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 | Anthropic | 28 | 82.5 | Claude Fable 5(97.1) | #1 | 0 | +116.8 | 21% | 0 |
| 2 | meta | 2 | 80.2 | Muse Spark 1.2(80.2) | #85 | 0 | +127.0 | 0% | 0 |
| 3 | xAI | 5 | 78.9 | Grok 4.5(88.8) | #44 | 0 | +288.6 | 0% | 0 |
| 4 | 27 | 78.5 | Gemini 3.1 Pro Preview Custom Tools(92.2) | #15 | 0 | +60.8 | 0% | 4 | |
| 5 | OpenAI | 86 | 77.6 | GPT-5.5 Pro(92.7) | #11 | +0 | +93.9 | 3% | 1 |
| 6 | Xiaomi | 2 | 74.6 | MiMo-V2.5-Pro(76.2) | #116 | 0 | -51.5 | 0% | 0 |
| 7 | MiniMax | 8 | 73.5 | MiniMax M2.7(78.0) | #105 | +0.3 | -9.1 | 13% | 0 |
| 8 | Zhipu AI | 13 | 73.1 | GLM 5.2(78.5) | #102 | +0.1 | -19.8 | 0% | 0 |
| 9 | thinkingmachines | 3 | 72.8 | Inkling(74.0) | #137 | -3.0 | +40.3 | 0% | 0 |
| 10 | Tencent | 2 | 71.1 | Hy3(74.0) | #138 | 0 | -60.0 | 0% | 0 |
| 11 | DeepSeek | 12 | 66.4 | DeepSeek V4 Pro(86.7) | #60 | +0.3 | -37.0 | 0% | 0 |
| 12 | Cursor | 2 | 65.7 | Composer 2(65.7) | #186 | 0 | -60.0 | 0% | 0 |
| 13 | Alibaba | 31 | 65.0 | Qwen3.8 Max(80.6) | #82 | 0 | -28.4 | 0% | 0 |
| 14 | arcee-ai | 1 | 63.9 | Trinity Large Thinking(63.9) | #198 | 0 | -62.0 | 0% | 0 |
| 15 | Mistral AI | 6 | 62.3 | Mistral Medium 3.5(71.7) | #153 | +0.2 | -55.8 | 0% | 0 |
| 16 | Inception | 1 | 61.0 | Mercury 2(61.0) | #205 | 0 | -63.0 | 0% | 0 |
| 17 | Amazon | 1 | 60.5 | Nova 2 Lite(60.5) | #207 | 0 | -63.0 | 0% | 0 |
| 18 | Microsoft | 1 | 60.2 | Phi 4(60.2) | #208 | 0 | -63.0 | 0% | 0 |
| 19 | Meta | 5 | 59.8 | Llama 4 Maverick(67.9) | #173 | 0 | -60.6 | 0% | 0 |
| 20 | IBM | 1 | 55.3 | Granite 4.1 8B(55.3) | #215 | 0 | -63.0 | 0% | 0 |
| 21 | Moonshot AI | 8 | 55.0 | Kimi K2.6(75.8) | #119 | 0 | -33.3 | 0% | 0 |
| 22 | Allen AI | 1 | 54.9 | Olmo 3 32B Think(54.9) | #216 | 0 | -63.0 | 0% | 0 |
| 23 | StepFun | 2 | 53.0 | Step 3.5 Flash(66.1) | #183 | 0 | -61.5 | 0% | 0 |
| 24 | Cohere | 4 | 47.0 | Command A(50.8) | #226 | +0.3 | -62.8 | 0% | 1 |
| 25 | inclusionai | 5 | 40.0 | Ling 3.0 Tiny (free)(40.0) | #234 | 0 | +19.2 | 0% | 1 |
| 26 | ~deepseek | 1 | 40.0 | DeepSeek V4 Flash Latest(40.0) | #235 | 0 | -64.0 | 0% | 0 |
| 27 | poolside | 4 | 40.0 | Laguna S 2.1(40.0) | #240 | 0 | -63.0 | 0% | 2 |
| 28 | Meituan | 1 | 40.0 | LongCat 2.0(40.0) | #242 | 0 | -63.0 | 0% | 0 |
| 29 | Kuaishou | 3 | 40.0 | KAT-Coder-Air V2.5(40.0) | #244 | 0 | -63.0 | 0% | 0 |
