Recap · 2025-03
AI leaderboard changes March 2025
As of Mar 26, 2025, 7 confirmed crown changes are recorded for March 2025.
Crowns
Confirmed crown changes
- Mar 26, 2025. Reasoning: GPT-4.5 Preview and DeepSeek R1 are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. GPT-4.5 PreviewDeepSeek R1 · Reasoning
- Mar 25, 2025. Long context: GPT-4.5 Preview takes the crown. Crown change confirmed by two consecutive snapshots or two independent primary sources. GPT-4.5 Preview · Long context
- Mar 25, 2025. Long context: DeepSeek R1 and Command A 03 2025 and Hunyuan Large are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. DeepSeek R1Command A 03 2025Hunyuan Large · Long context
- Mar 20, 2025. Reasoning: GPT-4.5 Preview and DeepSeek R1 and O1 are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. GPT-4.5 PreviewDeepSeek R1O1 · Reasoning
- Mar 15, 2025. Long context: DeepSeek R1 and Hunyuan Large and DeepSeek V3 are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. DeepSeek R1Hunyuan LargeDeepSeek V3 · Long context
- Mar 11, 2025. Long context: GPT-4.5 Preview and Claude 3.7 Sonnet are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. GPT-4.5 PreviewClaude 3.7 Sonnet · Long context
- Mar 11, 2025. General LLM: GPT-4.5 Preview takes the crown. Crown change confirmed by two consecutive snapshots or two independent primary sources. GPT-4.5 Preview · General LLM
Top 3
Models that entered the top 3
- Claude 3.7 Sonnet at #1 in Long context
- DeepSeek R1 at #1 in Reasoning
- GPT-4.5 Preview at #1 in General LLM
- GPT-4.5 Preview at #1 in Reasoning
- GPT-4.5 Preview at #1 in Long context
- O1 at #1 in Reasoning
Benchmarks
Benchmarks added or saturated
Benchmark additions for this month are still empty.