140 models improved, 145 declined, and 15 unchanged this week across 300 tracked models.
New Entries
10
new models entered rankings this week
Top 10 models with the largest absolute rank changes over the past 7 days.
| Model | Score | 7d Change | Rank |
|---|---|---|---|
| GPT-5.4 MiniOpenAI | 93.3 | +301 | #3 |
| MiMo-V2-OmniXiaomi | 85.0 | +282 | #22 |
| MiMo-V2-ProXiaomi | 85.0 | +281 | #23 |
| GPT-5.4 NanoOpenAI | 85.0 | +280 | #24 |
| MiniMax M2.7MiniMax | 83.0 | +251 | #53 |
| Mistral Small 4Mistral AI | 79.4 | +225 | #79 |
| GPT-5.1OpenAI | 85.2 | +29 | #21 |
| GPT-5 CodexOpenAI | 85.0 | -27 | #43 |
| Hunyuan A13B InstructTencent | 72.3 | -27 | #141 |
| o4 MiniOpenAI | 83.7 | -23 | #50 |
Models with the largest positive rank improvements this week.
Models with the largest negative rank drops this week.
10 new models entered the rankings this week.
| Model | Score | Rank |
|---|---|---|
| GPT-5.4 MiniOpenAI | 93.3 | #3 |
| MiMo-V2-OmniXiaomi | 85.0 | #22 |
| MiMo-V2-ProXiaomi | 85.0 | #23 |
| GPT-5.4 NanoOpenAI | 85.0 | #24 |
| MiniMax M2.7MiniMax | 83.0 | #53 |
| Mistral Small 4Mistral AI | 79.4 | #79 |
| GPT-5.1OpenAI | 85.2 | #21 |
| Seed 1.6 FlashByteDance | 85.0 | #33 |
| gpt-oss-20b (free)OpenAI | 73.8 | #117 |
| Nemotron 3 SuperNVIDIA | 73.5 | #120 |
Models in a fragile state that might degrade further. Monitor closely.
| Model | Score | 7d Change |
|---|---|---|
| 87.7 | +10 | |
| 85.8 | +20 | |
| 85.7 | +12 | |
| 85.7 | -6 | |
| 85.2 | +29 | |
| 85.0 | +6 | |
| 85.0 | +9 | |
| 85.0 | +9 | |
| 85.0 | +10 | |
| 85.0 | +21 | |
| 85.0 | +15 | |
| 85.0 | -13 | |
| 85.0 | +10 | |
| 85.0 | +11 | |
| 85.0 | -18 | |
| 85.0 | -8 | |
| 85.0 | +11 | |
| 85.0 | -27 | |
| 85.0 | -15 | |
| 84.8 | +10 | |
| 84.8 | -20 | |
| 84.3 | +15 | |
| 83.7 | +11 | |
| 83.7 | -23 | |
| 83.4 | +6 | |
| 83.3 | -19 | |
| 82.9 | +17 | |
| 82.8 | -14 | |
| 82.7 | +14 | |
| 82.6 | -15 | |
| 82.4 | -15 | |
| 82.3 | -15 | |
| 82.2 | +17 | |
| 82.0 | -11 | |
| 81.9 | +11 | |
| 81.8 | -7 | |
| 81.7 | -11 | |
| 81.3 | +9 | |
| 80.9 | -12 | |
| 80.9 | +17 | |
| 80.9 | +9 | |
| 80.1 | -15 | |
| 79.9 | -11 | |
| 79.7 | +6 | |
| 79.4 | -11 | |
| 79.3 | +14 | |
| 79.1 | -16 | |
| 78.6 | -7 | |
| 78.3 | +18 | |
| 78.2 | -10 | |
| 77.8 | -8 | |
| 77.4 | +16 | |
| 77.4 | -10 | |
| 77.4 | +15 | |
| 77.2 | -7 | |
| 77.1 | -9 | |
| 77.0 | +14 | |
| 76.7 | -10 | |
| 76.5 | +16 | |
| 76.0 | +14 | |
| 76.0 | -12 | |
| 75.7 | -15 | |
| 75.6 | +17 | |
| 75.2 | +6 | |
| 75.0 | +14 | |
| 75.0 | +11 | |
| 74.1 | -14 | |
| 74.0 | -7 | |
| 73.8 | -13 | |
| 73.8 | -12 | |
| 73.8 | +21 | |
| 73.7 | +10 | |
| 73.7 | +14 | |
| 73.5 | +21 | |
| 73.5 | -21 | |
| 73.5 | -7 | |
| 73.4 | +11 | |
| 73.2 | -7 | |
| 73.1 | +20 | |
| 72.9 | -8 | |
| 72.8 | +16 | |
