIA Nemotron 3 Nano 30B-A3B (no-tools) | 73.0% | Source for NVIDIA Nemotron 3 Nano 30B-A3B (no-tools) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 60001 |
| NVIDIA | NVIDIA Nemotron 3 Nano 30B-A3B (tools enabled) | 75.0% | Source for NVIDIA Nemotron 3 Nano 30B-A3B (tools enabled) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 60001 |
| OpenAI | GPT-5.2 (pro xhigh) | 93.2% | Source for GPT-5.2 (pro xhigh) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 10012 |
| OpenAI | GPT-5.2 (xhigh) | 92.4% | Source for GPT-5.2 (xhigh) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 10012 |
| Anthropic | Claude Opus 4.5 (extended thinking) | 87.0% | Source for Claude Opus 4.5 (extended thinking) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 20007 |
| Google (DeepMind) | Gemini 3 Pro (high) | 91.9% | Source for Gemini 3 Pro (high) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 30008 |
| OpenAI | gpt-oss-120b (low (no tools)) | 67.1% | Source for gpt-oss-120b (low (no tools)) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 15001 |
| OpenAI | gpt-oss-120b (medium (no tools)) | 73.1% | Source for gpt-oss-120b (medium (no tools)) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 15001 |
| OpenAI | gpt-oss-120b (low (with tools)) | 68.1% | Source for gpt-oss-120b (low (with tools)) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 15001 |
| OpenAI | gpt-oss-120b (medium (with tools)) | 73.5% | Source for gpt-oss-120b (medium (with tools)) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 15001 |
| OpenAI | gpt-oss-120b (high (with tools)) | 80.9% | Source for gpt-oss-120b (high (with tools)) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) | 15001 |