模型能力与价格
按来源比较能力与价格,保留配置、单位和真实核对日期。
Artificial Analysis
来源日期:来源未标注 · 核对:2026-10-26
原始来源| 模型/配置 | Intelligence Index v4.3 | 每项评测任务成本(美元) |
|---|---|---|
| Claude Opus 5.5 (max with fallback) Claude Opus 5.5 (Max, Default Fallback) | 57.6223698102963 | 5.982012019521066 |
| Claude Sonnet 5.5 (max with fallback) Claude Sonnet 5.5 (Max, Default Fallback) | 56.0001286580794 | 5.4608525948098325 |
| Claude Opus 5.5 (xhigh with fallback) Claude Opus 5.5 (Xhigh, Default Fallback) | 55.9873505840139 | 3.459110175822289 |
| Kimi K3.1 Pro Kimi K3.1 Pro | 55.0869210959395 | 2.1145052918767275 |
| Claude Opus 5.5 (high with fallback) Claude Opus 5.5 (High, Default Fallback) | 53.5831959822067 | 1.822504718771704 |
| Claude Fable 5.1 (max with fallback) Claude Fable 5.1 (Max, Default Fallback) | 53.3549259623252 | 7.629706364004841 |
| Claude Fable 5.1 (xhigh with fallback) Claude Fable 5.1 (Xhigh, Default Fallback) | 53.2032587538944 | 5.978304247388257 |
| GPT-6 Astra (max) GPT-6 Astra (Max) | 52.673669395513 | 3.2575003134834164 |
| Gemini 4 Argon (high) Gemini 4 Argon (High) | 52.5605655745982 | 1.990322379299008 |
| Muse Wonder (max) Muse Wonder (Max) | 52.393894697293 | 4.540034681803926 |
| GPT-6 Astra (xhigh) GPT-6 Astra (Xhigh) | 52.3863277108782 | 2.308795912269076 |
| Claude Sonnet 5.5 (xhigh with fallback) Claude Sonnet 5.5 (Xhigh, Default Fallback) | 51.8955544183089 | 2.0120345801545785 |
| GPT-6.1 Sol (max) GPT-6.1 Sol (Max) | 51.8332597011541 | 0.7241670655535033 |
| Claude Opus 5.5 (medium with fallback) Claude Opus 5.5 (Medium, Default Fallback) | 51.2434931792768 | 1.3360093438976588 |
| Claude Fable 5.1 (high with fallback) Claude Fable 5.1 (High, Default Fallback) | 51.1515708852237 | 3.912526554325558 |
| GPT-6.1 Sol (xhigh) GPT-6.1 Sol (Xhigh) | 51.0377679093761 | 0.39286117158850653 |
| GPT-6 Astra (high) GPT-6 Astra (High) | 50.9191471636152 | 1.7252530861048456 |
| Claude Opus 5 (max) Claude Opus 5 (Max) | 50.7771115797629 | 5.858396237036018 |
| GPT-6.1 Sol (high) GPT-6.1 Sol (High) | 50.2377777519769 | 0.31914442375664703 |
| Claude Opus 5 (xhigh) Claude Opus 5 (Xhigh) | 49.6773552926939 | 4.877843772646787 |
| Claude Fable 5 (with fallback) Claude Fable 5 (Max, Opus 4.8 Fallback) | 49.6258202733378 | 8.745961651687406 |
| GPT-6 Astra (medium) GPT-6 Astra (Medium) | 49.5704363034369 | 1.5406493220021167 |
| Claude Fable 5.1 (medium with fallback) Claude Fable 5.1 (Medium, Default Fallback) | 48.9206162609523 | 2.982597436096585 |
| Claude Opus 5 (high) Claude Opus 5 (High) | 48.1219182595908 | 3.6132670078004714 |
| Muse Spark 1.3 (max) Muse Spark 1.3 (Max) | 48.0923107719685 | 1.6048932100125866 |
| GPT-6.1 Sol (medium) GPT-6.1 Sol (Medium) | 47.7833271274065 | 0.21370088267875537 |
| GPT-6 Sol (max) GPT-6 Sol (Max) | 47.6305176437724 | 1.0446616686054255 |
| GPT-5.6 Sol (max) GPT-5.6 Sol (Max) | 46.9727068915036 | 1.98845538085375 |
| Claude Fable 5.1 (low with fallback) Claude Fable 5.1 (Low, Default Fallback) | 46.8163422014862 | 2.371025320183763 |
| Claude Sonnet 5.5 (high with fallback) Claude Sonnet 5.5 (High, Default Fallback) | 46.7533528066958 | 0.8844498581005511 |
