By model and setting

Each model and reasoning setting appears once. If a model produced more than one player program for this game, DuelLab averages them before ranking. Score is relative within this game (0–100).

GB2-01: Go - Reasoning Variants
Rank Model Reasoning Score Raw rating W / D / L
1GPT-5.4Medium100.02408.2431 / 5 / 4
2GPT-6 AstraXHigh96.62353.0343 / 0 / 9
3GPT-5.4XHigh87.02199.1408 / 8 / 22
4GPT-6 AstraLow82.32124.2340 / 12 / 20
5Claude Fable 5.1XHigh80.92102.4311 / 1 / 32
6Claude Opus 5.5Medium79.72082.0186 / 13 / 7
7Gemini 3.5 FlashHigh78.72066.3310 / 15 / 29
8GLM-5.3Max75.32011.6281 / 24 / 33
9Claude Fable 5.1Low73.31980.6297 / 2 / 52
10Claude Opus 5.5Low72.61968.5181 / 8 / 19
11Claude Fable 5XHigh71.11945.2482 / 0 / 86
12Grok 4.5High69.11912.9348 / 93 / 45
13MiMo-V2.6-ProEnabled68.11896.2162 / 0 / 34
14Muse Spark 1.2Medium68.01895.5361 / 14 / 73
15Grok 4.5Medium67.11880.2236 / 22 / 46
16GPT-5.4None65.51855.4343 / 36 / 77
17Claude Opus 5.5XHigh65.11847.8158 / 5 / 41
18Claude Sonnet 5.5XHigh64.41836.8133 / 54 / 17
19GPT-5.6 LunaXHigh64.01830.2313 / 0 / 107
20Muse Spark 1.3XHigh63.81828.2250 / 2 / 90
21GPT-5.6 TerraMedium63.41820.6309 / 5 / 92
22GPT-5.6 SolNone63.31820.1313 / 2 / 109
23Gemini 3.6 FlashMedium62.51806.8406 / 337 / 147
24Ember-1Max62.41804.4158 / 3 / 47
25GLM-5.3 FlashXHigh61.51790.5151 / 5 / 42
26GPT-6 AstraMedium61.41789.4265 / 24 / 81
27Grok 4.7Medium61.31787.4143 / 15 / 42
28Hy3 PreviewNone60.81779.6191 / 52 / 59
29Claude Fable 5.1Medium60.71778.0270 / 1 / 95
30Claude Opus 5None60.61775.9325 / 260 / 60
31GPT-5.5XHigh60.41773.1159 / 100 / 31
32Muse Spark 1.3Medium60.11768.9269 / 0 / 97
33GPT-6.1 SolXHigh59.51758.7152 / 0 / 56
34Qwen3.8 27BXHigh59.31755.8267 / 10 / 101
35GPT-5.6 SolXHigh59.01750.8299 / 10 / 129
36Gemini 3.8 FlashMedium58.81747.2199 / 48 / 95
37Gemini 3.5 FlashMedium58.71745.9236 / 6 / 108
38GPT-5.6 TerraXHigh57.91733.6259 / 66 / 89
39Claude Opus 5Medium57.71729.2408 / 66 / 152
40Gemini 3.1 Pro PreviewHigh57.31723.6132 / 5 / 59
41Claude Opus 5XHigh57.31722.8369 / 6 / 179
42Claude Fable 5Medium57.31722.5213 / 33 / 108
43GPT-6.1 SolMedium57.21721.7144 / 3 / 61
44GPT-5Low56.51710.1127 / 28 / 59
45Claude Opus 4.8XHigh56.21706.1221 / 44 / 73
46Claude Opus 4.5High56.21705.7282 / 64 / 135
47DeepSeek V4.1 FlashHigh56.21705.076 / 99 / 11
48MiMo-V2.5-ProEnabled56.11703.5313 / 59 / 146
49Qwen3.8 Max 0902XHigh55.91701.498 / 72 / 24
50GLM-5.3 FlashHigh55.91700.7218 / 11 / 131
51Claude Fable 5Low55.51694.4186 / 48 / 106
52MiMo-V2.6-FlashNone55.11687.9103 / 61 / 34
53Kimi K3Max54.81683.5285 / 53 / 164
54GPT-5.4 MiniMedium54.11671.3194 / 19 / 93
55GLM-5.3 FlashXLow54.11671.2106 / 47 / 41
56Qwen3.7 MaxNone53.11656.2150 / 94 / 70
57GPT-5.6 SolMedium53.01654.3193 / 99 / 132
58GLM-5.3 FlashMax52.91652.5407 / 8 / 221
59GLM-5.3Low52.81651.2213 / 66 / 103
60Kimi K3High52.81651.1237 / 79 / 162
61Grok 4.6Low52.51646.4206 / 48 / 134
62Ox AlphaHigh52.21640.9443 / 156 / 223
63Space Bunny AlphaXHigh51.91637.0102 / 58 / 50
64Claude Sonnet 5XHigh51.31627.0323 / 72 / 175
65DeepSeek V4.1 FlashMax51.31626.3119 / 8 / 73
66Hy3 PreviewHigh51.01622.7180 / 61 / 85
67Grok 4.6Medium50.81619.3267 / 152 / 159
68DeepSeek V4 ProHigh50.21609.9226 / 28 / 158
69Muse Spark 1.2XHigh50.11607.3271 / 51 / 182
70o3High49.61599.1816 / 208 / 630
71Ox AlphaMax49.11591.5605 / 70 / 491
72GPT-5.5Medium48.81586.9102 / 204 / 18
73Claude Opus 4.5Medium48.81586.5243 / 167 / 172
74GPT-4.1None48.61584.0177 / 26 / 120
75Gemini 3.5 FlashLow48.21577.4145 / 59 / 74
76Gemini 3.8 FlashHigh46.91556.3237 / 35 / 170
77Claude Opus 4.8None46.81555.4131 / 76 / 95
78GPT-6 SolNone46.81554.8104 / 8 / 90
79Grok 4.7XHigh46.51549.9112 / 1 / 89
80Gemini 3.8 FlashLow46.01541.2159 / 174 / 105
81Qwen3.8 2.4t A95BXHigh45.91539.6154 / 125 / 139
82Minimax M3None45.31530.9149 / 68 / 119
83Nemotron 3 Ultra 550B A55BNone45.21529.8109 / 49 / 122
84Grok 4.6XHigh45.11528.2101 / 224 / 99
85GPT-5.6 TerraNone45.11528.1247 / 199 / 194
86Ember-1High45.01526.054 / 104 / 52
87Gemini 3.6 FlashHigh44.91525.0360 / 294 / 338
88Hy4 PreviewHigh44.91524.3105 / 211 / 102
89GLM-5.2XHigh44.91523.9178 / 174 / 136
90GLM-5.3High44.41516.7188 / 74 / 172
91MiMo-V2.6-FlashEnabled44.41516.2102 / 2 / 94
92Qwen3.8 2.4t A95BMedium44.31514.473 / 173 / 124