| 30 | ~x-ai | 1 | 40.0 | Grok Latest(40.0) | #246 | 0 | -63.0 | 0% | 0 |
| 31 | aion-labs | 3 | 40.0 | Aion-3.0-Mini(40.0) | #247 | 0 | -63.0 | 0% | 0 |
| 32 | sakana | 1 | 40.0 | Fugu Ultra(40.0) | #252 | 0 | -63.0 | 0% | 0 |
| 33 | ~anthropic | 4 | 40.0 | Claude Fable Latest(40.0) | #254 | 0 | -63.0 | 0% | 0 |
| 34 | NVIDIA | 9 | 40.0 | Nemotron 3.5 Content Safety (free)(40.0) | #255 | 0 | -43.0 | 0% | 7 |
| 35 | perceptron | 1 | 40.0 | Perceptron Mk1(40.0) | #261 | 0 | -63.0 | 0% | 0 |
| 36 | ~openai | 2 | 40.0 | OpenAI GPT Mini Latest(40.0) | #266 | 0 | -63.0 | 0% | 0 |
| 37 | 2 | 40.0 | Google Gemini Pro Latest(40.0) | #267 | 0 | -63.0 | 0% | 0 | |
| 38 | ~moonshotai | 1 | 40.0 | MoonshotAI Kimi Latest(40.0) | #268 | 0 | -63.0 | 0% | 0 |
| 39 | rekaai | 1 | 40.0 | Reka Edge(40.0) | #282 | 0 | -63.0 | 0% | 0 |
| 40 | ByteDance | 4 | 40.0 | Seed-2.0-Lite(40.0) | #286 | 0 | -64.0 | 0% | 0 |
| 41 | Upstage | 1 | 40.0 | Solar Pro 3(40.0) | #290 | 0 | -62.0 | 0% | 0 |
| 42 | Writer | 1 | 40.0 | Palmyra X5(40.0) | #291 | 0 | -62.0 | 0% | 0 |
| 43 | TII | 3 | 40.0 | Falcon-H1-Arabic 34B Instruct(40.0) | #294 | 0 | +1.0 | 100% | 7 |
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 | 86 | 28.7% | |
| Alibaba | 31 | 10.3% | |
| Anthropic | 28 | 9.3% | |
| 27 | 9.0% | ||
| Zhipu AI | 13 | 4.3% | |
| DeepSeek | 12 | 4.0% | |
| NVIDIA | 9 | 3.0% | |
| MiniMax | 8 | 2.7% | |
| Moonshot AI | 8 | 2.7% | |
| Mistral AI | 6 | 2.0% | |
| xAI | 5 | 1.7% | |
| Meta | 5 | 1.7% | |
| inclusionai | 5 | 1.7% | |
| Cohere | 4 | 1.3% | |
| poolside | 4 | 1.3% | |
| ~anthropic | 4 | 1.3% | |
| ByteDance | 4 | 1.3% | |
| thinkingmachines | 3 | 1.0% | |
| Kuaishou | 3 | 1.0% | |
| aion-labs | 3 | 1.0% | |
| TII | 3 | 1.0% | |
| meta | 2 | 0.7% | |
| Xiaomi | 2 | 0.7% | |
| Tencent | 2 | 0.7% | |
| Cursor | 2 | 0.7% | |
| StepFun | 2 | 0.7% | |
| ~openai | 2 | 0.7% | |
| 2 | 0.7% | ||
| arcee-ai | 1 | 0.3% | |
| Inception | 1 | 0.3% | |
| Amazon | 1 | 0.3% | |
| Microsoft | 1 | 0.3% | |
| IBM | 1 | 0.3% | |
| Allen AI | 1 | 0.3% | |
| ~deepseek | 1 | 0.3% | |
| Meituan | 1 | 0.3% | |
| ~x-ai | 1 | 0.3% | |
| sakana | 1 | 0.3% | |
| perceptron | 1 | 0.3% | |
| ~moonshotai | 1 | 0.3% | |
| rekaai | 1 | 0.3% | |
| Upstage | 1 | 0.3% | |
| Writer | 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.