| Grok 4.7 (xhigh) Grok 4.7 (Xhigh) | 46.4465506302286 | 3.738325952106939 |
| Grok 4.7 (high) Grok 4.7 (High) | 46.3321770885625 | 2.726106691786027 |
| MiMo-V2.6-Pro MiMo-V2.6-Pro | 46.3242065310383 | 0.13322318937213493 |
| GPT-6 Astra (low) GPT-6 Astra (Low) | 45.7819243120341 | 0.8175139285656057 |
| Qwen3.8 Max (0902) Qwen3.8 Max (0902) | 45.4152084980521 | 5.408509428374016 |
| DeepSeek V4.1 Flash 1017 (max) DeepSeek V4.1 Flash 1017 (Max) | 45.0965048681912 | 0.2620484273114172 |
| Muse Spark 1.3 (xhigh) Muse Spark 1.3 (Xhigh) | 45.0732966922226 | 1.3677936514692752 |
| Claude Opus 5 (medium) Claude Opus 5 (Medium) | 44.8253265420613 | 2.1894793086538695 |
| GLM-5.3 (max) GLM-5.3 (Max) | 44.777392385614 | 2.0056375150449584 |
| Grok 4.6 (high) Grok 4.6 (High) | 44.3113073012592 | 1.4848449196688633 |
| GPT-6 Sol (xhigh) GPT-6 Sol (Xhigh) | 44.2448955516407 | 0.5208098524368193 |
| Grok 4.6 (xhigh) Grok 4.6 (Xhigh) | 44.199810436996 | 1.7523145158282367 |
| GPT-5.6 Sol (xhigh) GPT-5.6 Sol (Xhigh) | 44.008876369169 | 1.1843629381907275 |
| Ling 3.1 Flash 1019 Ling 3.1 Flash 1019 | 43.8973584978265 | 1.4886425967752979 |
| Step 5 Preview Step 5 Preview | 43.7343049141614 | 1.0264068637684054 |
| Kimi K3 (max) Kimi K3 (Max) | 43.5938229518782 | 2.0001323004425493 |
| Claude Haiku 5.5 (max) Claude Haiku 5.5 (Max) | 43.3950199670746 | 0.21276971216992022 |
| Grok 4.6 (medium) Grok 4.6 (Medium) | 42.836322654063 | 1.14381661681713 |
| MiniMax-M3.1-Flash MiniMax-M3.1-Flash | 42.7057475126235 | 0.2201135746720313 |
| GPT-6 Sol (high) GPT-6 Sol (High) | 42.4004513642985 | 0.3728406839161857 |
| GPT-5.6 Sol (high) GPT-5.6 Sol (High) | 42.3461010420519 | 0.807982690134498 |
| Claude Opus 5.5 (low with fallback) Claude Opus 5.5 (Low, Default Fallback) | 42.3077781466168 | 0.551180473909146 |
| Grok 4.7 (low) Grok 4.7 (Low) | 42.2166560223448 | 1.2479664056943975 |
| GPT-6.1 Sol (low) GPT-6.1 Sol (Low) | 42.0835618555848 | 0.13075190869859377 |
| GPT-5.6 Terra (max) GPT-5.6 Terra (Max) | 42.0829248239494 | 1.3987235612691513 |
| GLM-5.3-Flash GLM-5.3-Flash | 41.807466113455 | 0.2835948232103717 |
| Claude Opus 4.8 (max) Claude Opus 4.8 (Max) | 41.7899103794639 | 4.080976976477826 |
| Claude Haiku 5.5 (xhigh) Claude Haiku 5.5 (Xhigh) | 41.2489304677024 | 0.12378561092096102 |
| Ling 3.1 Flash Ling 3.1 Flash | 41.0906200397391 | 1.010607821950605 |
| Gemini 3.8 Flash (high) Gemini 3.8 Flash (High) | 40.9262321765904 | 1.2427947606950427 |
| Claude Sonnet 5.5 (medium with fallback) Claude Sonnet 5.5 (Medium, Default Fallback) | 40.838652287929 | 0.48326378260543096 |
| Qwen3.8 Max Qwen3.8 Max | 40.1528623585941 | 2.6699848505343478 |
| Qwen3.8 2.4T A95B Qwen3.8 2.4T A95B | 39.9461723105325 | 2.1551619442434675 |
| Qwen3.8-Flash-Next Qwen3.8-Flash-Next | 39.8223021864741 | 0.3721760025302965 |
| GPT-6 Sol (medium) GPT-6 Sol (Medium) | 39.8118971749522 | 0.24728577052042386 |
| Gemini 3.8 Flash (medium) Gemini 3.8 Flash (Medium) | 39.7740187061926 | 0.9310379374376306 |
| Muse Spark 1.2 (xhigh) Muse Spark 1.2 (Xhigh) | 39.5758607970943 | 0.9746948879931989 |