93Hy4 PreviewLow43.61504.1184 / 22 / 200
94GPT-6.1 SolLow43.21497.693 / 22 / 89
95Grok 4.5Low43.11495.5191 / 442 / 191
96Nemotron 3 Ultra 550B A55BMedium42.91493.0126 / 66 / 122
97Laguna S 2.1None42.41483.9266 / 124 / 266
98Ember-1None42.31483.057 / 83 / 68
99Kimi K3Low42.11479.5127 / 363 / 135
100Qwen3.8 FlashEnabled41.91476.2117 / 159 / 160
101Qwen3.7 PlusEnabled41.81475.0220 / 100 / 224
102GPT-5.5None41.81474.045 / 240 / 49
103GPT-5.4 NanoNone41.71473.7216 / 140 / 252
104Claude Sonnet 5Medium41.71472.7189 / 95 / 217
105DeepSeek V4 Pro 0813High41.61471.987 / 266 / 97
106DeepSeek V4.1 FlashNone41.41467.959 / 56 / 79
107Hy4 PreviewNone40.51453.8153 / 64 / 219
108GPT-5.6 LunaMedium40.31451.3180 / 74 / 251
109Claude Sonnet 5None40.31451.2190 / 89 / 249
110Seed 2.0 CodeMedium40.21448.2237 / 92 / 251
111DeepSeek V4 Pro 0813Max39.21433.0189 / 13 / 172
112Claude Opus 4.8Medium38.71425.5128 / 61 / 131
113MiMo-V2.5Reasoning38.71424.2203 / 120 / 291
114Space Bunny AlphaMedium38.61423.957 / 39 / 112
115Claude Sonnet 5.5Medium38.51422.178 / 5 / 117
116Claude Sonnet 5.5Low38.51421.876 / 15 / 111
117Ox AlphaLow38.41420.5408 / 300 / 502
118Gemma 4 31BNone38.31418.4139 / 71 / 142
119GPT-OSS 120BLow38.21416.2162 / 68 / 224
120GPT-4.1 NanoReasoning38.11414.4208 / 106 / 250
121o3Medium37.91412.2123 / 63 / 144
122Qwen3.8 MaxMedium37.91411.394 / 144 / 176
123GLM-5.2High37.81409.956 / 202 / 86
124Gemini 3.5 Flash LiteMedium37.71408.7422 / 202 / 580
125GPT-5High37.61407.1133 / 43 / 152
126Gemini 3.5 FlashMinimal37.01397.8133 / 86 / 145
127Laguna S 2.1Enabled37.01397.4203 / 90 / 297
128LongCat 2.0None36.91396.7231 / 221 / 280
129GLM-5.3 FlashXMax36.61391.779 / 1 / 122
130GPT-6 LunaMedium36.61391.545 / 71 / 86
131Claude Opus 4.5None36.01381.958 / 192 / 86
132Qwen3.8 Max 0902Low36.01381.830 / 72 / 82
133Gemini 3.1 Pro PreviewLow36.01381.554 / 26 / 122
134MiMo-V2.6-ProNone36.01381.232 / 79 / 87
135Grok Build 0.1Enabled35.91379.4167 / 116 / 261
136Qwen3.8 27BMedium35.71375.968 / 201 / 95
137Kimi K2.7 CodeEnabled35.41372.7141 / 9 / 181
138Gemini 3.5 Flash LiteMinimal35.41372.2327 / 210 / 553
139Seed 2.0 CodeHigh35.31370.565 / 165 / 120
140DeepSeek V4 FlashMedium35.21369.5149 / 118 / 285
141GPT-OSS 120BMedium34.91363.1104 / 63 / 195
142Muse Glimmer 30BLow34.81361.9118 / 95 / 175
143GPT-6 SolMedium34.61359.443 / 42 / 103
144GLM-5.3 FlashLow34.51357.460 / 210 / 154
145Ling 3.0 FlashNone34.41355.6204 / 191 / 365
146Muse Spark 1.2Minimal34.31354.689 / 178 / 179
147Gemini 3.5 Flash LiteHigh33.61343.0125 / 101 / 242
148DeepSeek V4 FlashHigh33.21336.8155 / 8 / 279
149MiMo-V2.5Reasoning33.21336.691 / 66 / 173
150Qwen3.8 FlashNone33.11334.4145 / 161 / 288
151GLM-5.2Medium33.01334.1118 / 20 / 176
152Gemini 3.1 Pro PreviewMedium33.01333.137 / 68 / 105
153Qwen3.8 MaxXHigh32.21319.985 / 66 / 207
154MiMo-V2.5-ProNone32.11319.591 / 96 / 167
155Gemini 3.1 Flash LiteMedium31.71313.250 / 172 / 116
156DeepSeek V4 Pro 0813None31.61310.7100 / 87 / 183
157Qwen3.8 2.4t A95BLow31.41307.855 / 142 / 165
158GPT-5.4 MiniNone31.21304.553 / 115 / 148
159Inkling SmallMax31.11302.873 / 138 / 189
160Grok 4.7Low30.31290.723 / 68 / 111
161Qwen3.8 Max 0902Medium30.21288.344 / 33 / 131
162Gemini 3.6 FlashMinimal30.11287.1221 / 240 / 555
163MiMo-V2.5Reasoning30.11286.9125 / 5 / 200
164Muse Glimmer 30BXHigh30.01284.958 / 105 / 190
165InklingMedium30.01284.589 / 151 / 254
166GLM-5.2Reasoning29.91284.163 / 109 / 182
167GPT-6 LunaXHigh29.81282.1123 / 1 / 290
168Claude Opus 4.5Historical29.11270.389 / 373 / 336
169MiMo-V2.5Medium28.81266.760 / 73 / 169
170DeepSeek V4 ProNone28.81266.167 / 128 / 207
171Mercury 2.5 PreviewHigh27.41243.869 / 104 / 211
172GLM-5.2Reasoning26.01221.6124 / 108 / 354
173Muse Spark 1.3Minimal25.81218.450 / 92 / 218
174InklingMax25.51213.622 / 178 / 258
175DeepSeek V4 ProXHigh25.51212.690 / 21 / 255
176GPT-5.6 LunaNone25.41211.358 / 89 / 285
177Qwen3.8 MaxMinimal25.41211.158 / 95 / 225
178Inkling SmallNone24.31193.575 / 62 / 280
179Nemotron 3 Ultra 550B A55BHigh24.11190.650 / 70 / 192
180Muse Glimmer 30BMedium23.91187.446 / 95 / 223
181MiMo-V2.5High23.21175.94 / 145 / 143
182GPT-6 LunaNone22.41163.729 / 24 / 149
183Qwen3.7 PlusNone22.11158.736 / 70 / 208
184Seed 2.0 CodeLow21.91155.126 / 99 / 229
