Skip to content
OneAtlas

Benchmarks

Published scores for every model, side by side. The best score in each column is highlighted.

208
indexed
128
in design arena
31
benchmarks

1,123 models

Benchmark scores
Claude Opus 5.5Anthropic57.6 (highest)——136413251386 (highest)1438 (highest)13771396 (highest)1468 (highest)1322—$8.0036
Claude Sonnet 5.5Anthropic56.0——1343132113531414137513871401——$4.0034
Kimi K3.1 ProMoonshot AI55.1——1366 (highest)1326135314071397 (highest)130514481327 (highest)—$8.0017
Claude Fable 5.1Anthropic53.481.6 (highest)57.9 (highest)133813121335138113331344139012961321$20.0037
GPT-6 AstraOpenAI52.776.951.0—————————$20.0037
Gemini 4 ArgonGoogle52.6——13351316133013691333133113851322—$4.0025
GPT-6.1 SolOpenAI51.8——1334131513581408133912921436——$4.0033
Claude Opus 5Anthropic50.878.056.5128813091323133813451330133213061358 (highest)$10.0042
Claude Fable 5Anthropic49.676.550.7128112941308133513131304131612981326$20.0046
GPT-6.1 TerraOpenAI48.1———————————$2.0016
Muse Spark 1.3Meta48.175.855.512851355 (highest)1350134313451342139313171278$2.0018
GPT-6 SolOpenAI47.6———————————$4.0034
GPT-5.6 SolOpenAI47.077.450.2—————————$8.0049
Grok 4.7xAI46.4——1269125312711313127412321273——$3.0028
MiMo-V2.6-ProXiaomi46.3——1318130613161315133313361333——$0.5424
Qwen3.8 Max 0902Alibaba45.476.256.0—————————$2.579
GLM-5.3Zhipu AI44.874.853.1126212921300130713061263132912871205$1.9491
Grok 4.6xAI44.376.853.0125012871290129412901282127312361279$3.0033
Step 5 PreviewStepFun (China)43.7———————————$1.5318
Kimi K3Moonshot AI43.676.250.012771335135913621338135013851300—$6.0083
Claude Haiku 5.5Anthropic43.4——1296126112801323127712911344——$0.2034
MiniMax-M3.1-FlashMiniMax42.7———————————$0.2626
GPT-5.6 TerraOpenAI42.176.743.2—————————$4.5045
GLM-5.3-FlashZhipu AI41.871.550.9128312701279127613091261131412801271$0.4984
Claude Opus 4.8Anthropic41.874.341.9124012571253126312531239122011921275$10.0050
Ling 3.1 FlashinclusionAI41.1———————————$0.456
Gemini 3.8 FlashGoogle40.976.340.2124012991302130413141271129312911267$1.5032
Claude Opus 4.7Anthropic40.773.638.6—————————$10.0048
Qwen3.8 2.4T A95BAlibaba39.971.950.1—————————$3.4423
Gemini 3.7 FlashGoogle39.671.5—125213021306131812931316130612791277$1.5030
Muse Spark 1.2Meta39.672.243.2121913111311130112961333130012791280$2.0018
DeepSeek V4.1 Flash 1017DeepSeek39.5——128112981289126413001278136212411220$0.2639
GPT-5.4OpenAI39.071.1—115012181210123712341235109711911196$5.6347
Grok 4.5xAI38.872.441.2122112791273126212751266125512091257$3.0027
Mistral Large 4Mistral38.4——124612561258122612691275124812291206$2.0613
GPT-5.5OpenAI38.474.936.4117012551258129112541262119512301253$11.2551
Claude Sonnet 5Anthropic38.271.543.6121212731274127412731251125811881205$4.0044
GPT-6 LunaOpenAI38.1———————————$0.2036
MiMo-V2.6-FlashXiaomi37.9———————————$0.1826
GPT-5.6 LunaOpenAI37.371.442.1—————————$0.4548