| DeepSeek V4.1 Flash (max) DeepSeek V4.1 Flash (Max) | 39.456167472527 | 0.48023810410688067 |
| Claude Opus 5 (low) Claude Opus 5 (Low) | 39.3543357992936 | 1.098302324514437 |
| GPT-5.6 Sol (medium) GPT-5.6 Sol (Medium) | 39.2363585889147 | 0.5049926304382959 |
| Muse Spark Open (xhigh) Muse Spark Open (Xhigh) | 38.8666662997805 | 0.8441853713458678 |
| Grok 4.5 (high) Grok 4.5 (High) | 38.8121153240657 | 0.8806608417078763 |
| Mistral Large 4 Preview Mistral Large 4 Preview | 38.3770408917494 | 1.1344391582388638 |
| GPT-5.5 (xhigh) GPT-5.5 (Xhigh) | 38.3556437590607 | 2.6339796841243297 |
| Claude Sonnet 5 (max) Claude Sonnet 5 (Max) | 38.1638712882576 | 5.091163584815694 |
| GPT-6 Luna (max) GPT-6 Luna (Max) | 38.1245186869738 | 0.06782295669812205 |
| GPT-5.6 Terra (xhigh) GPT-5.6 Terra (Xhigh) | 37.9513370742927 | 0.6317911346924275 |
| MiMo-V2.6-Flash MiMo-V2.6-Flash | 37.8843590141754 | 0.06237567475410205 |
| Claude Haiku 5.5 (high) Claude Haiku 5.5 (High) | 37.8240211671094 | 0.07942671568737021 |
| GPT-5.6 Luna (max) GPT-5.6 Luna (Max) | 37.3244239690841 | 0.17829726152289094 |
| GPT-5.5 (high) GPT-5.5 (High) | 36.9793737887731 | 1.541289049705234 |
| DeepSeek V4 Pro 0813 (max) DeepSeek V4 Pro 0813 (Max) | 35.9967791278402 | 0.6740219040435134 |
| Claude Sonnet 5.5 (low with fallback) Claude Sonnet 5.5 (Low, Default Fallback) | 35.8681594577587 | 0.3451610270666562 |
| Grok 4.6 (low) Grok 4.6 (Low) | 35.1246953482174 | 0.37578773607022314 |
| DeepSeek V4 Flash Vision (max) DeepSeek V4 Flash Vision (Max) | 34.8390628035969 | 1.037910627432751 |
| GPT-6 Luna (xhigh) GPT-6 Luna (Xhigh) | 34.5587320217785 | 0.042183547923951084 |
| GPT-5.6 Luna (xhigh) GPT-5.6 Luna (Xhigh) | 34.555348822309 | 0.085342806135728 |
| Claude Haiku 5.5 (medium) Claude Haiku 5.5 (Medium) | 34.4646519474657 | 0.04703084793955566 |
| Claude Sonnet 5 (xhigh) Claude Sonnet 5 (Xhigh) | 34.384211557212 | 2.8720437784323134 |
| DeepSeek V4 Flash 0731 (max) DeepSeek V4 Flash 0731 (Max) | 34.3305129347816 | 0.14869446586378726 |
| GLM-5.3 (low) GLM-5.3 (Low) | 34.2990078159643 | 0.8522174973386498 |
| GPT-5.6 Terra (high) GPT-5.6 Terra (High) | 34.2376558067555 | 0.3378727947949101 |
| GPT-6 Sol (low) GPT-6 Sol (Low) | 34.1548755585733 | 0.1327768361714764 |
| Gemini 3.6 Flash (high) Gemini 3.6 Flash (High) | 33.9785928920714 | 1.600530533263267 |
| GPT-5.5 (medium) GPT-5.5 (Medium) | 33.8043604432432 | 0.9016588021523384 |
| Muse Spark 1.1 (xhigh) Muse Spark 1.1 (Xhigh) | 33.7298425919846 | 1.3802453886670354 |
| GLM-5.2 (max) GLM-5.2 (Max) | 33.7054572377545 | 1.4726179494034382 |
| Qwen3.8 27B (xhigh) Qwen3.8 27B (Xhigh) | 33.6762858057476 | 1.0074896941565943 |
| GPT-5.6 Sol (low) GPT-5.6 Sol (Low) | 33.4731387646002 | 0.2606419442090313 |
| GPT-6 Luna (high) GPT-6 Luna (High) | 32.9282054150837 | 0.02903157640372802 |
| Gemini 3.5 Flash (high) Gemini 3.5 Flash (High) | 32.5983283695905 | 3.6936902127611133 |
| GPT-5.6 Luna (high) GPT-5.6 Luna (High) | 32.1196453501091 | 0.043981552251920096 |
| Claude Sonnet 5 (high) Claude Sonnet 5 (High) | 31.6623246664651 | 1.7924692244111728 |
| DeepSeek V4 Pro (max) DeepSeek V4 Pro 0424 (Max) | 30.4496601315524 | 0.12152059767597723 |