185Minimax M3Enabled21.91154.862 / 19 / 241
186DeepSeek V4 FlashNone21.61150.238 / 93 / 253
187InklingNone21.31145.346 / 220 / 386
188North Mini CodeNone21.11141.884 / 232 / 580
189DeepSeek V4 FlashXHigh20.61134.913 / 97 / 238
190o3Low20.51132.134 / 156 / 358
191GPT-5Medium20.41130.652 / 45 / 219
192Qwen3.7 MaxEnabled20.31129.345 / 82 / 237
193Ling 3.0 FlashEnabled20.01125.729 / 125 / 356
194Gemini 3.1 Flash LiteNone15.71055.724 / 60 / 228
195GPT-5.4 NanoMedium12.91010.866 / 90 / 462
196GPT-6 SolXHigh11.4987.015 / 5 / 168
197Mistral Medium 3.5None10.8977.121 / 35 / 308
198Step 3.7 FlashHigh9.8960.626 / 17 / 263
199Inkling SmallMedium9.6957.811 / 52 / 321

Individual player programs

Each row is one accepted player program for GB2-01: Go; a model can have more than one. Score is the 0–100 result in this game, and its rating and W / D / L record show how it played.

226 player programs.

ModelReasoningStatusScoreRatingW / D / LMatchesOpponentsNotesGenerated
Claude Fable 5.1E-61dcbc514347d53dMediumRated60.71778270 / 1 / 95366 / 3661431 capped draw2026-09-03First try
Claude Fable 5.1E-d04c4d8635b641f9LowRated73.31981297 / 2 / 52351 / 3521512 capped draws2026-09-03First try
Seed 2.0 CodeE-61c356c37d74f8eaHighRated35.3137165 / 165 / 120350 / 352144165 capped draws2026-09-03Repaired
Seed 2.0 CodeE-b72f9ae14db0a87cLowRated21.9115526 / 99 / 229354 / 35414199 capped draws2026-09-03First try
Seed 2.0 CodeE-d10da1bd9dc3e6e8MediumRated40.21448237 / 92 / 251580 / 58020792 capped draws2026-09-03Repaired
Claude Fable 5E-82883fa57c3f7c97MediumRated57.31722213 / 33 / 108354 / 35415233 capped draws2026-09-03First try
Claude Fable 5E-99c76fc062487714XHighRated71.11945482 / 0 / 86568 / 568207—2026-09-03First try
Claude Fable 5E-e777ffac36ac36c9LowRated55.51694186 / 48 / 106340 / 34013548 capped draws2026-09-03First try
Claude Fable 5.1E-443622d1ef9c6f19XHighRated80.92102311 / 1 / 32344 / 3441341 capped draw2026-09-08First try
Claude Opus 4.5E-2e3eca63f7980facNoneRated36.0138258 / 192 / 86336 / 336133192 capped draws2026-07-02First try
Claude Opus 4.5E-53c8add70ed7d2e7BudgetedRated26.1122334 / 104 / 152290 / 290119104 capped draws2026-07-02First try
Claude Opus 4.5E-5b675f86b98132f4HighRated56.21706282 / 64 / 135481 / 48115064 capped draws2026-07-21First try
Claude Opus 4.5E-7631f602d0516364BudgetedRated32.0131855 / 269 / 184508 / 508207269 capped draws2026-07-02First try
Claude Opus 4.5E-829b603611fbdcefMediumRated48.81587243 / 167 / 172582 / 582174167 capped draws2026-07-21First try
Claude Opus 4.8E-13ec9509bc80f2bfMediumRated38.71425128 / 61 / 131320 / 32012361 capped draws2026-07-02First try
Claude Opus 4.8E-3308d2952452916eXHighRated56.21706221 / 44 / 73338 / 33814044 capped draws2026-07-03First try
Claude Opus 4.8E-757a6149e87d8b53NoneRated46.81555131 / 76 / 95302 / 30212876 capped draws2026-07-02First try
Claude Opus 5E-0437af9582860271MediumRated50.31611195 / 42 / 99336 / 33613642 capped draws2026-07-25First try
Claude Opus 5E-6c30dc38efb07e9eNoneRated48.4158069 / 216 / 38323 / 324124216 capped draws2026-07-25First try
Claude Opus 5E-700f3dddd611df07XHighRated74.62000227 / 1 / 34262 / 2621081 capped draw2026-07-25First try
Claude Opus 5E-865d68ab219fd7eeNoneRated72.81972256 / 44 / 22322 / 32212844 capped draws2026-07-25First try
Claude Opus 5E-93a6875407c22137MediumRated65.01847213 / 24 / 53290 / 29011424 capped draws2026-07-25First try
Claude Opus 5E-bf06fe9df8858291XHighRated40.01445142 / 5 / 145292 / 2921235 capped draws2026-07-25First try
Claude Opus 5.5E-05f63acd714d31e5XHighRated65.11848158 / 5 / 41204 / 2041025 capped draws2026-09-22First try
Claude Opus 5.5E-9e6850818d33c592MediumRated79.72082186 / 13 / 7206 / 20610313 capped draws2026-09-22First try
Claude Opus 5.5E-c6c2699b24183df3LowRated72.61969181 / 8 / 19208 / 2081048 capped draws2026-09-22First try
Claude Sonnet 5E-41b4bf40efe85b59XHighRated51.31627323 / 72 / 175570 / 57017072 capped draws2026-08-09First try
Claude Sonnet 5E-93cff8e6feb76995NoneRated40.31451190 / 89 / 249528 / 52816389 capped draws2026-08-09First try
Claude Sonnet 5E-d1a3c0549627f78eMediumRated41.71473189 / 95 / 217501 / 50115795 capped draws2026-08-09First try
Claude Sonnet 5.5E-125c49d283c26a40XHighRated64.41837133 / 54 / 17204 / 20410254 capped draws2026-09-30First try
