Which model leads AA-Omniscience?

Q: Which model leads AA-Omniscience?

Claude Opus 5.5 tops the board at 46.417

AA-Omniscience Leaderboard — 355 Models Ranked

Pro Mode — raw scores, one benchmark under the lensAA-graded harness

The field · 200 measured

-43.5546.417

200 models measured, most on the AA-graded harness. Claude Opus 5.5 tops the board at 46.417.

200 measured·16 new this week·Lifecycle Updated Oct 9, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 200Bars show -43.55–46.417 · ◆ solid = first-party or better · outlined = arm's-length

01Claude Opus 5.5NEW+3 altsAnthropic46.417$4.0/M$20.0/M$0.259

02Claude Fable 5.1NEW+4 altsAnthropic43.45$10.0/M$50.0/M$0.690

03GPT-6 Astra+5 altsOpenAI43.4$10.0/M$50.0/M$0.691

04Claude Fable 5NEWAnthropic43.3$10.0/M$50.0/M$0.693

05Gemini 4 ArgonGoogle42.35$2.0/M$10.0/M$0.142

06GPT-6.1 Sol+4 altsOpenAI41.533$2.0/M$10.0/M$0.144

07Claude Opus 5.5 (Adaptive Reasoning, Medium Effort, Default Fallback)NEWAnthropic40.317$4.0/M$20.0/M$0.298

08Claude Opus 5NEW+4 altsAnthropic37.067$5.0/M$25.0/M$0.405

09Claude Sonnet 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)NEW+2 altsAnthropic32.3$2.0/M$10.0/M$0.186

10Grok 4.7+2 altsSpaceXAI32.033$2.0/M$6.0/M$0.125

11Gemini 3.1 ProGoogle31.883$2.0/M$12.0/M$0.220

12Gemini 3.8 Flash+2 altsGoogle29.55$0.75/M$3.8/M$0.076

13Grok 4.6+3 altsSpaceXAI29.317$2.0/M$6.0/M$0.136

14Claude Opus 4.8NEWAnthropic28.75$5.0/M$25.0/M$0.522

15Muse Spark 1.1Meta28.083$1.3/M$4.3/M$0.098

16Claude Opus 4.7NEW+1 altAnthropic27.267$5.0/M$25.0/M$0.550

17Muse Spark 1.2Meta27.2$1.3/M$4.3/M$0.101

18GPT-6 Sol+5 altsOpenAI27.117$2.0/M$10.0/M$0.221

19Gemini 3.7 Flash+2 altsGoogle26.483$0.75/M$3.8/M$0.085

20Grok4.5SpaceXAI25.317$2.0/M$6.0/M$0.158

21Muse Spark 1.3+1 altMeta25$1.3/M$4.3/M$0.110

22Gemini 3.6 FlashGoogle22.133$0.75/M$3.8/M$0.102

23GPT-5.6 Sol+5 altsOpenAI21.967$4.0/M$20.0/M$0.546

24Gemini 3.5 Flash+2 altsGoogle21.183$1.5/M$9.0/M$0.248

25JT-4.1 Flash 236B A21B+1 altChina Mobile20.567———

26GPT-5.5+4 altsOpenAI20.517$5.0/M$30.0/M$0.853

27Claude 5.5NEWAnthropic20.1$2.0/M$10.0/M$0.299

28Kimi K3+2 altsMoonshot19.7$0.58/M$12.3/M$0.327

29Claude Sonnet 5.5 (Adaptive Reasoning, Low Effort, Default Fallback)NEWAnthropic19.367$2.0/M$10.0/M$0.310