| Beam 1.0 Beam 1.0 | 30.3334426348039 | 0.22624169286047544 |
| GPT-5.6 Terra (medium) GPT-5.6 Terra (Medium) | 30.0938023419377 | 0.18337295992969213 |
| Kimi K3 (low) Kimi K3 (Low) | 30.0666987529068 | 1.1463056165227514 |
| Claude Sonnet 4.6 (max) Claude Sonnet 4.6 (Max) | 30.0575611117644 | 2.4858655963942224 |
| GPT-6 Luna (medium) GPT-6 Luna (Medium) | 29.9251773515762 | 0.017476906067835942 |
| Gemini 3.1 Pro Preview Gemini 3.1 Pro Preview | 29.7185656132261 | 1.2985855086120641 |
| Qwen3.7 Max Qwen3.7 Max | 29.4571634255623 | 1.1472961597972207 |
| Claude Haiku 5.5 (low) Claude Haiku 5.5 (Low) | 29.4523685891139 | 0.02445936101890973 |
| MiniMax-M3 MiniMax-M3 | 29.2202932236316 | 0.5076126905781733 |
| GPT-6 Sol (non-reasoning) GPT-6 Sol (Non-reasoning) | 28.5121413410513 | 0.33365590023828273 |
| Claude Sonnet 5 (medium) Claude Sonnet 5 (Medium) | 28.0531468379456 | 0.9991061406688175 |
| Qwen3.8 27B (medium) Qwen3.8 27B (Medium) | 27.5508228231586 | 1.133063774030521 |
| GPT-5.6 Terra (low) GPT-5.6 Terra (Low) | 27.496203401716 | 0.1444617614290821 |
| Kimi K2.6 Kimi K2.6 (Reasoning) | 26.9791999742844 | 0.799769615295709 |
| Solar Pro 4 Solar Pro 4 | 26.5600314812231 | 0.7113065897513132 |
| Nemotron 3.5 Super VL Nemotron 3.5 Super VL | 26.4910658661689 | 0.18823665957318256 |
| Apodex 1.1 Apodex 1.1 | 26.4103686249117 | 0.4637245706928438 |
| Qwen3.8 27B (low) Qwen3.8 27B (Low) | 26.2047978189896 | 1.0482225365160391 |
| GLM-5.1 GLM-5.1 (Reasoning) | 26.0585912980095 | 1.0192564984972659 |
| GPT-5.5 Instant (June 2026) GPT-5.5 Instant (June 2026) | 26.0135173401368 | 0.6914853678439488 |
| MiMo-V2.5-Pro MiMo-V2.5-Pro (Reasoning) | 25.9868888896511 | 0.13967150869386885 |
| Kimi K2.7 Code Kimi K2.7 Code | 25.8121062401836 | 0.541190247118529 |
| Inkling Small Inkling Small | 25.6582584411942 | 0.0894649973284348 |
| Hy3 Hy3 | 25.2972775731571 | 0.07179763081859954 |
| Qwen3.7 Plus Qwen3.7 Plus | 25.1622215821984 | 0.21702592259078568 |
| GPT-5.6 Luna (medium) GPT-5.6 Luna (Medium) | 25.0358741440784 | 0.015598049609820011 |
| Grok 4.3 (high) Grok 4.3 (High) | 24.8801191398002 | 0.20537871205068303 |
| DeepSeek V4.1 Flash (non-reasoning) DeepSeek V4.1 Flash (Non-reasoning) | 24.6733593924318 | 0.2488243348377231 |
| DeepSeek V4 Flash (high) DeepSeek V4 Flash 0420 (High) | 24.3839569152521 | 0.10256688240478459 |
| Claude Sonnet 5 (low) Claude Sonnet 5 (Low) | 24.2638393579597 | 0.5087545600633299 |
| DeepSeek V4 Flash (max) DeepSeek V4 Flash 0420 (Max) | 24.1673138235549 | 0.08953612525522162 |
| GPT-5.4 mini (xhigh) GPT-5.4 mini (Xhigh) | 24.0682169231964 | 0.4473810333705224 |
| Solar Mini 4 Solar Mini 4 | 24.0522018844171 | 0.3655852120863359 |
| Nemotron 3 Ultra Nemotron 3 Ultra 550B A55B (Reasoning) | 22.9279123422858 | 0.4696973787770703 |
| Gemini 3.5 Flash-Lite Gemini 3.5 Flash-Lite | 22.1685424839812 | 0.1927430131409478 |
| MiMo-V2.5 MiMo-V2.5 | 21.8248678794953 | 0.03798098899738771 |
| GPT-6 Luna (low) GPT-6 Luna (Low) | 21.5261980080866 | 0.004516607569410252 |
| Qwen3.6 27B Qwen3.6 27B (Reasoning) | 21.4279902240782 | 0.621236893699357 |