Claude Sonnet 5.5E-28039f80c11427f6LowRated38.5142276 / 15 / 111202 / 20210115 capped draws2026-09-30First try
Claude Sonnet 5.5E-963d80a1ca649e34MediumRated38.5142278 / 5 / 117200 / 2001005 capped draws2026-09-30First try
North Mini CodeE-194759b182ce3244BaselineRated36.0138273 / 167 / 118358 / 358129167 capped draws2026-07-02First try
North Mini CodeE-c309b463b29efb71BaselineRated6.190211 / 65 / 462538 / 53820865 capped draws2026-07-11Repaired
DeepSeek V4 FlashE-3f6e8607f2a8e080NoneRated21.6115038 / 93 / 253384 / 38414093 capped draws2026-09-03First try
DeepSeek V4 FlashE-563444f33259817eHighRated33.21337155 / 8 / 279442 / 4441628 capped draws2026-09-03Repaired
DeepSeek V4 FlashE-e3ed177071e23d5cXHighRated20.6113513 / 97 / 238348 / 34815297 capped draws2026-09-03Repaired
DeepSeek V4 FlashE-f1d9dfb787d0d902HighRated19.1111115 / 82 / 191288 / 28812382 capped draws2026-07-02Repaired
DeepSeek V4 FlashE-fd9da5310ad15cacHighRated51.41628134 / 36 / 94264 / 26410836 capped draws2026-07-01First try
DeepSeek V4 ProE-4ff2db0cd3cd685fXHighRated25.5121390 / 21 / 255366 / 36613821 capped draws2026-09-03Repaired
DeepSeek V4 ProE-a37ae962eab40085HighRated50.21610226 / 28 / 158412 / 41215428 capped draws2026-09-03First try
DeepSeek V4 ProE-f1f954929032d679NoneRated28.8126667 / 128 / 207402 / 402148128 capped draws2026-09-03First try
DeepSeek V4 Pro 0813E-0c50f7e5f5664685HighRated41.6147287 / 266 / 97450 / 450160266 capped draws2026-09-03First try
DeepSeek V4 Pro 0813E-1e760b131dcb416cMaxRated39.21433189 / 13 / 172374 / 37413713 capped draws2026-09-03First try
DeepSeek V4 Pro 0813E-6fee992ed0716fe2NoneRated31.61311100 / 87 / 183370 / 37013487 capped draws2026-09-03First try
DeepSeek V4.1 FlashE-451e85db0b7186b9MaxRated51.31626119 / 8 / 73200 / 2001008 capped draws2026-09-18First try
DeepSeek V4.1 FlashE-7a584639f9afeb6eNoneRated41.4146859 / 56 / 79194 / 1949756 capped draws2026-09-18First try
DeepSeek V4.1 FlashE-f2fb237cd6cbe1c7HighRated56.2170576 / 99 / 11186 / 1869399 capped draws2026-09-18First try
Ember-1E-02455866393318c8HighRated45.0152654 / 104 / 52210 / 210105104 capped draws2026-09-30First try
Ember-1E-12ebb30a83fbce17MaxRated62.41804158 / 3 / 47208 / 2081043 capped draws2026-09-30First try
Ember-1E-1f80bcad3abfdb70NoneRated42.3148357 / 83 / 68208 / 20810483 capped draws2026-09-30First try
Gemini 3.1 Pro PreviewE-410a21c6583e8bedHighRated57.31724132 / 5 / 59196 / 196985 capped draws2026-09-30First try
Gemini 3.1 Pro PreviewE-f28bdcdb0a25d68eMediumRated33.0133337 / 68 / 105210 / 21010568 capped draws2026-09-30First try
Gemini 3.1 Pro PreviewE-f378a905f3dfc53dLowRated36.0138154 / 26 / 122202 / 20210126 capped draws2026-09-30First try
Gemini 3.1 Flash LiteE-7669b8a03ef19548MediumRated31.7131350 / 172 / 116338 / 338124172 capped draws2026-07-02Repaired
Gemini 3.1 Flash LiteE-cc0af0bfa6a9a29fNoneRated15.7105624 / 60 / 228312 / 31212160 capped draws2026-07-02Repaired
Gemini 3.5 FlashE-1802f43944b4b6f0HighRated78.72066310 / 15 / 29354 / 35414615 capped draws2026-09-03First try
Gemini 3.5 FlashE-b33eea8b864e22bfLowWaiting——0 / 0 / 00 / 00—2026-07-21First try
Gemini 3.5 FlashE-c175c9b470a4d275MediumRated58.71746236 / 6 / 108350 / 3501376 capped draws2026-09-03First try
Gemini 3.5 FlashE-e238344b586c2d45MinimalRated37.01398133 / 86 / 145364 / 36413586 capped draws2026-09-03First try
Gemini 3.5 Flash LiteE-21c0edac8ac36f2eMinimalRated37.11400187 / 113 / 284584 / 584171113 capped draws2026-07-24First try
Gemini 3.5 Flash LiteE-4b4f303670ce9fb6MediumRated37.21400195 / 91 / 286572 / 57215891 capped draws2026-07-24First try
Gemini 3.5 Flash LiteE-77d8df8cd762fd09MediumRated38.21417227 / 111 / 294632 / 632177111 capped draws2026-07-24First try
Gemini 3.5 Flash LiteE-85d9dd9fbf531322HighRated33.61343125 / 101 / 242468 / 468150101 capped draws2026-07-24First try
Gemini 3.5 Flash LiteE-cf51875df5447bc2MinimalRated33.71344140 / 97 / 269506 / 50616297 capped draws2026-07-24First try
Gemini 3.6 FlashE-27590b9ddebe06e6MediumRated41.31467123 / 331 / 132586 / 586159331 capped draws2026-07-24First try
Gemini 3.6 FlashE-7484f4e7d8863a3bMediumRated83.72147283 / 6 / 15304 / 3041346 capped draws2026-07-24First try
