Explore
Rankings people have built and published. Open one to see the full page and every chart, or start from it and make it yours.
1,000+ rankings made · 50 published
- Sebastian Wilczyński@wolfort · todayArtificial Analysis59.41 Gemini 4 Carbon58.22 Opus 5.556.93 GPT-6 Astra
10 benchmarks · AA-Briefcase v1.1 15%, FrontierCode 2.0-AA 15%, Terminal-Bench-Science-AA 15%
- mypriors@legal · todayArtificial Analysis59.41 Gemini 4 Carbon58.22 Opus 5.556.93 GPT-6 Astra
10 benchmarks · AA-Briefcase v1.1 15%, FrontierCode 2.0-AA 15%, Terminal-Bench-Science-AA 15%
- Andrea Pontillo@justapc · todayWebDev Index
Also Adam's Capabilities Index, AA-II
55.11 Opus 5.554.22 Sonnet 5.551.33 GPT-6 Astra4 benchmarks · Arena WebDev · Image to WebDev 31%, Code2Video-AA 31%, Arena WebDev 31%
- Ignacio@ignacio · todayArtificial Analysis
Also Custom
58.21 Opus 5.554.42 GPT-6.1 Sol54.33 Sonnet 5.510 benchmarks · AA-Briefcase v1.1 15%, FrontierCode 2.0-AA 15%, Terminal-Bench-Science-AA 15%
- Kullywon54@kullywon54 · todayArtificial Analysis57.31 Gemini 4 Carbon55.62 Muse Wonder Full55.13 Sonnet 5.5
6 benchmarks · AA-Briefcase v1.1 25%, FrontierCode 2.0-AA 25%, Terminal-Bench v4-AA 19%
- BoredErica@borederica · todayMy priors61.41 Opus 5.559.02 Gemini 4 Carbon56.93 Sonnet 5.5
9 benchmarks · AA-Briefcase v1.1 12%, FrontierCode 2.0-AA 12%, HLE-Diamond 12%
- 呈 梦@zzz · todayWebDev Index
Also Adam's Capabilities Index, AA-II
60.41 Opus 5.560.12 Sonnet 5.556.83 GPT-6 Astra4 benchmarks · Code2Video-AA 31%, Arena WebDev · Image to WebDev 31%, Arena WebDev 30%
- Sebastian Bahoquez@sebastianbahoquez · todayWebDev Index
Also Adam's Capabilities Index, AA-II
56.31 Opus 5.555.52 Sonnet 5.54 benchmarks · Arena WebDev · Image to WebDev 31%, Code2Video-AA 31%, Arena WebDev 31%
- Project666@project666 · todayAgentic Coding Frontier63.41 Opus 5.561.82 Gemini 4 Carbon61.13 Sonnet 5.5
8 benchmarks · FrontierCode 2.0-AA 20%, Terminal-Bench v4-AA 20%, Arena WebDev 15%
- Judah Fuller@judah · todayWebDev Index
Also Adam's Capabilities Index, AA-II
60.51 Opus 5.560.22 Sonnet 5.556.93 GPT-6 Astra4 benchmarks · Arena WebDev · Image to WebDev 31%, Code2Video-AA 31%, Arena WebDev 31%
- Tim Bormann@tim · todayArtificial Analysis
Also Artificial Analysis copy, PMO, DEV and 1 more
59.21 Gemini 4 Carbon58.12 Opus 5.556.73 GPT-6 Astra10 benchmarks · FrontierCode 2.0-AA 16%, AA-Briefcase v1.1 15%, Terminal-Bench-Science-AA 15%
- Caio Henrique@caio · yesterdayReview
Also General frontier, GADA, Issue Workflow and 1 more
66.51 Opus 5.565.82 Sonnet 5.565.53 Kimi K3.16 benchmarks · Terminal-Bench v4-AA 25%, AA-Briefcase v1.1 20%, DeepSWE 1.1 20%
- Mark Kropf@mark · yesterdayWebDev Index
Also Adam's Capabilities Index, AA-II
60.51 Opus 5.560.22 Sonnet 5.556.93 GPT-6 Astra4 benchmarks · Arena WebDev · Image to WebDev 31%, Code2Video-AA 31%, Arena WebDev 31%
- Aquiles Fernandes@aqui · yesterdayFrontierBench61.21 Opus 5.559.82 GPT-6 Astra55.83 GPT-6.1 Sol
12 benchmarks · FrontierCode 19%, FrontierCode 1.1 Ext 11%, VulcanBench Frontier v4 11%
- Adam's Capabilities Index
Also WebDev Index, AA-II
59.91 Opus 5.556.62 GPT-6 Astra53.33 GPT-6.1 Sol8 benchmarks · AA-Robotics 13%, Agent Arena 13%, Arena WebDev 13%
- Code/Hypertext Noob@codehypertext · 2 days agoMy priors76.51 Opus 5.575.02 GPT-6.1 Terra73.23 GPT-6.1 Sol
12 benchmarks · AA-Omniscience v1.1 Software Engineering 24%, AA-LCR v1.1 21%, FrontierCode 13%
- khalil abdalmjeed@kamkm · 2 days agoMy priors
Also kamkmPriors
77.51 GPT-6 Astra Pro70.72 GPT-6 Astra68.43 GPT-5.6 Sol Pro13 benchmarks · Chess Puzzles 50%, FrontierCode 1.1 14%, SimpleBench 8%
- Nauczymycie.ai@nauczymycie-ai · 2 days agoArtificial Analysis
No ranked models on today's data.