30Grok 4.3+4 altsSpaceXAI17.983$1.3/M$2.5/M$0.104

31Claude Sonnet 5NEW+5 altsAnthropic16.45$2.0/M$10.0/M$0.365

32Step 5 PreviewStepFun16.383$1.0/M$2.7/M$0.113

33Gemini 3 Pro+1 altGoogle15.283$2.0/M$12.0/M$0.458

34GLM-5.3+1 altZ.ai14.3$1.4/M$4.4/M$0.203

35Claude Opus 4.5+1 altAnthropic14$5.0/M$25.0/M$1.071

36Claude Opus 4.6NEW+1 altAnthropic13.667$5.0/M$25.0/M$1.098

37Qwen3.7 MaxAlibaba13.483$2.5/M$7.5/M$0.371

38Grok 4.20SpaceXAI12.95$1.3/M$2.5/M$0.145

39Claude Sonnet 4.6NEW+2 altsAnthropic12.217$3.0/M$15.0/M$0.737

40Qwen3.8 Max Preview+1 altAlibaba11.983$3.3/M$9.9/M$0.551

41GPT-5.5 Instant+1 altOpenAI11.15$5.0/M$30.0/M$1.570

42GPT-5.3 CodexOpenAI10.867$1.8/M$14.0/M$0.725

43Haiku 5.5NEW+4 altsAnthropic10.667$0.10/M$0.50/M$0.028

44Motif-3Motif Technologies10.183———

45Gemini 3 Flash Preview+1 altGoogle10.133$0.50/M$3.0/M$0.173

46Qwen3.6 Max PreviewAlibaba9.167$1.3/M$7.8/M$0.496

47MiMo V2.6 ProXiaomi8.383$0.43/M$0.87/M$0.078

48GLM 5.3 FlashZ.ai7.467$0.15/M$0.50/M$0.044

49Muse SparkMeta7.167———

50GPT-5.4+2 altsOpenAI5.783$2.5/M$15.0/M$1.513

51GPT-5.1+1 altOpenAI5.4$1.3/M$10.0/M$1.042

52Kimi K2.6+1 altMoonshot5.3$0.95/M$4.0/M$0.467

53Gemini 3.5 Flash LiteGoogle5.233$0.30/M$2.5/M$0.268

54MiMo V2 ProXiaomi4.617———

55GLM-5.2+1 altZ.ai4.433$1.4/M$4.4/M$0.654

56Qwen3.8 2.4T A95BAlibaba4.317$2.0/M$6.0/M$0.927

57G9v3-39A5BAI9Stars3.767———

58MiMo V2.5 Pro+1 altXiaomi3.25$0.43/M$0.87/M$0.201

59Ling-3.1-flashNEWInclusionAI2.217$0.30/M$0.90/M$0.271

60Grok 4SpaceXAI2.1$3.0/M$15.0/M$4.286

61InklingThinking Machines2$0.95/M$4.0/M$1.250

62MiniMax M3MiniMax1.35$0.28/M$1.1/M$0.511

63Qwen3.7 Plus PreviewAlibaba1.083$0.40/M$1.6/M$0.923

64Qwen3.6 PlusAlibaba0.883$0.50/M$3.0/M$1.981

65GLM-5.1+1 altZ.ai0.85$1.4/M$4.4/M$3.400

66MiniMax M2.7MiniMax0.767$0.21/M$0.84/M$0.685

67GPT-6 Luna+5 altsOpenAI0.65$0.10/M$0.50/M$0.462

68GLM-5+1 altZ.ai0.267$1.0/M$3.2/M$7.875

69Claude Sonnet 4+1 altAnthropic0.167$3.0/M$15.0/M$54.000

70GPT-5.6 Terra+5 altsOpenAI0.05$2.0/M$12.0/M$140.000

71Claude Sonnet 4.5+1 altAnthropic-0.083$3.0/M$15.0/M—

72Nemotron 3 Ultra 550B A55BNVIDIA-0.4$0.60/M$2.5/M—

73Claude 3.7 Sonnet+1 altAnthropic-0.733$3.0/M$15.0/M—

74Solar Pro4Upstage-0.85$0.30/M$1.2/M—

75GPT-5.2+2 altsOpenAI-0.883$1.8/M$14.0/M—

76Solar Open2 250BUpstage-1.767———

77GPT-5.2 CodexOpenAI-2.167$1.8/M$14.0/M—

78K2 Horizon 375B A23BMBZUAI-2.967———

79Command A+Cohere-4.017$0.30/M$1.5/M—

80Claude Haiku 4.5+1 altAnthropic-4.367$1.0/M$5.0/M—

81G9v3-3BAI9Stars-4.367———

82Ling-3.0-flash-VLInclusionAI-4.533$0.02/M$0.06/M—

83DeepSeek-V4.1-Flash+1 altDeepSeek-5.3$0.20/M$0.60/M—

84Mistral Large 4NEWMistral-5.3$0.68/M$2.1/M—

85GPT-5.1 CodexOpenAI-6.5$1.3/M$10.0/M—

86K-EXAONE 2.0LG AI-6.6———

87Grok 3 Mini ReasoningSpaceXAI-6.8$0.30/M$0.50/M—

88Kimi K2.5+1 altMoonshot-7.333$0.45/M$2.3/M—