Gemini 3.6 FlashE-df0493ecef384a6aHighRated55.71697271 / 63 / 146480 / 48316763 capped draws · 1 fault2026-07-24First try
Gemini 3.6 FlashE-e0c4f14c94c0a42aMinimalRated27.7124868 / 140 / 286494 / 494156140 capped draws2026-07-24First try
Gemini 3.6 FlashE-e9260a0da3a64563HighRated34.2135389 / 231 / 192512 / 512153231 capped draws2026-07-24Repaired
Gemini 3.6 FlashE-e9733de94d982adeMinimalRated32.51326153 / 100 / 269522 / 522158100 capped draws2026-07-24First try
Gemini 3.8 FlashE-08c289c1f3e3a57dMediumRated58.81747199 / 48 / 95342 / 34213348 capped draws2026-09-03First try
Gemini 3.8 FlashE-7eaea1adf86737d5HighRated46.91556237 / 35 / 170442 / 44215735 capped draws2026-09-03First try
Gemini 3.8 FlashE-98517ee3374540f4LowRated46.01541159 / 174 / 105438 / 438156174 capped draws2026-09-03First try
Gemma 4 31BE-caaa54d3c88e6570NoneRated38.31418139 / 71 / 142352 / 35213171 capped draws2026-07-02First try
GPT-4.1E-f50ec6b60d5b85daNoneRated48.61584177 / 26 / 120323 / 32413626 capped draws · 1 fault2026-07-02First try
GPT-4.1 NanoE-e117cfcfd3d0bf38ReasoningRated38.11414208 / 106 / 250564 / 564172106 capped draws2026-07-12First try
GPT-5E-3e63b136f656e976HighRated37.61407133 / 43 / 152328 / 32812543 capped draws2026-07-02First try
GPT-5E-4370194a9beec334LowWaiting——0 / 0 / 00 / 00—2026-07-21First try
GPT-5E-adee794ecd761044MediumRated20.4113152 / 45 / 219316 / 31612345 capped draws2026-07-02First try
GPT-5.4E-9879a37f54e31cffXHighRated87.02199408 / 8 / 22438 / 4381408 capped draws2026-08-09First try
GPT-5.4E-d4fa7dbb9458c464MediumRated100.02408431 / 5 / 4440 / 4401505 capped draws2026-08-09First try
GPT-5.4E-ed2ff19b1858f2c4NoneRated65.51855343 / 36 / 77456 / 45615036 capped draws2026-08-09First try
GPT-5.4 MiniE-62424dfd649cbac9MediumRated54.11671194 / 19 / 93306 / 30812719 capped draws · 2 faults2026-07-02First try
GPT-5.4 MiniE-ea1cb793f92b3cffNoneRated31.2130453 / 115 / 148316 / 316124115 capped draws2026-07-02First try
GPT-5.4 NanoE-9257cc1e94bf4b17MediumRated25.8121858 / 74 / 188320 / 32012074 capped draws2026-07-02First try
GPT-5.4 NanoE-9eb27042bf28d67cNoneRated44.81522118 / 69 / 111298 / 29812169 capped draws2026-07-09First try
GPT-5.4 NanoE-a8887794a1195b75NoneRated38.7142598 / 71 / 141310 / 31012671 capped draws2026-07-02Repaired
GPT-5.4 NanoE-c48c1aed1cdecc72MediumRated0.08048 / 16 / 274298 / 30012816 capped draws · 2 faults2026-07-09Repaired
GPT-5.5E-58178b9b32a94ca0NoneRated41.8147445 / 240 / 49334 / 334127240 capped draws2026-07-02First try
GPT-5.5E-8c61292c31db2722XHighRated60.41773159 / 100 / 31290 / 290119100 capped draws2026-07-02First try
GPT-5.5E-e4496be687faac9dMediumRated48.81587102 / 204 / 18324 / 324130204 capped draws2026-07-02Repaired
GPT-5.6 LunaE-65def22b992d7636XHighRated64.01830313 / 0 / 107420 / 420140—2026-08-09First try
GPT-5.6 LunaE-87b37ed5ff73def5MediumRated40.31451180 / 74 / 251505 / 50516074 capped draws2026-08-09Repaired
GPT-5.6 LunaE-9502190155453416NoneRated25.4121158 / 89 / 285432 / 43214489 capped draws2026-08-09First try
GPT-5.6 SolE-544e51eb5e949386MediumRated53.01654193 / 99 / 132424 / 42414199 capped draws2026-08-09First try
GPT-5.6 SolE-72b9641e74736185NoneRated63.31820313 / 2 / 109424 / 4241432 capped draws2026-08-09First try
GPT-5.6 SolE-ecb408c0fdea8489XHighRated59.01751299 / 10 / 129438 / 43814610 capped draws2026-08-09First try
GPT-5.6 TerraE-485f592e036999acNoneRated45.11528247 / 199 / 194640 / 640207199 capped draws2026-09-03First try
GPT-5.6 TerraE-9c5999eb42ee9ba7MediumRated63.41821309 / 5 / 92406 / 4061575 capped draws2026-09-03First try
GPT-5.6 TerraE-b29d36ceeede0dbfXHighRated57.91734259 / 66 / 89414 / 41416166 capped draws2026-09-03Repaired
GPT-6 AstraE-7f329073c716559bMediumRated61.41789265 / 24 / 81370 / 37014324 capped draws2026-09-05First try
GPT-6 AstraE-7fbf151da7860da4LowRated82.32124340 / 12 / 20372 / 37214812 capped draws2026-09-05First try
GPT-6 AstraE-fc5055140bf78475XHighRated96.62353343 / 0 / 9352 / 352137—2026-09-05First try
GPT-6 LunaE-627d6b4b2cf8914dNoneRated22.4116429 / 24 / 149202 / 20210124 capped draws2026-09-22First try
GPT-6 LunaE-9196605310f7c096MediumRated36.6139145 / 71 / 86202 / 20210171 capped draws2026-09-22First try
GPT-6 LunaE-a9638bc6838d4df0XHighRated29.81282123 / 1 / 290414 / 4142071 capped draw2026-09-22First try
