Loading page content
Historical Trends
The horizontal axis is model release date; the vertical axis is the highest overall score among models released by that point.Updated 10/31, 17:09
Current Open-weight leader
125 Open-weight models are included in the overall score
Kimi K3
Overall score 91.5
Current Proprietary leader
80 Proprietary models are included in the overall score
Gemini 4 Argon
Overall score 100.0
Highest Overall Score Over Time
Scores use the current Overall frontier domain's Bradley-Terry / Elo results, normalized so the leading model scores 100.
Highest open-weight scoreHighest proprietary score
Leadership Changes
Only dates when the leading open-weight or proprietary model changed are shown.
| Date | Open-weight leader | Proprietary leader |
|---|---|---|
| 2026-09 | Kimi K391.5 | Gemini 4 Argon100.0 |
| 2026-07 | Kimi K391.5 | Claude Opus 595.6 |
| 2026-06 | GLM-5.282.1 | Claude Fable 594.0 |
| 2026-04 | Kimi-K2.679.7 | GPT-5.5 Pro87.5 |
| 2026-03 | GPT-5.4 Pro86.1 | |
| 2026-02 | GPT-5.2 Pro79.6 | |
| 2026-01 | Kimi-K2.572.4 | GPT-5.2 Pro79.6 |
| 2025-12 | GLM-4.769.7 | GPT-5.2 Pro79.6 |
| 2025-11 | Gemini 3 Pro77.8 | |
| 2025-10 | GPT-5 Pro72.8 | |
| 2025-08 | GPT-572.0 | |
| 2025-07 | o370.2 | |
| 2025-04 | Qwen3-235B-A22B68.1 | o370.2 |
| 2025-03 | DeepSeek-R166.1 | Gemini 2.5 Pro69.1 |
| 2025-02 | DeepSeek-R166.1 | |
| 2025-01 | DeepSeek-R166.1 | OpenAI o166.5 |
| 2024-12 | DeepSeek-V360.1 | OpenAI o166.5 |
| 2024-09 | Qwen2.5-72B58.1 | |
| 2024-07 | GPT-4o56.5 | |
| 2024-05 | DeepSeek-V2-050649.1 | GPT-4o56.5 |
| 2024-04 | Llama 3 8B Base42.2 | No model |
