AI Rankings
Compare top AI tools and models based on performance and community ratings.
| Rank | AI Model Name | Developer | Context Length (token) | Intelligence Score | Avg. Price (USD/1M token) | Speed (token/s) | Latency (s) | Rating |
|---|---|---|---|---|---|---|---|---|
| 1 |  Claude Fable 5 (max)Claude Fable 5 (Adaptive Reasoning, Max Effort) is… | Anthropic | 1m | 65 | $8.20 | 59.0 | 94.84 | (3.0) |
| 2 | Claude Opus 4.8 (max)Claude Opus 4.8 (Adaptive Reasoning, Max Effort) i… | Anthropic | 1m | 61 | $4.10 | 58.0 | 13.71 | |
| 3 |  GPT-5.5 (xhigh)GPT-5.5 (xhigh) is a proprietary OpenAI model, hig… | OpenAI | 922k | 60 | $11.25 | 73.0 | 64.21 | |
| 4 | GPT-5.5 (high)GPT-5.5 (high) is a proprietary OpenAI model, rank… | OpenAI | 922k | 59 | $11.25 | 82.0 | 26.60 | |
| 5 | Claude Opus 4.7 (max)Claude Opus 4.7 (Adaptive Reasoning, Max Effort) i… | Anthropic | 1m | 58 | $10.00 | 50.0 | 13.49 | |
| 6 |  Gemini 3.5 Flash (high)Gemini 3.5 Flash is Google DeepMind's latest effic… | 1m | 57 | $1.31 | 204.0 | 17.19 | ||
| 7 |  Qwen3.7 MaxQwen3.7 Max is a proprietary model from Alibaba, d… | Alibaba | 1m | 57 | $1.43 | 208.0 | 2.52 | |
| 8 | Gemini 3.1 Pro PreviewGemini 3.1 Pro Preview is Google's most advanced r… | 1m | 57 | $4.50 | 109.0 | 30.73 | (4.0) | |
| 9 | GPT-5.4 (xhigh)GPT-5.4 (xhigh) is one of the leading models in in… | OpenAI | 1m | 57 | $5.63 | 78.0 | 184.99 | (2.0) |
| 10 | GPT-5.5 (medium)GPT-5.5 (medium) is one of the leading models in i… | OpenAI | 922k | 57 | $11.25 | 79.0 | 5.90 | |
| 11 | GPT-5.3 Codex (xhigh)GPT-5.3 Codex (high) is one of the leading models … | OpenAI | 400k | 56 | $4.81 | 99.0 | 61.42 | (2.0) |
| 12 |  GLM-5.2 (max)GLM-5.2 (max) is the flagship model of Z.ai, desig… | Z.ai | 1m | 53 | $0.90 | 112.0 | 2.38 | |
| 13 |  Grok 4.3Grok 4.3 is a proprietary model from xAI, supporti… | xAI | 1m | 53 | $1.56 | 104.0 | 5.63 | |
| 14 | Claude Opus 4.6 (max)Claude Opus 4.6 (Thinking) is one of the models pr… | Anthropic | 1m | 53 | $10.00 | 66.0 | 1.80 | (3.0) |
| 15 |  DeepSeek V4 Pro (Max)DeepSeek V4 Pro (Reasoning, Max Effort) is one of … | DeepSeek | 1m | 52 | $2.17 | 34.0 | 1.86 | |
| 16 | Claude Opus 4.7Claude Opus 4.7 (Non-reasoning, High Effort) is on… | Anthropic | 1m | 52 | $10.00 | 40.0 | 1.67 | |
| 17 | Gemini 3 Pro Preview (high)Gemini 3 Pro Preview (high) is one of the leading … | 1m | 51 | $4.50 | 111.0 | 29.30 | (3.0) | |
| 18 | GPT-5.5 (low)GPT-5.5 (low) is a new model from OpenAI, notable … | OpenAI | 922k | 51 | $4.35 | 76.0 | 2.15 | |
| 19 | Qwen3.6 Max PreviewQwen3.6 Max Preview is a proprietary model from Al… | Alibaba | 256k | 51 | $2.92 | 36.0 | 3.44 | |
| 20 | GLM-5.1 (Reasoning)GLM-5.1 (Reasoning) is a leading intelligence mode… | Z.ai | 200k | 51 | $2.15 | 49.0 | 1.49 | |
| 21 | Claude Sonnet 4.6 (max)Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)… | Anthropic | 200k | 51 | $6.00 | 58.0 | 0.63 | (3.0) |
| 22 | DeepSeek V4 Pro (high)DeepSeek V4 Pro (Reasoning, High Effort) is one of… | DeepSeek | 1m | 50 | $0.18 | 51.0 | 1.91 | |
