Artificial Analysis index
Ranked by the Artificial Analysis Intelligence Index, as published via OpenRouter. Covers many new models before Epoch evaluates them.
Ranked by the Artificial Analysis Intelligence Index, as published via OpenRouter. Covers many new models before Epoch evaluates them. Source: Artificial Analysis (via OpenRouter). Variants (reasoning effort, batch) are folded into one row.
| # | Model | Capability | Reasoning | Coding | Context | $/M | Weights | Released |
|---|---|---|---|---|---|---|---|---|
| 1 | Claude Opus 5.5NEWAnthropic · +1 variant | — | — | — | 1M | $8.00 | — | 22 Sep 2026 |
| 2 | Claude Sonnet 5.5NEWAnthropic · +1 variant | — | — | — | 1M | $4.00 | — | 28 Sep 2026 |
| 3 | Claude Fable 5.1NEWAnthropic · +1 variant | 165.0 | — | — | 1M | $20.00 | Closed | 1 Sep 2026 |
| 4 | GPT-6 AstraNEWbatchOpenAI · +1 variant | — | — | — | 1.05M | $10.00 | — | 4 Sep 2026 |
| 5 | Claude Opus 5Anthropic · +1 variant | 162.7 | 93.9 | 73.6 | 1M | $10.00 | Closed | 24 Jul 2026 |
| 6 | GPT-6 SolNEWOpenAI · +1 variant | — | — | — | 1.05M | $4.00 | — | 22 Sep 2026 |
| 7 | GPT-5.6 SolOpenAI · +1 variant | 162.0 | 93.5 | 72.7 | 1.05M | $4.00 | Closed | 9 Jul 2026 |
| 8 | Grok 4.7NEWxAI | — | — | — | 500K | $3.00 | — | 21 Sep 2026 |
| 9 | MiMo-V2.6-ProNEWXiaomi | — | — | — | 1.05M | $0.54 | Open | 21 Sep 2026 |
| 10 | Qwen3.8 Max (0902)NEWAlibaba (Qwen) | 155.3 | — | — | 1M | $3.00 | Closed | 1 Sep 2026 |
| 11 | GLM 5.3batchZ.ai (Zhipu AI) · +1 variant | — | — | — | 1.05M | $0.84 | Open | 18 Aug 2026 |
| 12 | Grok 4.6xAI | 156.5 | 94.0 | 65.2 | 500K | $3.00 | Closed | 12 Aug 2026 |
| 13 | Kimi K3Moonshot AI · +1 variant | 157.7 | 93.1 | 68.5 | 1.05M | $6.00 | Open | 16 Jul 2026 |
| 14 | GPT-5.6 TerraOpenAI · +1 variant | 159.3 | 93.3 | 69.6 | 1.05M | $4.50 | Closed | 9 Jul 2026 |
| 15 | GLM 5.3 FlashbatchZ.ai (Zhipu AI) · +1 variant | — | — | — | 1.05M | $0.095 | Open | 26 Aug 2026 |
| 16 | Gemini 3.8 FlashNEWGoogle · +1 variant | 157.1 | 95.4 | 73.8 | 1.05M | $1.50 | Closed | 2 Sep 2026 |
| 17 | Qwen3.8 2.4T A95BAlibaba (Qwen) | — | — | — | 1.05M | $3.00 | Open | 12 Aug 2026 |
| 18 | Muse Spark 1.2Meta | 155.2 | — | — | 1.05M | $2.00 | Closed | 5 Aug 2026 |
| 19 | DeepSeek V4.1 FlashNEWbatchDeepSeek · +1 variant | — | — | — | 1.05M | $0.17 | Open | 10 Sep 2026 |
| 20 | Gemini 3.7 FlashGoogle · +1 variant | 157.7 | 94.8 | 65.3 | 1.05M | $1.50 | Closed | 13 Aug 2026 |
| 21 | Grok 4.5xAI | 154.0 | 93.4 | 53.8 | 500K | $3.00 | Closed | 8 Jul 2026 |
| 22 | MiMo-V2.6-FlashNEWXiaomi | — | — | — | 1.05M | $0.17 | Open | 21 Sep 2026 |