GPT-6 SolE-2308e2afec906ba2XHighRated11.498715 / 5 / 168188 / 188945 capped draws2026-09-22First try
GPT-6 SolE-5303370b62ef3c71NoneRated46.81555104 / 8 / 90202 / 2021018 capped draws2026-09-22First try
GPT-6 SolE-701cd211886854b0MediumRated34.6135943 / 42 / 103188 / 1889442 capped draws2026-09-22First try
GPT-6.1 SolE-31adc58b02c1372fMediumRated57.21722144 / 3 / 61208 / 2081043 capped draws2026-10-01First try
GPT-6.1 SolE-368b9d3008a9770fXHighRated59.51759152 / 0 / 56208 / 208104—2026-10-01First try
GPT-6.1 SolE-bd0e592cac00d46aLowRated43.2149893 / 22 / 89204 / 20410222 capped draws2026-10-01First try
Mercury 2.5 PreviewE-baf0b5208b4d0df5HighRated27.4124469 / 104 / 211384 / 384135104 capped draws2026-09-03First try
Ling 3.0 FlashE-3c618b88b6bdb039BaselineRated30.4129299 / 109 / 200408 / 408150109 capped draws2026-07-24First try
Ling 3.0 FlashE-dd34dd6c69ef6a73EnabledRated20.711363 / 8 / 1728 / 30148 capped draws2026-07-24First try
Ling 3.0 FlashE-f9af396559c3a1cdBaselineRated38.31419105 / 82 / 165352 / 35212182 capped draws2026-07-24First try
LongCat 2.0E-9f5585b5fd96f2c3NoneRated37.61407125 / 86 / 155366 / 36613586 capped draws2026-07-24First try
LongCat 2.0E-ed0f8e084958eebcNoneRated36.31386106 / 135 / 125366 / 366130135 capped draws2026-07-24First try
Muse Glimmer 30BE-1693e15cc9beba1fXHighRated30.0128558 / 105 / 190353 / 354148105 capped draws · 1 fault2026-09-03First try
Muse Glimmer 30BE-6c4ddba2a587c771LowRated34.81362118 / 95 / 175388 / 38814395 capped draws2026-09-03First try
Muse Glimmer 30BE-7a7fb1f65482c8c1MediumRated23.9118746 / 95 / 223364 / 36414095 capped draws2026-09-03First try
Muse Spark 1.2E-052cdf1e5975b860MediumRated68.01896361 / 14 / 73448 / 44814614 capped draws2026-08-13First try
Muse Spark 1.2E-60e0feec8e72ba89XHighRated50.11607271 / 51 / 182504 / 50415951 capped draws2026-08-13First try
Muse Spark 1.2E-d883d9ce56d6c656MinimalRated34.3135589 / 178 / 179446 / 446148178 capped draws2026-08-13First try
Muse Spark 1.3E-4a0018273c954f49MinimalRated25.8121850 / 92 / 218360 / 36014092 capped draws2026-09-03First try
Muse Spark 1.3E-d486cf265379dff2XHighRated63.81828250 / 2 / 90342 / 3421372 capped draws2026-09-03First try
Muse Spark 1.3E-e1d07e565134ac39MediumRated60.11769269 / 0 / 97366 / 368143—2026-09-03First try
Minimax M3E-444510032bc433fcNoneRated45.31531149 / 68 / 119336 / 33612568 capped draws2026-07-02First try
Minimax M3E-e0a841a9daa66219EnabledRated21.9115562 / 19 / 241322 / 32213019 capped draws2026-07-02Repaired
Mistral Medium 3.5E-ebdfd5028b9c1ab9NoneRated10.897721 / 35 / 308364 / 36414035 capped draws2026-09-08First try
Kimi K2.7 CodeE-4935e918b1e70ea1EnabledRated35.41373141 / 9 / 181331 / 3321329 capped draws · 1 fault2026-07-02Repaired
Kimi K3E-58aadd759ee9fa72HighRated52.81651237 / 79 / 162478 / 48314279 capped draws2026-07-24First try
Kimi K3E-dbb89dcf5242a5a0MaxRated54.81683285 / 53 / 164502 / 50817753 capped draws2026-07-24Repaired
Kimi K3E-fb8801908d28001fLowRated42.11480127 / 363 / 135625 / 625170363 capped draws2026-07-24First try
Nemotron 3 Ultra 550B A55BE-0ce5e196701b51f3NoneRated45.21530109 / 49 / 122280 / 28010849 capped draws2026-07-02First try
Nemotron 3 Ultra 550B A55BE-b851008baae8f441MediumRated42.91493126 / 66 / 122314 / 31412866 capped draws2026-07-02Repaired
Nemotron 3 Ultra 550B A55BE-ce064a9927030b28HighRated24.1119150 / 70 / 192312 / 31212770 capped draws2026-07-11Repaired
o3E-01ad69b67b42a9e7HighRated53.91669282 / 28 / 178488 / 48815128 capped draws2026-07-03First try
o3E-21b0558e9f2190f7HighRated54.61679289 / 5 / 180474 / 4741425 capped draws2026-07-03First try
o3E-428923c2eb87dc7aMediumRated37.91412123 / 63 / 144330 / 33012763 capped draws2026-07-02First try
o3E-5e8b87fcfa2225fdHighRated40.21449245 / 175 / 272692 / 692207175 capped draws2026-07-03First try
o3E-cb2bd51b4adfa607LowRated20.5113234 / 156 / 358548 / 548162156 capped draws2026-07-21First try
GPT-OSS 120BE-bf01371eb32d6cc7MediumRated34.91363104 / 63 / 195362 / 36214863 capped draws2026-09-03First try
GPT-OSS 120BE-cacdbc8932bb28b9LowRated38.21416162 / 68 / 224454 / 45416368 capped draws2026-09-03First try
Laguna S 2.1E-8461eb1b16e40129NoneRated46.41548134 / 52 / 124310 / 31011952 capped draws2026-07-24Repaired
