Find models

97 models shown.

Browse models

Source: Overall Models Models: 97
Model results directory for DuelLab GameBench 2
Rank Model Provider Score Reasoning settings tested By game Cost / player Last tested Status
1GPT-6 AstraOpenAI89.7XHigh94.4Medium89.6Low85.1$0.652026-10-26Complete
2Claude Opus 5.5Anthropic88.8XHigh95.1Medium93.0Low78.2$0.812026-10-26Complete
3Claude Fable 5.1Anthropic88.6XHigh94.4Medium84.8Low86.6$2.322026-10-26Complete
4GPT-6.1 SolOpenAI86.0XHigh92.7Medium87.5Low77.8$0.132026-10-26Complete
5Gemini 4 ArgonGoogle83.3High90.1Medium78.7Low81.0$0.212026-10-24Complete
6Kimi K3.1 ProMoonshot82.9Max85.7High82.3Low80.8$0.282026-10-24Partial 3/3
7Claude Opus 5Anthropic78.1XHigh86.1Medium76.5None71.8$0.702026-10-26Complete
8GPT-6 SolOpenAI74.7XHigh80.6Medium76.4None67.0$0.112026-10-26Complete
9GPT-5.6 SolOpenAI68.7XHigh81.1Medium68.0None57.1$0.382026-10-26Complete
10Claude Fable 5Anthropic67.6XHigh76.9Medium65.8Low60.2$0.762026-10-26Complete
11Muse WonderMeta66.4XHigh78.8Medium63.5Minimal56.8$0.292026-10-24Complete
12GLM-5.3Zhipu65.7Max73.5High72.0Low51.4$0.252026-10-26Complete
13Grok 4.7xAI65.0XHigh73.2Medium73.4Low48.4$0.422026-10-26Complete
14DeepSeek V4.1 Flash 1017DeepSeek63.4Max71.9High66.7None51.7$0.042026-10-24Complete
15Claude Sonnet 5.5Anthropic61.7XHigh91.8Medium51.9Low41.3$0.222026-10-26Complete
16Grok 4.6xAI61.1XHigh66.4Medium71.4Low45.4$0.132026-10-26Complete
17Gemini 3.8 FlashGoogle61.0High66.2Medium61.2Low55.5$0.082026-10-26Complete
18Muse Spark 1.3Meta59.7XHigh70.9Medium66.8Minimal41.5$0.112026-10-26Complete
19Muse Spark OpenMeta58.3XHigh63.6Medium55.0Low56.3$0.062026-10-24Partial 3/3
20Grok 4.5xAI58.3High63.5Medium61.9Low49.4$0.072026-10-26Complete
21GLM-5.3 FlashXZhipu57.6Max68.6High52.3Low51.9$0.032026-10-26Complete
22Claude Haiku 5.5Anthropic57.3XHigh74.9Medium57.6None39.3$0.022026-10-24Partial 3/3
23GLM-5.3 FlashZhipu56.9Max59.1High63.3Low48.2$0.00812026-10-26Complete
24Qwen3.8 Max 0902Alibaba55.3XHigh70.2Medium45.0Low50.7$0.212026-10-26Complete
25GPT-5.4OpenAI55.2XHigh63.5Medium55.3None46.8$0.632026-10-26Complete
26Qwen3.8 2.4T A95BAlibaba54.6XHigh68.7Medium43.8Low51.2$0.232026-10-26Complete
27DeepSeek V4.1 FlashDeepSeek53.7Max69.0High55.6None36.5$0.022026-10-26Complete
28Muse Spark 1.2Meta53.7XHigh59.7Medium59.3Minimal42.0$0.072026-10-26Complete
29Hy4 PreviewTencent53.3High64.5Low51.1None44.2$0.092026-10-26Complete
30Gemini 3.6 FlashGoogle52.5High64.6Medium52.5Minimal40.4$0.252026-10-26Complete
31Ember-1Fireworks AI52.4Max65.1High54.7None37.4$0.172026-10-26Complete
32Ox AlphaOther52.3Max68.3High47.3Low41.2$0.002026-10-26Complete
33Claude Opus 4.8Anthropic51.6XHigh63.8Medium48.3None42.8$0.442026-10-26Complete
34Gemini 3.5 FlashGoogle51.1High64.1Medium57.4Minimal31.9Low31.9Minimal35.5Low28.2$0.182026-10-26Complete
35GPT-5.5OpenAI50.7XHigh61.6Medium53.1None37.5$1.112026-10-26Complete
36Qwen3.8 MaxAlibaba50.4XHigh51.9Medium50.7Minimal48.6$0.192026-10-26Complete
37GPT-6 LunaOpenAI49.0XHigh57.9Medium43.9None45.1$0.00632026-10-26Complete
38Claude Opus 4.5Anthropic48.9High50.0Budgeted50.0Medium48.8Budgeted48.8None47.9Historical44.3$0.252026-10-26Complete
39Kimi K3Moonshot48.8Max45.1High49.6Low51.6$0.282026-10-26Complete