| GPT-5.6 Luna (low) GPT-5.6 Luna (Low) | 21.0124783424265 | 0.009827249754655997 |
| GPT-5.6 Terra (non-reasoning) GPT-5.6 Terra (Non-reasoning) | 20.7797013584503 | 0.13972397093498629 |
| GPT-5.4 nano (xhigh) GPT-5.4 nano (Xhigh) | 20.7197352504557 | 0.1830802502922872 |
| DeepSeek V4 Pro 0813 (non-reasoning) DeepSeek V4 Pro 0813 (Non-reasoning) | 20.3605101726847 | 0.35547065335335964 |
| Qwen3.8 27B (non-reasoning) Qwen3.8 27B (Non-reasoning) | 20.1502427055595 | 2.487757391889078 |
| LongCat 2.0 LongCat 2.0 | 19.1123256610623 | 0.14624850952440743 |
| GPT-6 Luna (non-reasoning) GPT-6 Luna (Non-reasoning) | 18.4678465935701 | 0.011345057120527267 |
| Qwen3.5 397B A17B Qwen3.5 397B A17B (Reasoning) | 18.4204249294815 | 0.47457695829894075 |
| Qwen3.6 35B A3B Qwen3.6 35B A3B (Reasoning) | 18.2289900189843 | 0.4750534562511306 |
| Muse Glimmer (high) Muse Glimmer (High) | 17.4754176089465 | 0.05755125039078422 |
| Ring-2.6-1T Ring-2.6-1T | 16.6172363768618 | 0.2871573189066596 |
| Qwen3.5 122B A10B Qwen3.5 122B A10B (Reasoning) | 15.5694009312969 | 0.3247468637357143 |
| Gemini 3.1 Flash-Lite Gemini 3.1 Flash-Lite | 15.554288713025 | 0.06018072627659897 |
| GPT-5.6 Luna (non-reasoning) GPT-5.6 Luna (Non-reasoning) | 15.5270002110259 | 0.010091821810180262 |
| Mistral Medium 3.5 Mistral Medium 3.5 | 14.1889227802691 | 0.5020382394983653 |
| Grok 4.3 (non-reasoning) Grok 4.3 (Non-reasoning) | 13.9926809505055 | 0.16974590796834474 |
| Nemotron 3.5 Lightning Nemotron 3.5 Lightning | 12.8572306217144 | 0.07948959749314857 |
| Nemotron 3 Super Nemotron 3 Super 120B A12B (Reasoning) | 12.8287575290979 | 1.6390663672616101 |
| Granite 4.2 30B Granite 4.2 30B | 12.68315341158 | 0.0716641484962871 |
| Mercury 2.5 Mercury 2.5 | 12.3408453757638 | 0.11668472036336801 |
| Mistral Small 4 Mistral Small 4 (Reasoning) | 11.2675794141469 | 0.01504679036588765 |
| Qwen3.5 9B Qwen3.5 9B (Reasoning) | 11.1961650827156 | 0.21258346272934256 |
| Granite 4.2 8B Granite 4.2 8B | 11.0812712267815 | 0.023596091491929188 |
| Trinity Large Thinking Trinity Large Thinking | 10.8242425924218 | 0.11883788334567012 |
| Mercury 2 Mercury 2 | 10.7770340974661 | 0.03862922542636743 |
| Qwen3 Coder Next Qwen3 Coder Next | 9.23682203219174 | 0.46969565354948617 |
| Granite 4.2 3B Granite 4.2 3B | 9.05588232376756 | 0.005987243224456071 |
| Gemma 4 E4B Gemma 4 E4B (Reasoning) | 8.90908441839731 | 0.008163276245907385 |
| Solar Pro 3 Solar Pro 3 | 7.81551744502774 | 0.07942705217350178 |
| Celeris-1 Celeris-1 | 6.3469533538601 | 0.05015755586591194 |
Arena
来源日期:2026-10-22 · 核对:2026-10-26
原始来源| 模型/配置 | Text Arena · Overall · Style Control | 输出价格(美元 / 百万 token) |
|---|---|---|
| Gemini 4 Argon (High) Text Overall · Style Control;10083 票;评分区间不代表名次差异显著。 | 1517.1715740590357 | 10 |
| Claude Opus 5.5 (High) Text Overall · Style Control;10322 票;评分区间不代表名次差异显著。 | 1508.7303522485386 | 20 |
| Muse Wonder (Max) Text Overall · Style Control;6001 票;评分区间不代表名次差异显著。 | 1508.7101317781676 | 20 |
| Claude Fable 5 (High) Text Overall · Style Control;44253 票;评分区间不代表名次差异显著。 | 1503.2756933519508 | 50 |
| Claude Fable 5.1 (Max) Text Overall · Style Control;16343 票;评分区间不代表名次差异显著。 | 1503.1905093383516 | 50 |
