This is a comparison of generative AI models, such as language models and text-to-image models, across various benchmarks and user-generated Elo ratings. Leading large language models are sometimes called frontier models.

Background Independent evaluation is widely used to compare frontier models because developer-reported scores are hard to compare directly.

Artificial Analysis (AA) runs the Artificial Analysis Intelligence Index v4.3.2 across 10 evaluations including AA-Briefcase, GDPval-AA, AutomationBench-AA and Terminal-Bench 4.0, plus price per 1M tokens and output speed in tokens/s. Its pricing and index data have been cited in coverage reporting DeepSeek V4-Flash as by far the cheapest well-known model to run. Arena.ai, formerly Chatbot Arena from University of California, Berkeley, ranks models by blind human votes into elo-style ratings. It tripled to a $1.7 billion valuation in January 2026 after raising $150 million. Earlier coverage described its spin-out from an academic project into a $600 million startup. Epoch AI publishes the Epoch Capabilities Index (ECI), a composite across 50 plus benchmarks scaled so that Claude 3.5 Sonnet equals 130. GPT-6 Astra set a new record at 166 in September 2026, ahead of Claude Fable 5.1 at 164. Its independence has been scrutinized over delayed disclosure of OpenAI funding for FrontierMath. Vals AI publishes the Vals Index, agentic performance across finance, coding and legal tasks weighted by share of United States GDP, updated 10 September 2026 with 56 models tested.