| 23 | GPT-5.6 LunaOpenAI · +1 variant | 156.3 | 91.6 | 67.2 | 1.05M | $0.45 | Closed | 9 Jul 2026 |
| 24 | GPT-6 LunaNEWOpenAI · +1 variant | — | — | — | 1.05M | $0.20 | — | 22 Sep 2026 |
| 25 | DeepSeek V4 Pro 0813DeepSeek | 155.4 | 91.7 | — | 1.05M | $1.41 | Open | 13 Aug 2026 |
| 26 | DeepSeek V4 Flash 0731DeepSeek | 154.5 | 91.0 | — | 1.31M | $0.093 | Open | 31 Jul 2026 |
| 27 | Gemini 3.6 FlashGoogle · +1 variant | 154.4 | 94.1 | 46.7 | 1.05M | $1.50 | Closed | 21 Jul 2026 |
| 28 | Muse Spark 1.1Meta | 154.3 | — | 53.3 | 1.05M | $2.00 | Closed | 9 Jul 2026 |
| 29 | Qwen3.8 27BAlibaba (Qwen) | — | — | — | 1M | $1.14 | Open | 14 Aug 2026 |
| 30 | InklingThinking Machines Lab | 148.6 | — | — | 524K | $1.76 | Open | 15 Jul 2026 |
| 31 | Ling 3.0 Flash VLNEWinclusionAI (Ant Group) | — | — | — | 262K | $0.031 | Open | 10 Sep 2026 |
| 32 | Ling 3.0 Flash FininclusionAI (Ant Group) | — | — | — | 262K | $0.090 | — | 27 Aug 2026 |
| 33 | Gemini 3.5 Flash LiteGoogle · +1 variant | 145.1 | 83.3 | — | 1.05M | $0.85 | Closed | 21 Jul 2026 |
| 34 | LongCat 2.0Meituan | — | — | — | 1.05M | $0.53 | Open | 20 Jul 2026 |
| 35 | Nemotron 3.5 LightningNVIDIA | — | — | — | 1M | $0.085 | Open | 11 Aug 2026 |
| 36 | Mercury 2.5NEWInception Labs | — | — | — | 260K | $0.068 | — | 8 Sep 2026 |
| 37 | Granite 4.2 8BNEWIBM | — | — | — | 131K | $0.11 | Open | 31 Aug 2026 |
— means no published score from that source yet · click a model for every benchmark with its source
New - awaiting independent evaluation
All new models →- Claude Sonnet 5.5Anthropic · 28 Sep 2026 · AA 56 · 1M · $4.00/M
- Qwen3.8 Max PrimeAlibaba (Qwen) · 23 Sep 2026 · 1M · $6.00/M
- GPT-6 SolOpenAI · 22 Sep 2026 · AA 47.5 · 1.05M · $4.00/M
- GPT-6 LunaOpenAI · 22 Sep 2026 · AA 37.3 · 1.05M · $0.20/M
- GPT-6 Sol ProOpenAI · 22 Sep 2026 · 1.05M · $4.00/M
- GPT-6 Luna ProOpenAI · 22 Sep 2026 · 1.05M · $0.20/M
- Claude Opus 5.5Anthropic · 22 Sep 2026 · AA 57.6 · 1M · $8.00/M
- Grok 4.7xAI · 21 Sep 2026 · AA 46.4 · 500K · $3.00/M
Not ranked until an independent evaluator (Epoch AI) publishes scores. We don't use vendor-reported benchmark claims for rankings.
Best AI for coding →
Models ranked on DeepSWE
Best AI for reasoning →
Ranked on GPQA Diamond
Best AI for math →
Ranked on competition math
Best open-weight models →
Weights you can run yourself
Cheapest capable models →
Lowest blended API price
Best AI coding tools →
Apps & agents by popularity
Best AI image generators →
Apps & models
Best AI for research →
Answer engines & deep research