| Claude Opus 4.6 (High) Text Overall · Style Control;83454 票;评分区间不代表名次差异显著。 | 1502.8892762970327 | 25 |
| Claude Opus 4.7 (High) Text Overall · Style Control;65140 票;评分区间不代表名次差异显著。 | 1501.05116478266 | 25 |
| Claude Opus 4.6 Text Overall · Style Control;88206 票;评分区间不代表名次差异显著。 | 1496.652551971709 | 25 |
| Gemini 3.8 Flash (High) Text Overall · Style Control;43997 票;评分区间不代表名次差异显著。 | 1495.7009350762085 | 3.75 |
| Muse Spark 1.3 (Max) Text Overall · Style Control;20506 票;评分区间不代表名次差异显著。 | 1495.565274618029 | 4.25 |
| Claude Opus 4.7 Text Overall · Style Control;66183 票;评分区间不代表名次差异显著。 | 1493.6753149588794 | 25 |
| Muse Spark 1.2 (xHigh) Text Overall · Style Control;10470 票;评分区间不代表名次差异显著。 | 1491.3642050323658 | 4.25 |
| Claude Opus 5 (Max) Text Overall · Style Control;34526 票;评分区间不代表名次差异显著。 | 1490.8728559881154 | 25 |
| Claude Opus 5 (High) Text Overall · Style Control;71020 票;评分区间不代表名次差异显著。 | 1490.7170594183362 | 25 |
| Muse Spark 1.1 Text Overall · Style Control;46121 票;评分区间不代表名次差异显著。 | 1489.8545257025703 | 4.25 |
| Gemini 3.7 Flash (High) Text Overall · Style Control;30501 票;评分区间不代表名次差异显著。 | 1489.8431217694936 | 3.75 |
| Gemini 3.1 Pro Preview Text Overall · Style Control;130819 票;评分区间不代表名次差异显著。 | 1487.018467203929 | 6 |
| GPT-5.6 Sol (xHigh) Text Overall · Style Control;42713 票;评分区间不代表名次差异显著。 | 1485.1373541029157 | 20 |
| Gemini 3.6 Flash (High) Text Overall · Style Control;36102 票;评分区间不代表名次差异显著。 | 1483.0478951263665 | 3.75 |
| Qwen3.8-Max Text Overall · Style Control;30500 票;评分区间不代表名次差异显著。 | 1482.9118943499611 | 6 |
| GPT-5.5 (High) Text Overall · Style Control;69375 票;评分区间不代表名次差异显著。 | 1481.6294193391002 | 30 |
| Claude Opus 4.8 (High) Text Overall · Style Control;64096 票;评分区间不代表名次差异显著。 | 1481.4818924471078 | 25 |
| GLM-5.3 (Max) Text Overall · Style Control;25144 票;评分区间不代表名次差异显著。 | 1480.7355272301697 | 4.4 |
| GPT-6.1 Sol (Max) Text Overall · Style Control;8305 票;评分区间不代表名次差异显著。 | 1479.9433082251264 | 10 |
| MiMo-V2.6-Pro Text Overall · Style Control;4067 票;评分区间不代表名次差异显著。 | 1479.5470990311535 | 0.87 |
| Claude Sonnet 5.5 (xHigh) Text Overall · Style Control;8977 票;评分区间不代表名次差异显著。 | 1477.512147734337 | 10 |
| Gemini 3.5 Flash (High) Text Overall · Style Control;48504 票;评分区间不代表名次差异显著。 | 1477.326500368638 | 4.5 |
| GPT-5.5 Text Overall · Style Control;70998 票;评分区间不代表名次差异显著。 | 1476.6876302100268 | 30 |
| Gemini 3.5 Flash (Medium) Text Overall · Style Control;47271 票;评分区间不代表名次差异显著。 | 1476.0495947789236 | 4.5 |
| DeepSeek-V4.1-Flash-20260910 (Max) Text Overall · Style Control;13750 票;评分区间不代表名次差异显著。 | 1476.0190205724746 | 1.2 |
| GLM-5.3-Flash Text Overall · Style Control;38359 票;评分区间不代表名次差异显著。 | 1475.957904524776 | 0.18 |
| GPT-5.2 Chat (20260210) Text Overall · Style Control;35982 票;评分区间不代表名次差异显著。 | 1475.6263256912114 | 14 |
| GLM-5.2 (Max) Text Overall · Style Control;52283 票;评分区间不代表名次差异显著。 | 1475.4156684253448 | 4.4 |
| GPT-5.4 (High) Text Overall · Style Control;64757 票;评分区间不代表名次差异显著。 | 1475.382294700097 | 15 |
| Claude Opus 4.8 Text Overall · Style Control;65208 票;评分区间不代表名次差异显著。 | 1474.2127030951465 | 25 |
