AI models compared
584 models with published results from our own benchmarks and licensed sources, strongest first: by our overall score, then the Artificial Analysis Intelligence Index. Open a model for every result, with its source and date. 225 of them are on sale through OpenRouter, with prices on the API pricing page; launches are on the release tracker.
Sorted by Spring Prompt overall, lowest first; models without a value come last. Select a column heading to sort by it.
| Model | Spring Prompt overall | Intelligence Index | Price, blended | Released | Context | Sources |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5Anthropic | 8 | 16.9 | $2.00 | 15 Oct 2025 | 200k | 12 |
| GLM-5V-TurboZ.ai | 10 | 23.5 | $1.90 | 1 Apr 2026 | 202k | 3 |
| Mistral Medium 3.5Mistral AI | 16 | 14.2 | $3.00 | 28 Apr 2026 | 262k | 8 |
| Gemini 3.5 Flash-LiteGoogle | 25 | 22.2 | $0.85 | 21 Jul 2026 | 1,048k | 8 |
| DeepSeek-V4-Pro (0423)DeepSeek · open weights | 31 | 30.4 | $1.77 | 24 Apr 2026 | 1,048k | 10 |
| Mistral Large 4Mistral AI | 33 | 38.4 | $2.06 | 6 Oct 2026 | 524k | 6 |
| GLM-5.3Z.ai · open weights | 36 | 44.8 | $2.15 | 14 Aug 2026 | 1,048k | 7 |
| Mercury 3Inception | 39 | – | $0.33 | 19 Oct 2026 | 1,000k | 4 |
| GPT-6 LunaOpenAI | 40 | 38.1 | $0.20 | 22 Sep 2026 | 1,050k | 9 |
| Claude Haiku 5.5Anthropic | 43 | 43.4 | $0.20 | 7 Oct 2026 | 1,000k | 6 |
| Grok 4.7xAI | 43 | 46.4 | $3.00 | 21 Sep 2026 | 500k | 6 |
| DeepSeek-V4.1-Flash-1017DeepSeek · open weights | 44 | 45.1 | $0.52 | 17 Oct 2026 | 1,048k | 6 |
| Qwen3.8-Max (0902)Alibaba | 46 | 45.4 | $3.00 | 3 Aug 2026 | 1,000k | 8 |
| MiniMax M3.1 FlashMiniMax | 47 | 42.4 | $0.26 | 19 Oct 2026 | 1,048k | 5 |
| Gemini 3.1 Pro PreviewGoogle | 48 | 29.7 | $4.50 | 19 Feb 2026 | 1,048k | 15 |
| Kimi K3Moonshot AI · open weights | 49 | 43.6 | $6.00 | 16 Jul 2026 | 1,048k | 11 |
| DeepSeek-V4.1-FlashDeepSeek · open weights | 53 | 39.5 | $0.52 | 10 Sep 2026 | 1,048k | 3 |
| Gemini 3.8 FlashGoogle | 60 | 40.9 | $3.00 | 2 Sep 2026 | 1,048k | 11 |
| Muse Spark 1.3Meta | 62 | 48.1 | $2.00 | 2 Sep 2026 | 1,048k | 8 |
| Claude Sonnet 5.5Anthropic | 63 | 56.0 | $4.00 | 28 Sep 2026 | 1,000k | 8 |
| Claude Fable 5.1Anthropic | 66 | 53.4 | $20.00 | 1 Sep 2026 | 1,000k | 12 |
| GPT-6 SolOpenAI | 69 | 47.6 | $4.00 | 22 Sep 2026 | 1,050k | 12 |
| Muse WonderMeta | 72 | 52.4 | $8.00 | 12 Oct 2026 | 1,048k | 6 |
| Gemini 4 ArgonGoogle | 76 | 52.6 | $4.00 | 13 Oct 2026 | 1,048k | 7 |
| GPT-6 AstraOpenAI | 78 | 52.7 | $20.00 | 3 Sep 2026 | 1,050k | 12 |
| GPT-6.1 SolOpenAI | 80 | 51.8 | $4.00 | 29 Sep 2026 | 1,050k | 9 |
| Claude Opus 5.5Anthropic | 85 | 57.6 | $8.00 | 22 Sep 2026 | 1,000k | 11 |
| Claude Opus 5Anthropic | – | 50.8 | $10.00 | 24 Jul 2026 | 1,000k | 7 |
| Claude Fable 5Anthropic | – | 49.6 | $20.00 | 9 Jun 2026 | 1,000k | 10 |
| GPT-5.6 SolOpenAI | – | 47.0 | $8.00 | 9 Jul 2026 | 1,050k | 8 |
| MiMo-V2.6-ProXiaomi · open weights | – | 46.3 | $0.54 | 21 Sep 2026 | 1,050k | 2 |
| Grok 4.6xAI | – | 44.3 | $3.00 | 12 Aug 2026 | 500k | 7 |
| GPT-5.6 TerraOpenAI | – | 42.1 | $4.50 | 9 Jul 2026 | 1,050k | 7 |
| Claude Opus 4.8Anthropic | – | 41.8 | $10.00 | 28 May 2026 | 1,000k | 10 |
| GLM-5.3-FlashZ.ai · open weights | – | 41.8 | $0.24 | 20 Aug 2026 | 1,048k | 4 |
| Claude Opus 4.7Anthropic | – | 40.7 | $10.00 | 16 Apr 2026 | 1,000k | 11 |
| Qwen3.8-MaxAlibaba · not on sale | – | 40.2 | – | 3 Aug 2026 | – | 2 |
| Qwen3.8-2.4T-A95BAlibaba · open weights | – | 39.9 | $3.00 | 12 Aug 2026 | 1,048k | 1 |
| Qwen3.8-Flash-NextAlibaba · not on sale | – | 39.8 | – | 26 Aug 2026 | – | 2 |
| Gemini 3.7 FlashGoogle | – | 39.6 | $3.00 | 13 Aug 2026 | 1,048k | 7 |
| Muse Spark 1.2Meta | – | 39.6 | $2.00 | 5 Aug 2026 | 1,048k | 5 |
| GPT-5.4OpenAI | – | 39.0 | $5.62 | 5 Mar 2026 | 1,050k | 10 |
| Muse Spark OpenMeta · not on sale | – | 38.9 | – | 15 Oct 2026 | – | 1 |
| Grok 4.5xAI | – | 38.8 | $3.00 | 8 Jul 2026 | 500k | 8 |
| GPT-5.5OpenAI | – | 38.4 | $11.25 | 23 Apr 2026 | 1,050k | 12 |
| Claude Sonnet 5Anthropic | – | 38.2 | $4.00 | 30 Jun 2026 | 1,000k | 6 |
| MiMo-V2.6-FlashXiaomi · open weights | – | 37.9 | $0.18 | 21 Sep 2026 | 1,050k | 2 |
| GPT-5.6 LunaOpenAI | – | 37.3 | $0.45 | 9 Jul 2026 | 1,050k | 6 |
| DeepSeek-V4-Pro (0813)DeepSeek · open weights | – | 36.0 | $1.98 | 13 Aug 2026 | 1,048k | 4 |
| DeepSeek-V4-Flash-Vision-ExpDeepSeek · open weights | – | 34.8 | $0.66 | 21 Aug 2026 | 1,048k | 1 |
Spring Prompt overall is our score across every source, out of 100 (how it works). The Intelligence Index is Artificial Analysis's, at each model's best setting. Price is the developer's list price, or the typical OpenRouter host, for three input tokens to one output, per million tokens.
Want two models side by side? Compare models.