Recap · 2025-08
AI leaderboard changes August 2025
As of Aug 28, 2025, 20 confirmed crown changes are recorded for August 2025.
Crowns
Confirmed crown changes
- Aug 28, 2025. Long context: Kimi K2 0711 Preview and DeepSeek V3.1 are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. Kimi K2 0711 PreviewDeepSeek V3.1 · Long context
- Aug 28, 2025. Image generation: Qwen Image Prompt Extend takes the crown. Crown change confirmed by two consecutive snapshots or two independent primary sources. Qwen Image Prompt Extend · Image generation
- Aug 28, 2025. General LLM: Kimi K2 0711 Preview and DeepSeek V3.1 are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. Kimi K2 0711 PreviewDeepSeek V3.1 · General LLM
- Aug 27, 2025. Long context: Gemini 2.5 Pro and GPT-5 are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. Gemini 2.5 ProGPT-5 · Long context
- Aug 27, 2025. General LLM: Gemini 2.5 Pro and GPT-5 are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. Gemini 2.5 ProGPT-5 · General LLM
- Aug 27, 2025. Reasoning: Qwen3 235B A22b Instruct 2507 and GLM 4.5 are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. Qwen3 235B A22b Instruct 2507GLM 4.5 · Reasoning
- Aug 27, 2025. Image edit: Qwen Image Edit takes the crown. Crown change confirmed by two consecutive snapshots or two independent primary sources. Qwen Image Edit · Image edit
- Aug 18, 2025. Reasoning: GPT-5 and Claude Opus 4.1 and Gemini 2.5 Pro and Qwen3 235B A22b Instruct 2507 are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. GPT-5Claude Opus 4.1Gemini 2.5 ProQwen3 235B A22b Instruct 2507 · Reasoning
- Aug 18, 2025. Long context: GPT-5 and Gemini 2.5 Pro and Claude Opus 4.1 are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. GPT-5Gemini 2.5 ProClaude Opus 4.1 · Long context
- Aug 18, 2025. General LLM: GPT-5 and Gemini 2.5 Pro and Claude Opus 4.1 are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. GPT-5Gemini 2.5 ProClaude Opus 4.1 · General LLM
- Aug 18, 2025. Long context: Qwen3 235B A22b Instruct 2507 and Kimi K2 0711 Preview are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. Qwen3 235B A22b Instruct 2507Kimi K2 0711 Preview · Long context
- Aug 18, 2025. General LLM: Qwen3 235B A22b Instruct 2507 and Kimi K2 0711 Preview are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. Qwen3 235B A22b Instruct 2507Kimi K2 0711 Preview · General LLM
- Aug 14, 2025. Image generation: Qwen Image takes the crown. Crown change confirmed by two consecutive snapshots or two independent primary sources. Qwen Image · Image generation
- Aug 7, 2025. Video generation: Veo 3 takes the crown. First holder recorded for this category and slice. Veo 3 · Video generation
- Aug 7, 2025. Video generation: Wan V2.2 A14b takes the crown. First holder recorded for this category and slice. Wan V2.2 A14b · Video generation
- Aug 7, 2025. Reasoning: Qwen3 235B A22b Instruct 2507 and GLM 4.5 and Kimi K2 0711 Preview and DeepSeek R1 0528 are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. Qwen3 235B A22b Instruct 2507GLM 4.5Kimi K2 0711 PreviewDeepSeek R1 0528 · Reasoning
- Aug 7, 2025. Long context: Qwen3 235B A22b Instruct 2507 and Kimi K2 0711 Preview and DeepSeek R1 0528 and GLM 4.5 are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. Qwen3 235B A22b Instruct 2507Kimi K2 0711 PreviewDeepSeek R1 0528GLM 4.5 · Long context
- Aug 7, 2025. General LLM: Qwen3 235B A22b Instruct 2507 and Kimi K2 0711 Preview and DeepSeek R1 0528 and GLM 4.5 are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. Qwen3 235B A22b Instruct 2507Kimi K2 0711 PreviewDeepSeek R1 0528GLM 4.5 · General LLM
- Aug 7, 2025. Image generation: Qwen Image takes the crown. First holder recorded for this category and slice. Qwen Image · Image generation
- Aug 4, 2025. Reasoning: Gemini 2.5 Pro and Qwen3 235B A22b Instruct 2507 and O3 are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. Gemini 2.5 ProQwen3 235B A22b Instruct 2507O3 · Reasoning
Top 3
Models that entered the top 3
- Claude Opus 4.1 at #1 in General LLM
- Claude Opus 4.1 at #1 in Reasoning
- Claude Opus 4.1 at #1 in Long context
- Gemini 2.5 Pro at #1 in General LLM
- Gemini 2.5 Pro at #1 in Reasoning
- Gemini 2.5 Pro at #1 in Long context
- GPT-5 at #1 in General LLM
- GPT-5 at #1 in Reasoning
- GPT-5 at #1 in Long context
- O3 at #1 in Reasoning
- Qwen3 235B A22b Instruct 2507 at #1 in Reasoning
- Veo 3 at #1 in Video generation
Benchmarks
Benchmarks added or saturated
Benchmark additions for this month are still empty.