Provider Head-to-Head
Compare AI providers across score, stability, momentum, and market share. Rankings derived from composite scores of 300 tracked models, updated hourly.
Provider Rankings
| # | Provider | Models | Avg Score | Best Model | Top Rank | 24h Avg | 7d Avg | Stability% | Free |
|---|---|---|---|---|---|---|---|---|---|
| 1 | xAI | 7 | 87.6 | Grok 4.7(88.8) | #42 | +53.9 | +64.9 | 29% | 0 |
| 2 | Anthropic | 26 | 81.7 | Claude Fable 5.1(95.9) | #1 | -2.5 | +15.2 | 46% | 0 |
| 3 | OpenAI | 78 | 79.7 | GPT-5.5 Pro(92.7) | #10 | +0.4 | -3.3 | 47% | 0 |
| 4 | 28 | 75.6 | Gemini 3.1 Pro Preview Custom Tools(92.2) | #14 | +0.4 | -6.0 | 25% | 4 | |
| 5 | Zhipu AI | 19 | 74.6 | GLM 5.3(78.6) | #100 | +0.8 | -1.2 | 5% | 1 |
| 6 | MiniMax | 7 | 71.1 | MiniMax M3(73.9) | #137 | +0.9 | -7.6 | 14% | 0 |
| 7 | thinkingmachines | 4 | 70.8 | Inkling(72.9) | #146 | +0.5 | -9.0 | 0% | 2 |
| 8 | Alibaba | 31 | 66.9 | Qwen3.5 397B A17B(79.4) | #87 | +0.7 | +19.9 | 6% | 1 |
| 9 | Mistral AI | 5 | 66.8 | Mistral Medium 3.5(71.6) | #154 | +1.0 | -3.0 | 0% | 0 |
| 10 | StepFun | 1 | 66.1 | Step 3.5 Flash(66.1) | #189 | +1.0 | -9.0 | 0% | 0 |
| 11 | Cursor | 2 | 65.7 | Composer 2(65.7) | #192 | +1.0 | -10.0 | 0% | 0 |
| 12 | arcee-ai | 1 | 63.1 | Trinity Large Thinking(63.1) | #205 | +1.0 | -10.0 | 0% | 0 |
| 13 | Meta | 5 | 61.5 | Llama 4 Maverick(70.7) | #165 | +1.4 | -9.2 | 0% | 0 |
| 14 | Xiaomi | 5 | 61.1 | MiMo-V2.6-Pro(76.2) | #117 | +137.0 | +133.6 | 0% | 0 |
| 15 | Inception | 2 | 61.0 | Mercury 2.5(61.2) | #211 | +2.0 | -9.0 | 0% | 0 |
| 16 | Amazon | 1 | 60.4 | Nova 2 Lite(60.4) | #214 | +2.0 | -9.0 | 0% | 0 |
| 17 | Microsoft | 1 | 60.2 | Phi 4(60.2) | #216 | +2.0 | -9.0 | 0% | 0 |
| 18 | meta | 7 | 57.5 | Muse Spark 1.3(80.9) | #82 | +0.7 | +45.6 | 0% | 0 |
| 19 | DeepSeek | 16 | 57.0 | DeepSeek V3.2(83.4) | #70 | +0.6 | -5.6 | 19% | 0 |
| 20 | IBM | 1 | 53.8 | Granite 4.2 8B(53.8) | #223 | +2.0 | -8.0 | 0% | 0 |
| 21 | Moonshot AI | 4 | 50.8 | Kimi K2.6(75.7) | #121 | +1.3 | -5.0 | 50% | 0 |
| 22 | Tencent | 6 | 50.5 | Hy3(74.4) | #132 | +0.2 | -7.8 | 0% | 0 |
| 23 | Cohere | 4 | 47.0 | Command A(50.8) | #226 | +2.3 | -5.5 | 25% | 1 |
| 24 | prism-ml | 1 | 40.0 | Ternary Bonsai 2 27B(40.0) | #235 | 0 | -9.0 | 0% | 0 |
| 25 | unbiased | 1 | 40.0 | Pareto(40.0) | #236 | 0 | -9.0 | 0% | 0 |
| 26 | ~deepseek | 3 | 40.0 | DeepSeek Pro Latest(40.0) | #237 | +0.3 | -7.7 | 33% | 0 |
| 27 | inference-net | 2 | 40.0 | Schematron V2 Turbo(40.0) | #239 | 0 | -9.0 | 0% | 0 |
| 28 | ~openai | 4 | 40.0 | GPT Astra Latest(40.0) | #241 | 0 | -9.0 | 0% | 0 |
| 29 | sakana | 4 | 40.0 | Fugu Ultra v2(40.0) | #245 | +0.8 | -6.5 | 25% | 0 |
| 30 | inclusionai | 6 | 40.0 | Ling 3.0 Flash VL(40.0) | #247 | +0.2 | -7.5 | 17% | 3 |
| 31 | ~z-ai | 2 | 40.0 | GLM Flash Latest(40.0) | #255 | 0 | -7.0 | 0% | 0 |
| 32 | dots-studio | 1 | 40.0 | Dots3-Note Preview (free)(40.0) | #264 | 0 | -7.0 | 0% | 1 |
| 33 | ByteDance | 2 | 40.0 | Seed 2.1 Turbo(40.0) | #267 | +0.5 | -6.5 | 0% | 0 |