| Qwen3.7-Max-Preview Text Overall · Style Control;3941 票;评分区间不代表名次差异显著。 | 1474.1611214615284 | 4.425 |
| GPT-5.5 Instant Text Overall · Style Control;27163 票;评分区间不代表名次差异显著。 | 1473.20224383745 | 30 |
| Claude Sonnet 4.6 Text Overall · Style Control;70953 票;评分区间不代表名次差异显著。 | 1472.082135371373 | 7.5 |
| Grok 4.20 Beta (Reasoning, 0309) Text Overall · Style Control;66418 票;评分区间不代表名次差异显著。 | 1471.7014836559058 | 2.5 |
| GPT-5.6 Terra (xHigh) Text Overall · Style Control;46470 票;评分区间不代表名次差异显著。 | 1467.2183652681626 | 12 |
| ERNIE 5.1 Text Overall · Style Control;39474 票;评分区间不代表名次差异显著。 | 1467.1171176845064 | 2.5353 |
| MiMo-V2.5-Pro Text Overall · Style Control;77883 票;评分区间不代表名次差异显著。 | 1466.4622105406606 | 0.609 |
| Grok 4.5 Text Overall · Style Control;39880 票;评分区间不代表名次差异显著。 | 1465.7682811634877 | 6 |
| GLM-5.1 Text Overall · Style Control;65402 票;评分区间不代表名次差异显著。 | 1465.3593126717285 | 4.4 |
| GPT-5.4 Text Overall · Style Control;67855 票;评分区间不代表名次差异显著。 | 1464.8231556982098 | 15 |
| DeepSeek-V4-Pro (High, 20260813) Text Overall · Style Control;9797 票;评分区间不代表名次差异显著。 | 1464.5421674005563 | 3.96 |
| Claude Sonnet 5 (High) Text Overall · Style Control;51784 票;评分区间不代表名次差异显著。 | 1461.479847444079 | 10 |
| Kimi K2.6 Text Overall · Style Control;40026 票;评分区间不代表名次差异显著。 | 1460.6629424609475 | 4 |
| Qwen3.6-Max-Preview Text Overall · Style Control;5423 票;评分区间不代表名次差异显著。 | 1460.5907390607254 | 7.608 |
| GPT-6 Sol (Max) Text Overall · Style Control;14707 票;评分区间不代表名次差异显著。 | 1459.032251281731 | 10 |
| DeepSeek-V4-Pro Text Overall · Style Control;57588 票;评分区间不代表名次差异显著。 | 1457.8787534988062 | 3.96 |
| GLM-5 Text Overall · Style Control;29267 票;评分区间不代表名次差异显著。 | 1457.4128976153304 | 3.2 |
| Grok 4.6 (High) Text Overall · Style Control;32189 票;评分区间不代表名次差异显著。 | 1456.3622941261822 | 6 |
| Qwen3.7-Plus Text Overall · Style Control;42058 票;评分区间不代表名次差异显著。 | 1455.7042471746377 | 1.28 |
| Gemini 3.5 Flash-Lite Text Overall · Style Control;35829 票;评分区间不代表名次差异显著。 | 1455.1995844712576 | 1.25 |
| DeepSeek-V4-Pro Preview (High) Text Overall · Style Control;54896 票;评分区间不代表名次差异显著。 | 1454.946848514609 | 3.96 |
| Hy3 Text Overall · Style Control;13220 票;评分区间不代表名次差异显著。 | 1453.7970900098853 | 0.528 |
| GPT-5.6 Luna (xHigh) Text Overall · Style Control;41426 票;评分区间不代表名次差异显著。 | 1452.9827749897509 | 1.2 |
| Gemma 4 31B Text Overall · Style Control;6137 票;评分区间不代表名次差异显著。 | 1452.2536965362306 | 1.49 |
| GPT-5.3 Chat Text Overall · Style Control;34324 票;评分区间不代表名次差异显著。 | 1450.1309402897728 | 14 |
| Kimi K2.5 (Thinking) Text Overall · Style Control;74744 票;评分区间不代表名次差异显著。 | 1449.8685141924625 | 3 |
| MiMo-V2.6-Flash Text Overall · Style Control;13730 票;评分区间不代表名次差异显著。 | 1448.1035716010952 | 0.28 |
| MiMo-V2-Pro Text Overall · Style Control;25435 票;评分区间不代表名次差异显著。 | 1447.9506994793653 | 3.3 |
| GPT-5.4 mini (High) Text Overall · Style Control;63451 票;评分区间不代表名次差异显著。 | 1447.0944068597867 | 4.5 |
| Qwen3.6-Plus Text Overall · Style Control;48142 票;评分区间不代表名次差异显著。 | 1443.1174163752908 | 3 |
| GPT-6 Luna (Max) Text Overall · Style Control;72504 票;评分区间不代表名次差异显著。 | 1442.1952399830611 | 0.5 |
| Qwen3.5-397B-A17B Text Overall · Style Control;96206 票;评分区间不代表名次差异显著。 | 1441.6936982868262 | 3.6 |