40Claude Sonnet 5Anthropic48.1XHigh56.5Medium44.0None43.8$0.162026-10-26Complete
41Mercury 3Inception47.8High59.6Medium45.0None38.9$0.032026-10-24Partial 3/3Many programs needed repairMany programs failed
42GPT-5.6 TerraOpenAI47.2XHigh54.8Medium51.0None35.9$0.192026-10-26Complete
43Gemini 3.1 Pro PreviewGoogle46.2High66.2Medium42.3Low30.2$0.152026-10-26Complete
44Beam 1.0 501B A23BOther44.7XHigh55.6Medium37.7Low40.9$0.022026-10-24CompleteMany programs needed repair
45GLM-5.2Zhipu44.5XHigh44.5High47.8Medium47.8High51.6Medium44.0None41.3Reasoning44.8Reasoning34.3$0.102026-10-26CompleteMany programs needed repair
46DeepSeek V4 Pro 0813DeepSeek43.8Max55.9High46.9None28.5$0.102026-10-26CompleteMany programs failed
47DeepSeek V4 ProDeepSeek43.5XHigh48.7High53.7None28.2$0.062026-10-26CompleteMany programs needed repairMany programs failed
48GPT-5OpenAI43.2High49.5Medium38.6Low41.5$0.192026-10-26Partial 3/3
49GPT-5.6 LunaOpenAI41.6XHigh55.9Medium43.0None25.9$0.012026-10-26Complete
50Minimax M3.1 FlashMiniMax38.1XHigh40.0Medium42.7Low31.5$0.002026-10-24Partial 3/3
51Seed 2.0 CodeByteDance36.4High43.0Medium40.1Low26.1$0.042026-10-26CompleteMany programs needed repair
52o3OpenAI36.2High32.1Medium34.3Low42.3$0.062026-10-26CompleteMany programs failed
53Qwen3.8 27BAlibaba34.6XHigh45.5Medium40.8None17.5$0.092026-10-24Partial 3/3Many programs failed
54DeepSeek V4 FlashDeepSeek34.2XHigh36.6High34.9Medium34.9High44.0Medium30.2None31.1$0.00412026-10-26Complete
55Space Bunny AlphaOther33.4XHigh36.8Medium35.8Low27.6$0.002026-10-26CompleteMany programs needed repairMany programs failed
56Gemini 3.5 Flash LiteGoogle33.1High32.9Medium27.2Minimal39.2$0.042026-10-26Complete
57Inkling SmallThinking Machines31.8Max36.2Medium29.8None29.4$0.022026-10-26Complete
58Muse Glimmer 30BMeta30.3XHigh35.9Medium31.4Low23.7$0.012026-10-26CompleteMany programs failed
59GPT-OSS 120BOpenAI30.2High35.1Medium31.2Low24.3$0.00332026-10-26CompleteMany programs failed
60Nemotron 3 Ultra 550B A55BNVIDIA27.3High24.0Medium27.7None30.3$0.032026-10-26Partial 3/3Many programs needed repairMany programs failed
61InklingThinking Machines26.7Max33.1Medium19.2None27.7$0.102026-10-26CompleteMany programs failed
62Step 3.7 FlashStepFun24.2High15.5Medium26.4Low30.6$0.032026-10-24CompleteMany programs needed repairMany programs failed
63Mercury 2.5 PreviewInception21.9High21.1Medium20.3None24.2$0.00122026-10-26CompleteMany programs failed
64Gemini 3.1 Flash LiteGoogle16.2High17.4Medium20.1None11.1$0.012026-10-25Partial 3/3Many programs needed repairMany programs failed
65Solar Mini 4Upstage8.2XHigh13.8Medium5.7None5.1$0.00842026-10-24Partial 3/3Many programs failed
66Granite 4.2 8BIBM1.6Full0.0Low4.9Non-thinking0.0$0.00452026-10-24Partial 3/3Many programs failed
PPareto 26.10Unbiased90.6Provider90.6$0.032026-10-24No Overall rankIntensive not supportedBalanced not supported
PPareto 26.10 PreviewUnbiased89.7Provider89.7$0.032026-10-24No Overall rankIntensive not supportedBalanced not supported
PMiMo-V2.6-ProXiaomi62.1Enabled73.2None51.0$0.032026-10-26No Overall rankIntensive not supported
PStep 5 PreviewStepFun58.6Medium83.0Low34.3$0.192026-10-24No Overall rankMissing Intensive