| 72.7 | -21 | |
| 72.7 | +19 | |
| 72.7 | -20 | |
| 72.6 | +21 | |
| 72.6 | +21 | |
| 72.6 | +8 | |
| 72.6 | -15 | |
| 72.3 | -27 | |
| 72.1 | -13 | |
| 72.0 | -12 | |
| 71.6 | -18 | |
| 71.4 | -16 | |
| 71.2 | -7 | |
| 70.3 | +13 | |
| 70.1 | +7 | |
| 70.0 | -19 | |
| 69.8 | +8 | |
| 69.7 | -17 | |
| 69.2 | -9 | |
| 69.0 | +9 | |
| 68.6 | -8 | |
| 68.4 | -6 | |
| 68.4 | -12 | |
| 68.4 | +11 | |
| 67.7 | +16 | |
| 67.7 | -12 | |
| 67.3 | +10 | |
| 66.7 | +6 | |
| 66.3 | -8 | |
| 66.1 | +9 | |
| 65.8 | -8 | |
| 65.7 | -15 | |
| 65.4 | +21 | |
| 65.2 | +15 | |
| 65.0 | -6 | |
| 64.9 | -13 | |
| 64.8 | -17 | |
| 64.6 | +10 | |
| 64.4 | +6 | |
| 63.6 | +11 | |
| 63.3 | +8 | |
| 63.1 | +8 | |
| 63.0 | -16 | |
| 62.8 | -6 | |
| 62.7 | -17 | |
| 62.6 | -11 | |
| 62.3 | -15 | |
| 62.2 | +11 | |
| 62.0 | -6 | |
| 61.6 | +8 | |
| 61.0 | +8 | |
| 60.9 | +8 | |
| 60.3 | +10 | |
| 60.2 | +12 | |
| 59.7 | -6 | |
| 59.6 | +6 | |
| 59.5 | +6 | |
| 59.4 | -8 | |
| 59.0 | -7 | |
| 59.0 | -17 | |
| 59.0 | -17 | |
| 57.5 | -6 | |
| 56.7 | +15 | |
| 56.6 | +15 | |
| 56.6 | +6 | |
| 56.2 | -12 | |
| 55.6 | +12 | |
| 54.3 | -10 | |
| 54.1 | -9 | |
| 53.7 | +7 | |
| 53.2 | +9 | |
| 53.2 | -16 | |
| 53.0 | -8 | |
| 43.0 | +9 | |
| 42.9 | +6 | |
| 42.7 | +6 | |
| 42.4 | -6 | |
| 39.0 | +6 |
Top 10 AI models this week by composite score.
| # | Model | Score | 7d Change |
|---|---|---|---|
| 1 | GPT-5.4 ProOpenAI | 94.0 | 0 |
| 2 | GPT-5.4OpenAI | 94.0 | +4 |
| 3 | GPT-5.4 MiniOpenAI | 93.3 | +301 |
| 4 | GPT-5.2 ProOpenAI | 92.7 | -1 |
| 5 | GPT-5.2OpenAI | 92.7 | +4 |
| 6 | Claude Opus 4.6Anthropic | 92.1 | -1 |
| 7 | GPT-5 ProOpenAI | 91.9 | 0 |
| 8 | o3 Deep ResearchOpenAI | 91.5 | -4 |
| 9 | Claude Opus 4.5Anthropic | 90.4 | -1 |
| 10 | Gemini 3 Pro PreviewGoogle | 90.3 | +1 |
Total Ranked
300
Avg Score
68.2
Top 10 Moved
8/10
Most Active Provider
OpenAI
The weekly report summarizes seven days of AI model ranking changes. It highlights the biggest gainers and losers by rank position, new models entering the leaderboard, models in a fragile watch-list state, and a snapshot of the current top 10. All data comes from hourly-updated composite scores across 290+ models.
Gainers and losers are ranked by their 7-day rank change, which measures how many positions a model moved up or down on the leaderboard over the past week. The models with the largest positive changes are the top gainers, and those with the largest negative changes are the top losers.
The watch list contains models currently in a "fragile" state, meaning their rankings are unstable and could degrade further. Monitoring these models is important if you rely on them in production, as they may experience significant quality or performance drops in the near term.