| Grok 4.3 Text Overall · Style Control;71348 票;评分区间不代表名次差异显著。 | 1441.6651712905812 | 2.5 |
| Inkling Text Overall · Style Control;43705 票;评分区间不代表名次差异显著。 | 1441.5997781740728 | 4.05 |
| Grok 4.7 (xHigh) Text Overall · Style Control;14693 票;评分区间不代表名次差异显著。 | 1441.0413192045798 | 6 |
| MiniMax-M3 Text Overall · Style Control;67030 票;评分区间不代表名次差异显著。 | 1439.812467462423 | 1.2 |
| DeepSeek-V4-Flash Preview (High) Text Overall · Style Control;51781 票;评分区间不代表名次差异显著。 | 1438.6554496886292 | 1.2 |
| Qwen3.8-27B Text Overall · Style Control;26238 票;评分区间不代表名次差异显著。 | 1437.138461278535 | 3 |
| Beam 1.0 501B A23B Text Overall · Style Control;4237 票;评分区间不代表名次差异显著。 | 1435.8720914214146 | 1 |
| DeepSeek-V4-Flash Text Overall · Style Control;51982 票;评分区间不代表名次差异显著。 | 1435.6906597797793 | 1.2 |
| MiMo-V2.5 Text Overall · Style Control;47364 票;评分区间不代表名次差异显著。 | 1433.9706183756462 | 0.238 |
| GLM-5V-Turbo Text Overall · Style Control;10477 票;评分区间不代表名次差异显著。 | 1433.9223996040687 | 4 |
| Mistral Large 4 Text Overall · Style Control;10331 票;评分区间不代表名次差异显著。 | 1433.81507721277 | 2.09 |
| Gemini 3.1 Flash-Lite Preview Text Overall · Style Control;64209 票;评分区间不代表名次差异显著。 | 1432.9648637006137 | 1.5 |
| Kimi K2.5 (Instant) Text Overall · Style Control;8371 票;评分区间不代表名次差异显著。 | 1430.6598999809685 | 2.5 |
| MiMo-V2-Omni Text Overall · Style Control;20618 票;评分区间不代表名次差异显著。 | 1430.6173225402135 | 2.2 |
| Mistral Medium 3.5 Text Overall · Style Control;11791 票;评分区间不代表名次差异显著。 | 1426.4014493272962 | 3.75 |
| Claude Haiku 5.5 (High) Text Overall · Style Control;6080 票;评分区间不代表名次差异显著。 | 1424.6044605030932 | 0.5 |
| Qwen3.5-122B-A10B Text Overall · Style Control;29716 票;评分区间不代表名次差异显著。 | 1416.567975329745 | 2.08 |
| MiniMax-M2.7 Text Overall · Style Control;87731 票;评分区间不代表名次差异显著。 | 1414.9702489524907 | 1.2 |
| Hy3 preview Text Overall · Style Control;6875 票;评分区间不代表名次差异显著。 | 1409.0082849192663 | 1.17 |
| Qwen3.5-27B Text Overall · Style Control;28661 票;评分区间不代表名次差异显著。 | 1408.724565227215 | 2.16 |
| Inkling-Small Text Overall · Style Control;35359 票;评分区间不代表名次差异显著。 | 1404.5495117878907 | 1.2 |
| GPT-5.4 nano (High) Text Overall · Style Control;62375 票;评分区间不代表名次差异显著。 | 1401.3880769513587 | 1.25 |
| Qwen3.5-35B-A3B Text Overall · Style Control;30443 票;评分区间不代表名次差异显著。 | 1393.9437750184882 | 1 |
| Step-3.5-Flash Text Overall · Style Control;60329 票;评分区间不代表名次差异显著。 | 1392.9703531883067 | 0.3 |
| MiniMax-M2.5 Text Overall · Style Control;42791 票;评分区间不代表名次差异显著。 | 1390.7198475369528 | 1.2 |
| Solar Pro 4 Text Overall · Style Control;24453 票;评分区间不代表名次差异显著。 | 1387.2626226091422 | 0.6 |
| Trinity Large Thinking Text Overall · Style Control;30307 票;评分区间不代表名次差异显著。 | 1367.3510497819354 | 0.8 |
| GLM-4.7-Flash Text Overall · Style Control;12013 票;评分区间不代表名次差异显著。 | 1364.7191823451406 | 0.4 |
| Mercury 2 Text Overall · Style Control;3193 票;评分区间不代表名次差异显著。 | 1342.957476420446 | 0.75 |
| Olmo 3.1 32B Instruct Text Overall · Style Control;11805 票;评分区间不代表名次差异显著。 | 1329.3826199354912 | 0.6 |
| Granite 4.1 8B Text Overall · Style Control;4177 票;评分区间不代表名次差异显著。 | 1304.179532694888 | 0.1 |
| Granite 4.2 8B Text Overall · Style Control;3259 票;评分区间不代表名次差异显著。 | 1289.7857353610057 | 0.25 |