| 23 | Qwen3.6 PlusQwen3.6 Plus is one of the leading models in intel… | Alibaba | 1m | 50 | $1.13 | 53.0 | 2.76 | |
| 24 | GPT-5.2 Codex (high)GPT-5.2 Codex (high) is one of the leading models … | OpenAI | 400k | 50 | $4.81 | 92.0 | 37.37 | |
| 25 | Claude Opus 4.5 (thinking)Claude Opus 4.5 in Thinking mode is a powerful mod… | Anthropic | 200k | 50 | $10.00 | 70.0 | 1.54 | |
| 26 | Gemini 3 Flash Preview (reasoning)Gemini 3 Flash (Reasoning) is Google's high-speed … | 1m | 49 | $1.13 | 163.0 | 10.54 | ||
| 27 | GPT-5.4 mini (high)GPT-5.4 mini (xhigh) is one of the leading models … | OpenAI | 400k | 49 | $1.69 | 199.0 | 3.35 | |
| 28 | Claude Opus 4.6Claude Opus 4.6 (Non-thinking) — the default high-… | Anthropic | 200k | 48 | $10.00 | 45.0 | 1.91 | |
| 29 | GLM-5 (reasoning)GLM-5 (Reasoning) is a leading intelligence model … | Z.ai | 200k | 47 | $1.55 | 95.0 | 1.40 | |
| 30 | DeepSeek V4 Flash (max)DeepSeek V4 Flash (Max/Reasoning, Max Effort) is a… | DeepSeek | 1m | 46 | $0.06 | 137.0 | 1.18 | |
| 31 | Qwen3.5 397B A17B (reasoning)Qwen3.5 397B A17B (reasoning) is an open-source mo… | Alibaba | 262k | 46 | $1.35 | 84.0 | 2.68 | |
| 32 | Grok 4.20 Beta 0309 (reasoning)Grok 4.20 Beta 0309 (Reasoning) is a proprietary m… | xAI | 2m | 45 | $3.00 | 220.0 | 11.87 | (2.0) |
| 33 | Claude Sonnet 4.6Claude Sonnet 4.6 (Non-reasoning, High Effort) is … | Anthropic | 200k | 45 | $6.00 | 46.0 | 0.90 | |
| 34 | GPT-5.4 nano (high)GPT-5.4 nano (xhigh) is a leading intelligence mod… | OpenAI | 400k | 44 | $0.46 | 199.0 | 3.23 | |
| 35 | Gemini 3 Pro Preview (low)Gemini 3 Pro Preview (low) is the speed- and cost-… | 1m | 43 | $4.50 | 117.0 | 4.31 | ||
| 36 | Claude 4.5 Sonnet (thinking)Claude Sonnet 4.5 is Anthropic's most advanced Son… | Anthropic | 1m | 42 | $6.00 | 67.0 | 11.50 | (2.0) |
| 37 | DeepSeek V3.2 (reasoning)DeepSeek V3.2 (Reasoning) is the umbrella name for… | DeepSeek | 128k | 42 | $0.32 | 31.0 | 1.20 | |
| 38 | Grok 4.1 Fast (reasoning)Grok 4.1 Fast Reasoning is a high-speed variant op… | xAI | 2m | 38 | $0.28 | 143.0 | 6.86 | |
| 39 | Gemini 3 Flash PreviewGemini 3 Flash Preview (non-reasoning) is one of t… | 1m | 37 | $1.13 | 146.0 | 0.88 | ||
| 40 | OpenAI o3OpenAI o3 is a next-generation language model deve… | OpenAI | 200k | 37 | $3.50 | 98.0 | 14.43 | (3.3) |
| 41 |  Doubao Seed CodeDoubao Seed Code is a proprietary model from ByteD… | ByteDance | 256k | 34 | $0.41 | 38.0 | 2.41 | |
| 42 | Gpt-oss-120B (high)Gpt-oss-120B (high) is one of the leading models i… | OpenAI | 131k | 34 | $0.26 | 298.0 | 0.45 | |
| 43 | Claude 4.5 Haiku (thinking)Claude 4.5 Haiku (Thinking) by Anthropic is one of… | Anthropic | 200k | 33 | $2.00 | 108.0 | 0.61 | |
| 44 | DeepSeek V3.2DeepSeek V3.2 is one of the leading models in term… | DeepSeek | 128k | 33 | $0.32 | 31.0 | 1.17 | |
| 45 | Gpt-oss-20b (high)Gpt-oss-20b is an open language model released by … | OpenAI | 131k | 25 | $0.10 | 120.0 | 0.98 |