Language models + Comparison of language models across benchmarks, as of 22 September 2026 Model Developer Origin Release Date License AA Intelligence Index Arena.ai Text Rating Epoch Capability Index Vals Index AA Cost per Task (USD) AA Speed (Median Tokens/s) Claude Fable 5.1 Anthropic September 2026 53 1498 164 68.8 $7.63 66 GPT-6 Astra OpenAI 3 September 2026 53 1479 166 66.6 $3.26 67 Claude Opus 5 Anthropic 24 July 2026 51 1492 162 67.2 $5.86 56 Claude Fable 5 Anthropic 9 June 2026 50 1506 163 66.0 $8.75 68 Muse Spark 1.3 Meta Platforms September 2026 48 1493 n/a 64.5 $1.60 223 GPT-5.6 Sol OpenAI 9 July 2026 47 1483 161 63.7 $1.99 79 Grok 4.7 xAI September 2026 46 n/a n/a n/a $3.74 39 MiMo-V2.6-Pro Xiaomi 21 September 2026 46 n/a n/a n/a $0.13 130 Qwen3.8 Max 0902 Alibaba Cloud 2 September 2026 45 1481 156 51.8 $5.41 39 GLM-5.3 Zhipu AI August 2026 45 n/a 155 57.0 $2.01 57 Grok 4.6 xAI 12 August 2026 44 1456 156 59.2 $1.86 60 Step 5 Preview StepFun August 2026 44 n/a n/a n/a $0.71 92 Kimi K3 Moonshot AI 16 July 2026 44 1485 157 57.8 $2.00 43 GPT-5.6 Terra OpenAI 9 July 2026 42 1466 159 59.6 $1.40 107 GLM-5.3-Flash Zhipu AI August 2026 42 n/a 151 47.2 $0.25 89 Claude Opus 4.8 Anthropic 28 May 2026 42 n/a 158 n/a $4.08 57 Gemini 3.8 Flash Google DeepMind September 2026 41 1493 156 62.3 $1.24 329 Claude Opus 4.7 Anthropic 16 April 2026 41 1502 156 n/a n/a 50 Qwen3.8 2.4T A95B Alibaba Cloud September 2026 40 n/a 156 n/a $2.16 39 Qwen3.8-Flash-Next Alibaba Cloud September 2026 40 n/a n/a n/a $0.37 54 Gemini 3.7 Flash Google DeepMind 13 August 2026 39 1490 157 59.3 $0.93 318 DeepSeek V4.1 Flash DeepSeek August 2026 39 n/a n/a 57.9 $0.27 219 GPT-5.4 OpenAI 5 March 2026 39 1476 156 n/a n/a 142 Grok 4.5 xAI 8 July 2026 39 1468 153 n/a $1.04 61 Claude Sonnet 5 Anthropic 30 June 2026 38 1461 156 59.6 $5.09 77 GPT-5.5 OpenAI 23 April 2026 38 1482 159 57.4 $2.63 108 GPT-5.6 Luna OpenAI 9 July 2026 37 1452 156 59.9 $0.18 159 DeepSeek V4 Pro 0813 DeepSeek 13 August 2026 36 1463 155 52.4 $0.67 97 Agnes 3.0 Flash Sapiens AI 2026 36* n/a n/a n/a n/a n/a Agnes 2.5 Pro Beta Sapiens AI 2026 35* n/a n/a n/a n/a n/a DeepSeek V4 Flash Vision DeepSeek August 2026 35 n/a n/a n/a $0.31 235 Qwen3.8 27B Alibaba Cloud September 2026 34 n/a n/a 48.5 $0.82 45 GLM-5.2 Zhipu AI 16 June 2026 34 n/a 151 53.1 $0.96 71 Gemini 3.6 Flash Google DeepMind 21 July 2026 34 1480 154 n/a $0.93 209 Motif 3 Motif Technologies 14 July 2026 34* n/a n/a n/a n/a n/a GPT-5.3 Codex OpenAI 5 February 2026 33* n/a 156 n/a n/a 170 K2 Horizon 375B A23B Institute of Foundation Models August 2026 31 n/a n/a n/a n/a n/a Apodex 1.1 Apodex August 2026 30* n/a n/a n/a n/a n/a Gemini 3.1 Pro Preview Google DeepMind 19 February 2026 30 1487 155 41.9 $0.67 115 Qwen3.7 Max Alibaba Cloud 19 May 2026 29 1473 n/a n/a $1.15 197 Text-to-image models + Comparison of text-to-image models, as of 20 September 2026 Model Developer Origin Release Date AA Elo Arena Elo API Price per 1k Images (USD) License GPT Image 2.5 Sunburst OpenAI September 2026 1182 1421 $210.70 GPT Image 2.5 Flare OpenAI September 2026 1188 1399 $210.70 GPT Image 2 OpenAI April 2026 1171 1381 $211.00 MAI-Image-2.6 Microsoft AI August 2026 1147 1331 $38.90 Grok Imagine Image 2.0 xAI August 2026 1154 1315 $60.00 Reve 2.1 Reve July 2026 1129 1301 $200.00 Muse Image Meta Platforms July 2026 1111 1277 $10.00 Nano Banana 2 Google DeepMind February 2026 1122 1261 $67.00 Seedream 5.0 Pro ByteDance 2026 1078 1257 $90.00 Qwen-Image-3.0-Pro Alibaba Cloud July 2026 1088 1254 $40.00 MAI-Image-2.5 Microsoft AI June 2026 1102 1254 $48.10 Nano Banana 2 Lite Google DeepMind June 2026 1091 1250 $33.60 Nano Banana Pro Google DeepMind November 2025 1100 1246 $134.00 GPT Image 1.5 OpenAI December 2025 1102 1239 $133.00 Ideogram 4.0 Quality Ideogram June 2026 1012 1204 $60.00 Luma UNI Max Luma AI 2026 1012 1188 n/a MAI-Image-2 Microsoft AI 2026 1009 1183 n/a Grok Imagine Image xAI 2026 1018 1171 n/a Recraft V4.1 Utility Pro Recraft 2026 1017 1169 $210.00 Cosmos3-Super-Text2Image Nvidia May 2026 983 1167 n/a

See also List of large language models Text-to-image model Arena.ai

Notes

References

External links Artificial Analysis Epoch AI Vals AI Arena.ai