Loading...
Loading...
Loading...
8.7%
Year-over-year SOTA improvement
4 months
Avg. time between SOTA records
-0.0024
Change in improvement rate (points/month²)
75.7x
Total GPQA improvement since 2019
o3 Preview | 01 Dec 2023 | - | Proprietary | - | - | - | - | 87.7% | ||
Claude 3.7 Sonnet | 01 Apr 2024 | 24 Feb 2025 | Proprietary | - | 200,000 | $3.00 | $15.00 | 84.8% | ||
Gemini 2.5 Pro | 31 Jan 2025 | 28 Mar 2025 | Proprietary | - | 1,048,576 | - | - | 84.0% | ||
Grok 3 Mini Beta (Think) | - | - | Proprietary | - | - | - | - | 84.0% | ||
Claude Sonnet 4 | 01 Mar 2025 | 21 May 2025 | Proprietary | - | 200,000 | $3.00 | $15.00 | 83.8% | ||
Claude Opus 4 | 01 Mar 2025 | 21 May 2025 | Proprietary | - | 200,000 | $15.00 | $75.00 | 83.3% | ||
o3 | 01 Jun 2024 | 16 Apr 2025 | Proprietary | - | 200,000 | $10.00 | $40.00 | 83.3% | ||
o4 Mini | 01 Jun 2024 | 16 Apr 2025 | Proprietary | - | 200,000 | $1.10 | $4.40 | 81.4% | ||
o4 Mini High | 01 Jun 2024 | 16 Apr 2025 | Proprietary | - | 200,000 | $1.10 | $4.40 | 81.4% | ||
o3 Mini High | - | 12 Feb 2025 | Proprietary | - | 200,000 | $1.10 | $4.40 | 79.7% | ||
o1-pro | - | 19 Mar 2025 | Proprietary | - | 200,000 | $150.00 | $600.00 | 79.0% | ||
Gemini 2.5 Flash | 31 Jan 2025 | 17 Apr 2025 | Proprietary | - | 1,048,576 | - | - | 78.3% | ||
Claude 3.7 Sonnet (thinking) | - | 24 Feb 2025 | Proprietary | - | 200,000 | $3.00 | $15.00 | 78.2% | ||
o1 | - | 17 Dec 2024 | Proprietary | - | 200,000 | $15.00 | $60.00 | 78.0% | ||
o3-mini | 30 Sept 2023 | 30 Jan 2025 | Proprietary | - | 200,000 | - | - | 77.2% | ||
o3 Mini Medium | - | 31 Jan 2025 | Proprietary | - | 200,000 | $1.10 | $4.40 | 76.8% | ||
Llama 3.1 Nemotron Ultra 253B v1 | 01 Dec 2023 | 07 Apr 2025 | Open | 253.0B | 131,072 | - | - | 76.0% | ||
Grok 3 Beta | 17 Nov 2024 | 17 Feb 2025 | Proprietary | - | 128,000 | - | - | 75.4% | ||
Grok 3 Beta (Think) | 17 Nov 2024 | - | Proprietary | - | 128,000 | - | - | 75.4% | ||
Gemini 2.0 Flash Thinking | 01 Aug 2024 | 21 Jan 2025 | Proprietary | - | 1,000,000 | - | - | 74.2% | ||
o1-preview | - | 12 Sept 2024 | Proprietary | - | 128,000 | $15.00 | $60.00 | 73.3% | ||
R1 | - | 20 Jan 2025 | Open | 671.0B | 128,000 | $0.50 | $3.00 | 71.5% | ||
GPT-4.5 (Preview) | - | 27 Feb 2025 | Proprietary | - | 128,000 | $75.00 | $150.00 | 71.4% | ||
o3 Mini Low | - | 12 Feb 2025 | Proprietary | - | 200,000 | $1.10 | $4.40 | 70.6% | ||
Llama 4 Maverick | - | 05 Apr 2025 | - | - | 1,048,576 | $0.17 | $0.85 | 69.8% |
Event | Model | Provider | Type | Announced Date | Release Date | |
---|---|---|---|---|---|---|
Announced Released | R1 | Text | 28 May 2025 | 28 May 2025 | 5 days ago | |
Announced Released | Claude Opus 4 | Multimodal | 21 May 2025 | 21 May 2025 | 12 days ago | |
Announced Released | Claude Sonnet 4 | Multimodal | 21 May 2025 | 21 May 2025 | 12 days ago | |
Announced Released | Granite 4.0 Tiny Preview | Text | 02 May 2025 | 02 May 2025 | 1 mo ago | |
Announced Released | Nova Premier | Multimodal | 30 Apr 2025 | 30 Apr 2025 | 1 mo ago |