| 34 | Liquid AI | 1 | 40.0 | LFM2.5-2.6B (free)(40.0) | #272 | +1.0 | -6.0 | 0% | 1 |
| 35 | NVIDIA | 2 | 40.0 | Nemotron 3.5 Lightning(40.0) | #273 | +1.0 | -6.0 | 0% | 5 |
| 36 | Upstage | 1 | 40.0 | Solar Pro 4(40.0) | #276 | +1.0 | -6.0 | 0% | 0 |
| 37 | poolside | 4 | 40.0 | Laguna S 2.1(40.0) | #285 | +1.5 | -3.5 | 100% | 2 |
| 38 | Meituan | 1 | 40.0 | LongCat 2.0(40.0) | #289 | +1.0 | -4.0 | 100% | 0 |
| 39 | Kuaishou | 1 | 40.0 | KAT-Coder-Pro V2.5(40.0) | #291 | +2.0 | -3.0 | 100% | 0 |
| 40 | ~x-ai | 1 | 40.0 | Grok Latest(40.0) | #292 | +2.0 | -3.0 | 100% | 0 |
| 41 | aion-labs | 2 | 40.0 | Aion-3.0-Mini(40.0) | #293 | +2.0 | -3.0 | 100% | 0 |
Top 5 Providers
Stability Comparison
Providers with at least 2 models, ranked by percentage of models in a "stable" state. Higher stability means more consistent performance over time.
Market Concentration
Distribution of tracked models across providers. Shows each provider's share of the total 300 models in the leaderboard.
| Provider | Models | Share | % |
|---|---|---|---|
| OpenAI | 78 | 26.0% | |
| Alibaba | 31 | 10.3% | |
| 28 | 9.3% | ||
| Anthropic | 26 | 8.7% | |
| Zhipu AI | 19 | 6.3% | |
| DeepSeek | 16 | 5.3% | |
| xAI | 7 | 2.3% | |
| MiniMax | 7 | 2.3% | |
| meta | 7 | 2.3% | |
| Tencent | 6 | 2.0% | |
| inclusionai | 6 | 2.0% | |
| Mistral AI | 5 | 1.7% | |
| Meta | 5 | 1.7% | |
| Xiaomi | 5 | 1.7% | |
| thinkingmachines | 4 | 1.3% | |
| Moonshot AI | 4 | 1.3% | |
| Cohere | 4 | 1.3% | |
| ~openai | 4 | 1.3% | |
| sakana | 4 | 1.3% | |
| poolside | 4 | 1.3% | |
| ~deepseek | 3 | 1.0% | |
| Cursor | 2 | 0.7% | |
| Inception | 2 | 0.7% | |
| inference-net | 2 | 0.7% | |
| ~z-ai | 2 | 0.7% | |
| ByteDance | 2 | 0.7% | |
| NVIDIA | 2 | 0.7% | |
| aion-labs | 2 | 0.7% | |
| StepFun | 1 | 0.3% | |
| arcee-ai | 1 | 0.3% | |
| Amazon | 1 | 0.3% | |
| Microsoft | 1 | 0.3% | |
| IBM | 1 | 0.3% | |
| prism-ml | 1 | 0.3% | |
| unbiased | 1 | 0.3% | |
| dots-studio | 1 | 0.3% | |
| Liquid AI | 1 | 0.3% | |
| Upstage | 1 | 0.3% | |
| Meituan | 1 | 0.3% | |
| Kuaishou | 1 | 0.3% | |
| ~x-ai | 1 | 0.3% |
Related
Providers are compared across multiple dimensions: average composite score across all models, best individual model score, stability rate (percentage of models in a stable state), 24-hour and 7-day momentum, model count, and availability of free models. Data is derived from hourly-updated rankings of 290+ tracked models.
The stability percentage represents the fraction of a provider's models that are in a "stable" ranking state. A higher percentage means the provider's models consistently maintain their positions over time, suggesting reliable and predictable performance across their lineup.
Market concentration is shown as each provider's share of the total tracked models. The visual bar chart and percentage table reveal how models are distributed among providers, helping identify whether the market is dominated by a few large players or spread across many competitors.