Laguna S 2.1E-c58ec61528547516NoneRated38.41420132 / 72 / 142346 / 34612972 capped draws2026-07-24First try
Laguna S 2.1E-ffd72d2c5c11728aEnabledRated37.01397203 / 90 / 297590 / 59017390 capped draws2026-07-24First try
Qwen3.7 MaxE-24581eb49b81bf8fEnabledRated20.3112945 / 82 / 237364 / 36413982 capped draws2026-07-02Repaired
Qwen3.7 MaxE-8a70cd704fcbcf6fNoneRated53.11656150 / 94 / 70314 / 31412694 capped draws2026-07-02First try
Qwen3.7 PlusE-1e5dceaf2ba3ca9aEnabledRated41.81475220 / 100 / 224544 / 544206100 capped draws2026-07-02Repaired
Qwen3.7 PlusE-5e09f0c994a59f3cNoneRated22.1115936 / 70 / 208314 / 31412270 capped draws2026-07-03Repaired
Qwen3.8 2.4t A95BE-5c62bb2678affbe1MediumRated44.3151473 / 173 / 124370 / 370140173 capped draws2026-09-03First try
Qwen3.8 2.4t A95BE-7f2df030d9d6c2c3LowRated31.4130855 / 142 / 165362 / 362154142 capped draws2026-09-03Repaired
Qwen3.8 2.4t A95BE-8eaba1f886272536XHighRated45.91540154 / 125 / 139418 / 418160125 capped draws2026-09-03First try
Qwen3.8 27BE-7d4183592c1053f4NoneWaiting——0 / 0 / 00 / 24024 faults2026-09-03First try
Qwen3.8 27BE-8e1be1631d467764MediumRated35.7137668 / 201 / 95364 / 364131201 capped draws2026-09-03Repaired
Qwen3.8 27BE-bc41613035d2e499XHighRated59.31756267 / 10 / 101378 / 37814710 capped draws2026-09-03First try
Qwen3.8 FlashE-2eb3841ab5cbf0bbEnabledRated41.91476117 / 159 / 160436 / 436164159 capped draws2026-09-03First try
Qwen3.8 FlashE-e6f122ba71f78c3dNoneRated33.11334145 / 161 / 288594 / 594207161 capped draws2026-09-03Repaired
Qwen3.8 MaxE-06acc10727220528XHighRated32.2132085 / 66 / 207358 / 35815266 capped draws2026-08-08First try
Qwen3.8 MaxE-60f1c4442483d5b0MinimalRated25.4121158 / 95 / 225378 / 37814095 capped draws2026-08-08First try
Qwen3.8 MaxE-ef3bbb2ff5470c0fMediumRated37.9141194 / 144 / 176414 / 414154144 capped draws2026-08-08First try
Qwen3.8 Max 0902E-8dbf1b087995f71fXHighRated55.9170198 / 72 / 24194 / 1949772 capped draws2026-09-18First try
Qwen3.8 Max 0902E-974c9e1778fdfacaMediumRated30.2128844 / 33 / 131208 / 20810433 capped draws2026-09-18Repaired
Qwen3.8 Max 0902E-e6c7f3ef8643f8a8LowRated36.0138230 / 72 / 82184 / 1849272 capped draws2026-09-18Repaired
Ox AlphaE-3869622aa388e835MaxRated53.41661233 / 5 / 132370 / 3701435 capped draws2026-08-22First try
Ox AlphaE-5661caf556b12391LowRated44.41516175 / 130 / 143448 / 448164130 capped draws2026-08-22Repaired
Ox AlphaE-98157b387f582b30LowRated29.0127059 / 93 / 202354 / 35414993 capped draws2026-08-22Repaired
Ox AlphaE-c6a1445bccefbe07HighRated54.61680188 / 119 / 73380 / 380151119 capped draws2026-08-22Repaired
Ox AlphaE-d28e485f395cbca4HighRated49.71602255 / 37 / 150442 / 44215937 capped draws2026-08-22First try
Ox AlphaE-dc2b7cd047c7694aMaxRated40.41452166 / 53 / 209428 / 42817953 capped draws2026-08-22First try
Ox AlphaE-e66ff5a9cbd5132fLowRated41.91476174 / 77 / 157408 / 40814677 capped draws2026-08-22First try
Ox AlphaE-e70cadce2bb0e8b1MaxRated53.41661206 / 12 / 150368 / 36814112 capped draws2026-08-22First try
Space Bunny AlphaE-6e1db8c82fa295edXHighRated51.91637102 / 58 / 50210 / 21010558 capped draws2026-09-30Repaired
Space Bunny AlphaE-779d556823e36368MediumRated38.6142457 / 39 / 112208 / 20810439 capped draws2026-09-30First try
Step 3.7 FlashE-4b0ce2bc67b08d8aHighRated9.896126 / 17 / 263306 / 30612817 capped draws2026-07-02Repaired
Hy3 PreviewE-29e8870e43d717e5HighRated51.01623180 / 61 / 85326 / 32613561 capped draws2026-07-02First try
Hy3 PreviewE-3407ff2dd1928eb5NoneRated60.81780191 / 52 / 59302 / 30211952 capped draws2026-07-02First try
Hy4 PreviewE-7f22e7a7766baabaLowRated43.61504184 / 22 / 200406 / 40617222 capped draws2026-09-03First try
Hy4 PreviewE-b237904f2bbb5756NoneRated40.51454153 / 64 / 219436 / 43616464 capped draws2026-09-03First try
Hy4 PreviewE-c7c1dfb86d5797f2HighRated44.91524105 / 211 / 102418 / 418158211 capped draws2026-09-03First try
InklingE-46c7f693daaae605MediumRated30.0128589 / 151 / 254494 / 494153151 capped draws2026-07-24First try
InklingE-9e638fc0ac98df4fNoneRated24.5119736 / 121 / 175332 / 332136121 capped draws2026-07-24First try
InklingE-ab1de1dc51400446MaxRated25.5121422 / 178 / 258458 / 458149178 capped draws2026-07-24First try
InklingE-bc7c657b08ebac66NoneRated18.1109410 / 99 / 211320 / 32012999 capped draws2026-07-24First try