PMiMo-V2.6-FlashXiaomi50.4Enabled60.2None40.5$0.012026-10-26No Overall rankIntensive not supported
PQwen3.8 FlashAlibaba48.4Enabled63.1None33.8$0.022026-10-26No Overall rankIntensive not supported
PMistral Large 4Mistral46.7High57.9None35.6$0.112026-10-24No Overall rankBalanced not supported
PGlimpseOther42.7Enabled65.8None19.5$0.082026-10-24No Overall rankIntensive not supportedMany programs failed
PGPT-4.1OpenAI42.4None42.4$0.062026-10-26No Overall rankIntensive not supportedBalanced not supported
PKimi K2.7 CodeMoonshot40.6Enabled40.6$0.162026-10-25No Overall rankIntensive not supportedBaseline not supportedMany programs needed repair
PGPT-5.4 MiniOpenAI38.9Medium48.3None29.5$0.222026-10-26No Overall rankMissing Intensive
PMiMo-V2.5-ProXiaomi38.3Enabled46.8None29.8$0.082026-10-26No Overall rankIntensive not supportedMany programs needed repair
PQwen3.7 MaxAlibaba37.6Enabled39.9None35.3$0.062026-10-26No Overall rankIntensive not supportedMany programs needed repair
PGrok Build 0.1xAI34.9Enabled34.9$0.062026-10-26No Overall rankIntensive not supportedBaseline not supportedMany programs needed repair
PLing 3.1 FlashInclusionAI33.3None33.3$0.002026-10-24No Overall rankIntensive not supportedMissing Balanced
PLaguna S 2.1Poolside31.6Enabled31.3None31.9$0.00322026-10-26No Overall rankIntensive not supported
PHy3 PreviewTencent31.4High32.6None30.3$0.00232026-10-26No Overall rankMissing BalancedMany programs failed
PNemotron 3.5 Super VlNVIDIA30.9Enabled50.2None11.7$0.00762026-10-24No Overall rankIntensive not supportedMany programs failed
PMiMo-V2.5Xiaomi30.7High35.9Enabled30.2Medium30.2Reasoning34.1Medium29.4None26.1Reasoning24.6Reasoning27.0$0.022026-10-26No Overall rankMany programs needed repairMany programs failed
PGPT-5.4 NanoOpenAI29.5Medium32.5None26.6$0.032026-10-26No Overall rankMissing IntensiveMany programs failed
PGemma 4 31BGoogle29.2Enabled38.1None20.3$0.00292026-10-24No Overall rankIntensive not supportedMany programs failed
PLongCat 2.0Meituan28.2Enabled27.0None29.4$0.052026-10-26No Overall rankIntensive not supportedMany programs failed
PMinimax M3MiniMax26.7Enabled23.1None30.4$0.052026-10-26No Overall rankIntensive not supportedMany programs needed repairMany programs failed
PNex N2 ProNex AGI26.5Enabled15.9None37.0$0.132026-10-26No Overall rankIntensive not supportedMany programs needed repair
PMistral Medium 3.5Mistral25.9High28.9None22.8$0.122026-10-26No Overall rankBalanced not supportedMany programs needed repair
PQwen3.7 PlusAlibaba25.6Enabled33.0None18.3$0.032026-10-26No Overall rankIntensive not supportedMany programs needed repairMany programs failed
PLing 3.0 FlashInclusionAI24.7Enabled30.6Enabled30.6None18.8None19.0None30.2$0.0002042026-10-26No Overall rankIntensive not supportedMany programs needed repairMany programs failed
PFlint V1.0Other23.6Enabled23.6$0.002026-10-24No Overall rankMissing Intensive, Baseline
PNex N2.5 ProNex AGI19.6High20.6High20.6None18.6None18.6$0.00502026-10-24No Overall rankMissing BalancedMany programs failed
PNorth Mini CodeCohere15.0Enabled23.4None6.7$0.002026-08-05No Overall rankMissing IntensiveMany programs failed
PGPT-4.1 NanoOpenAI11.8Reasoning11.8$0.00222026-10-24No Overall rankIntensive not supportedBalanced not supportedMany programs failed