89GPT-5 CodexOpenAI-7.533$1.3/M$10.0/M—

90A.X-K2SK Telecom-8.233———

91GPT-5+3 altsOpenAI-8.733$1.3/M$10.0/M—

92Inkling-SmallThinking Machines-8.933$0.30/M$1.2/M—

93Qwen3.8 Flash NextAlibaba-9.717$0.15/M$0.47/M—

94MiMo V2.5Xiaomi-9.833$0.14/M$0.28/M—

95Qwen3.8 27B+3 altsAlibaba-9.983$0.50/M$3.0/M—

96Kimi K2.7 CodeMoonshot-10.217$1.9/M$8.1/M—

97GPT-5.6 Luna+5 altsOpenAI-10.283$0.20/M$1.2/M—

98GPT-4o+1 altOpenAI-10.517$5.0/M$15.0/M—

99Agnes 2.5 Pro BetaSapiens AI-10.533———

100Agnes 3.0 FlashSapiens AI-10.567———

101DeepSeek-V4-Pro+4 altsDeepSeek-10.733$0.43/M$0.87/M—

102Solar Mini4Upstage-10.817$0.10/M$0.40/M—

103LFM2.5-2.6BLiquid AI-10.95———

104K2 Horizon 36B-A4BMBZUAI-10.95———

105O1OpenAI-11.05$15.0/M$60.0/M—

106MiniCPM5-2BOpenBMB-11.65———

107MiMo V2.6 Flash RLXiaomi-12.683$0.14/M$0.28/M—

108Granite 4.2 30BIBM-12.917$0.16/M$0.65/M—

109Qwen3.5 Omni PlusAlibaba-13.117$0.40/M$4.8/M—

110DeepSeek-V4-Flash+6 altsDeepSeek-14.283$0.44/M$1.3/M—

111Ling-3.0-flash-FinInclusionAI-14.583$0.04/M$0.12/M—

112MiniCPM5-1B+1 altOpenBMB-14.617———

113Granite 4.2 3BIBM-14.717$0.03/M$0.12/M—

114O3OpenAI-15.55$2.0/M$8.0/M—

115Gemini 2.5 ProGoogle-16.35$1.3/M$10.0/M—

116GLM-5-TurboZ.ai-16.367$1.2/M$4.0/M—

117Gemini 3.1 Flash Lite PreviewGoogle-16.417$0.25/M$1.5/M—

118GPT-5.1 Codex miniOpenAI-16.417$0.25/M$2.0/M—

119K2 Horizon 7BMBZUAI-16.567———

120Llama 3.1 Instruct 405BMeta-17.1———

121Granite 4.2 8BIBM-17.167$0.06/M$0.25/M—

122GPT-5 mini+2 altsOpenAI-17.317$0.25/M$2.0/M—

123Nemotron 3.5 LightningNVIDIA-17.717$0.06/M$0.20/M—

124DeepSeek-V3.2-SpecialeDeepSeek-17.717$0.29/M$0.43/M—

125Motif-3-BetaMotif Technologies-17.767———

126Ling-3.0-flashInclusionAI-17.883$0.07/M$0.22/M—

127Hy3-preview+1 altTencent-18.467$0.14/M$0.56/M—

128GPT-5.4 mini+2 altsOpenAI-18.917$0.75/M$4.5/M—

129GLM 5V TurboZ.ai-19.283$1.2/M$4.0/M—

130Ling 3.0 TinyInclusionAI-19.35———

131Gemma 4 E4B+1 altGoogle-19.7$0.02/M$0.10/M—

132Qwen3.6 27B+1 altAlibaba-20.017$0.60/M$3.6/M—

133MiMo V2 Omni+1 altXiaomi-20.133$0.40/M$2.0/M—

134Kimi K2 ThinkingMoonshot-21.417$0.60/M$2.5/M—

135Apodex 1.1Apodex-21.9$0.30/M$3.0/M—

136Qwen3.6 35B A3B+1 altAlibaba-22.183$0.38/M$2.3/M—

137Qwen3 Coder 480B A35B InstructAlibaba-22.2$1.5/M$7.5/M—

138DeepSeek-V3.2+1 altDeepSeek-22.483$0.28/M$0.42/M—

139Claude 3.5 HaikuAnthropic-22.517———

140LongCat-2.0Meituan-23.417$0.30/M$1.2/M—

141Gemma 4 E2B+1 altGoogle-23.583———

142JT-35B-FlashChina Mobile-24.217———

143Agnes 2.5 Pro AlphaSapiens AI-25.1———

144DeepSeek-V3.1-Terminus+1 altDeepSeek-26.4$0.27/M$1.0/M—

145Kimi K2 InstructMoonshot-26.583$0.57/M$2.3/M—

146Magistral Medium 1.2Mistral-26.733———

147Magistral Medium 1Mistral-26.933———

148GLM-4.6V+1 altZ.ai-26.95$0.30/M$0.90/M—

149Nex-N2-ProNex AGI-27.05$0.25/M$1.0/M—

150GLM-4.5Z.ai-27.383$0.60/M$2.2/M—