Inkling SmallE-40197ff2c5984de1MaxRated31.1130373 / 138 / 189400 / 400148138 capped draws2026-08-09First try
Inkling SmallE-52cb66309e46f2f3NoneRated24.3119375 / 62 / 280417 / 41715062 capped draws2026-08-09First try
Inkling SmallE-53de0c492cdf9f2fMediumRated9.695811 / 52 / 321384 / 38414152 capped draws2026-08-09First try
Grok 4.5E-1c8e452ede41ea2eHighRated69.11913348 / 93 / 45486 / 48614893 capped draws2026-07-24Repaired
Grok 4.5E-7ee1b68d1249ac22LowRated43.11495191 / 442 / 191824 / 825207442 capped draws2026-07-24First try
Grok 4.5E-d709aeb6802f9289MediumRated67.11880236 / 22 / 46304 / 30612422 capped draws · 2 faults2026-07-24First try
Grok 4.6E-140f77709da43a59LowRated52.51646206 / 48 / 134388 / 38814948 capped draws2026-09-03First try
Grok 4.6E-1f493e5801fda3ebMediumRated50.81619267 / 152 / 159578 / 578207152 capped draws2026-09-03First try
Grok 4.6E-934139cf98cd9b6dXHighRated45.11528101 / 224 / 99424 / 424161224 capped draws2026-09-03First try
Grok 4.7E-4e41c6896cd841aeMediumRated61.31787143 / 15 / 42200 / 20010015 capped draws2026-09-30First try
Grok 4.7E-675aab0d0910fe06XHighRated46.51550112 / 1 / 89202 / 2021011 capped draw2026-09-30First try
Grok 4.7E-e3041fe95bb93074LowRated30.3129123 / 68 / 111202 / 20210168 capped draws2026-09-23First try
Grok Build 0.1E-f1ded648f3ab17dcEnabledRated35.91379167 / 116 / 261544 / 544207116 capped draws2026-07-02Repaired
MiMo-V2.5E-1208f50b0908ecb4EnabledRated30.11287125 / 5 / 200330 / 3301275 capped draws2026-07-02Repaired
MiMo-V2.5E-2a71bee21bd7c0b9EnabledRated28.8126760 / 73 / 169302 / 30212473 capped draws2026-07-02Repaired
MiMo-V2.5E-2cdd8ae895784956NoneRated45.01526136 / 22 / 140298 / 29812322 capped draws2026-07-02First try
MiMo-V2.5E-8478c64d84536b61HighRated19.411162 / 39 / 1960 / 603039 capped draws2026-07-02Repaired
MiMo-V2.5E-912a4a40bbdcbd45NoneRated33.2133791 / 66 / 173330 / 33013666 capped draws2026-07-02First try
MiMo-V2.5E-a168350bd057f924NoneRated32.3132267 / 98 / 151316 / 31613198 capped draws2026-07-01First try
MiMo-V2.5-ProE-43e640c1d46cb4daEnabledRated56.11703313 / 59 / 146518 / 51816459 capped draws2026-07-02Repaired
MiMo-V2.5-ProE-9ce4191c7f1f3b3eNoneRated32.1132091 / 96 / 167354 / 35413496 capped draws2026-07-02First try
MiMo-V2.6-FlashE-b99c8243722f2cd0NoneRated55.11688103 / 61 / 34198 / 1989961 capped draws2026-09-22First try
MiMo-V2.6-FlashE-b9d8a9914f18fe13EnabledRated44.41516102 / 2 / 94198 / 198992 capped draws2026-09-22First try
MiMo-V2.6-ProE-6e0c417b7c1bd882NoneRated36.0138132 / 79 / 87198 / 1989979 capped draws2026-09-22Repaired
MiMo-V2.6-ProE-f0285d53fcb42c03EnabledRated68.11896162 / 0 / 34196 / 19698—2026-09-30First try
GLM-5.2E-219f4abe33922e82XHighRated44.91524178 / 174 / 136488 / 488171174 capped draws2026-09-03First try
GLM-5.2E-5c3b7f5666a38043NoneRated31.2130579 / 78 / 149306 / 30611978 capped draws2026-07-11First try
GLM-5.2E-8ae36a8fda030541HighRated37.8141056 / 202 / 86344 / 344146202 capped draws2026-09-03First try
GLM-5.2E-c8076ea61de8da45NoneRated20.8113845 / 30 / 205280 / 28011930 capped draws2026-07-02First try
GLM-5.2E-f889d782e3cce209HighRated33.01334118 / 20 / 176314 / 31412820 capped draws2026-07-11Repaired
GLM-5.2E-f8acb170edf2e5c4NoneRated29.9128463 / 109 / 182354 / 354142109 capped draws2026-09-03Repaired
GLM-5.3E-17767e91e6f49c66MaxRated75.32012281 / 24 / 33338 / 33813324 capped draws2026-09-03First try
GLM-5.3E-71ce958d7b654d8aHighRated44.41517188 / 74 / 172434 / 43416174 capped draws2026-09-03First try
GLM-5.3E-7c77e01c809e543bLowRated52.81651213 / 66 / 103382 / 38414766 capped draws2026-09-03First try
GLM-5.3 FlashE-18eb21100be69d1bHighRated55.91701218 / 11 / 131360 / 36613711 capped draws2026-09-03First try
GLM-5.3 FlashE-3d3e1d24632521c6LowRated34.5135760 / 210 / 154424 / 424161210 capped draws2026-09-03Repaired
GLM-5.3 FlashE-4d0fb8c838c2a646MaxRated52.91653407 / 8 / 221636 / 6362078 capped draws2026-09-03First try
GLM-5.3 FlashXE-676808a0be64a7eaLowRated54.11671106 / 47 / 41194 / 1949747 capped draws2026-09-22First try
GLM-5.3 FlashXE-ca17c17e962ac5aaMaxRated36.6139279 / 1 / 122202 / 2021011 capped draw2026-09-22First try
GLM-5.3 FlashXE-fecc1078f898884eHighRated61.51791151 / 5 / 42198 / 198995 capped draws2026-09-22First try