151Kimi K2 (Non-Reasoning)Moonshot-28.317$0.57/M$2.3/M—

152K2 Horizon 3.7BMBZUAI-28.617———

153GPT-5 nano+2 altsOpenAI-28.667$0.05/M$0.40/M—

154Gemma 3 270MGoogle-29.267———

155GPT-5.4 nano+2 altsOpenAI-29.467$0.20/M$1.3/M—

156DeepSeek-V3.1+1 altDeepSeek-29.583$0.56/M$1.7/M—

157Gemini 2.5 Flash+1 altGoogle-29.8$0.30/M$2.5/M—

158Grok 4.1 Fast+1 altSpaceXAI-29.917$0.20/M$0.50/M—

159Grok 4 Fast+1 altSpaceXAI-29.933$0.20/M$0.50/M—

160Mistral Small 4+1 altMistral-30.4$0.15/M$0.60/M—

161Qwen3.5 397B A17B+1 altAlibaba-30.75$0.60/M$3.6/M—

162Llama 3.1 8B InstructMeta-30.883$0.02/M$0.04/M—

163DeepSeek-V3.2-Exp+1 altDeepSeek-30.967$0.28/M$0.42/M—

164Devstral MediumMistral-31.567$0.40/M$2.0/M—

165DeepSeek-R1DeepSeek-32.217$2.0/M$4.0/M—

166Muse GlimmerMeta-32.85$0.33/M$1.4/M—

167MiniMax M2.1MiniMax-32.867$0.30/M$1.2/M—

168Grok 3SpaceXAI-33.183$4.0/M$20.0/M—

169LFM2.5-8B-A1BLiquid AI-33.2———

170GPT-4OpenAI-33.833$30.0/M$60.0/M—

171Mistral Large 2Mistral-34.367$2.0/M$6.0/M—

172ERNIE 4.5 300B A47BBaidu-35.133$0.28/M$1.1/M—

173Doubao Seed CodeByteDance-35.2———

174Nova PremierAmazon-35.383———

175O4 MiniOpenAI-35.7$1.1/M$4.4/M—

176Gemini 2.5 Flash (Sep) (Non-Reasoning)+1 altGoogle-36.1———

177GLM-4.7+1 altZ.ai-36.433$0.60/M$2.2/M—

178Qwen3 Max (Reasoning)Alibaba-36.617$1.2/M$6.0/M—

179Mistral Medium 3.5 128BMistral-36.8$1.5/M$7.5/M—

180Grok Code Fast 1SpaceXAI-37.067$0.20/M$1.5/M—

181Step 3.7 FlashStepFun-37.283$0.20/M$1.1/M—

182MiniMax M2.5MiniMax-38.867$0.27/M$1.1/M—

183Mercury 2.5 PreviewInception-39.483$0.25/M$0.75/M—

184Mistral Large 3Mistral-39.567$0.50/M$1.5/M—

185GPT-4.1OpenAI-39.633$2.0/M$8.0/M—

186K2 Think V2MBZUAI-40.333———

187DeepSeek-V3+1 altDeepSeek-40.667$0.24/M$0.90/M—

188Llama 3.1 Nemotron Instruct 70BNVIDIA-40.833———

189Nemotron 3 Super 120B A12BNVIDIA-41.5$0.30/M$0.90/M—

190Qwen3.5 122B A10B+1 altAlibaba-41.5$0.40/M$3.2/M—

191NVIDIA Nemotron Nano 9B V2+1 altNVIDIA-41.55$0.04/M$0.16/M—

192Step 3.5 Flash+1 altStepFun-41.817$0.10/M$0.30/M—

193Llama 4 MaverickMeta-41.85$0.25/M$0.87/M—

194GLM-4.6+1 altZ.ai-41.883$0.57/M$2.2/M—

195Nova LiteAmazon-42.167$0.06/M$0.24/M—

196Nanbeige4.1-3BNanbeige-42.5———

197Gemini 2.0 Flash (Non-Reasoning)Google-42.533———

198O3 MiniOpenAI-42.567$1.1/M$4.4/M—

199Llama 3.1 70B InstructMeta-43.1$0.56/M$0.56/M—

200Qwen3 Max (Non-Reasoning)Alibaba-43.55$1.2/M$6.0/M—

◆ solid = independently verified · aggregator attested · vendor attributed — outlined = cross-reference · source-attributed. Dimmed ◆ = confidence inferred. “+N alts” = alternate disclosures in the drawer with why-demoted. Prices per million tokens; $/point = input price ÷ score. Every row opens its model dossier.

Verification: 200 models scored · 0 independently verified · 200 aggregator-attributed · 0 with source disagreement. How these tiers are assigned