20 benchmarks · GDP.xlsx 5%, Agent Arena 5%, Real-SWE 5%
- SL@sl · 3 days agoArtificial Analysis50.91 Opus 5.548.22 Gemini 4 Carbon47.83 GPT-6 Astra
9 benchmarks · FrontierCode 2.0-AA 67%, AA-Briefcase v1.1 6%, Terminal-Bench-Science-AA 6%
- Brad Hallett@brad · 3 days agoArtificial Analysis59.41 Gemini 4 Carbon58.22 Opus 5.556.93 GPT-6 Astra
10 benchmarks · AA-Briefcase v1.1 15%, FrontierCode 2.0-AA 15%, Terminal-Bench-Science-AA 15%
- Mike Wilson@mike · 4 days agoMy priors62.51 Gemini 4 Carbon59.92 Opus 5.557.93 GPT-6 Astra
10 benchmarks · Terminal-Bench v4-AA 15%, AutomationBench-AA 14%, AA-Briefcase v1.1 14%
- Pier-Luc C.@pier-luc · 4 days agoMy priors75.71 Opus 5.571.32 GPT-6 Astra70.83 Gemini 4 Carbon
8 benchmarks · HLE-Diamond 50%, ClutterBench 20%, MMMU-Pro 10%
- Zerole@aa · 4 days agoMy priors67.41 Opus 5.564.52 Gemini 4 Carbon64.33 GPT-6 Astra
7 benchmarks · Humanity's Last Exam 14%, AA Index v5.0 14%, Arena WebDev 14%
- mypriors.mnufp@latchlilies · 4 days agoGeneral frontier58.21 Opus 5.556.92 GPT-6 Astra54.43 GPT-6.1 Sol
10 benchmarks · AA-Briefcase v1.1 15%, FrontierCode 2.0-AA 15%, Terminal-Bench-Science-AA 15%
- Onemedia Digital@onemedia · 4 days agoMy priors61.81 Opus 5.560.42 Opus 5.558.93 Gemini 4 Carbon
13 benchmarks · Terminal-Bench v4-AA 15%, FrontierCode 2.0-AA 15%, WeirdML v2 9%
- ferret@ferret · 5 days agoPi work mix
Also Scientific coding, Study and sources, File deliverables and 2 more
66.71 Opus 5.566.32 GPT-6 Astra64.63 GPT-6.1 Sol5 benchmarks · Terminal-Bench-Science-AA 25%, AA-LCR v1.1 20%, FrontierCode 2.0-AA 20%
- Davison@davison · 5 days agoAdam's Capabilities Index
Also WebDev Index, AA-II
59.91 Opus 5.556.62 GPT-6 Astra53.33 GPT-6.1 Sol8 benchmarks · AA-Robotics 13%, Agent Arena 13%, Arena WebDev 13%
- TUNG J@tung · 5 days agoDefault mix
Also Policy research desk, My all-rounder
59.41 Gemini 4 Carbon58.22 Opus 5.556.93 GPT-6 Astra10 benchmarks · AA-Briefcase v1.1 15%, FrontierCode 2.0-AA 15%, Terminal-Bench-Science-AA 15%
- Arys Aikyn@arys · 5 days agoDefault mix
Also Artificial Analysis
59.41 Gemini 4 Carbon58.22 Opus 5.556.93 GPT-6 Astra10 benchmarks · AA-Briefcase v1.1 15%, FrontierCode 2.0-AA 15%, Terminal-Bench-Science-AA 15%
- Jacob Jennings@jakej · 5 days agoArtificial Analysis59.41 Gemini 4 Carbon58.22 Opus 5.556.93 GPT-6 Astra
10 benchmarks · AA-Briefcase v1.1 15%, FrontierCode 2.0-AA 15%, Terminal-Bench-Science-AA 15%
- Luiz Guilherme Lopes de Deus Silva@luizguilherme · 5 days agoGeneral frontier73.71 GPT-6 Astra72.92 GPT-6.1 Sol69.43 Sonnet 5.5
8 benchmarks · DeepSWE 1.1 37%, TB 4.0 33%, ARC-AGI-3 18%
- KovD3v@kovd3v · 6 days agoKovD3v's Priors v1.4
Also KovD3v's Priors v1.3
57.21 Opus 5.551.82 Gemini 4 Carbon49.83 Sonnet 5.57 benchmarks · FrontierCode 2.0-AA 30%, ProgramBench 95% 24%, Arena WebDev 13%
- Hudson Gouge@hudson · 6 days agoMy priors61.41 Opus 5.560.02 Sonnet 5.559.33 GPT-6 Astra
10 benchmarks · AA-AnalystAgent 20%, Slop 20%, FrontierCode 13%
- Vadim Zak@vz · 14 days agoDev
Also All
73.61 Opus 5.569.92 Fable 5.168.83 GPT-6 Astra6 benchmarks · TB 4.0 26%, DeepSWE 1.1 21%, SimpleBench 19%
- ! sen@sen · 15 days agoMy priors71.61 Opus 5.569.82 Fable 5.165.43 GPT-6 Astra
3 benchmarks · AA-Omniscience v1 Accuracy 46%, AA-Briefcase v1.1 28%, SimpleBench 26%
- Raphael@raphael · 16 days agoMy priors
Also General frontier
56.31 Opus 5.555.52 GPT-6 Astra53.83 GPT-6.1 Sol20 benchmarks · Agent Arena 22%, Arena Vision 19%, Chartography 10%
- Víctor@vingren · 17 days agoMy priors41.41 Opus 5.534.42 Fable 5.131.13 GPT-6 Astra
11 benchmarks · ProgramBench 35%, HANDBOOK.md Agents 16%, ClutterBench 15%
- Andrew@xyzzy · 17 days agoMy priors58.91 Opus 5.556.32 GPT-6 Astra54.63 GPT-6.1 Sol
12 benchmarks · AA-Omniscience v1 Accuracy 31%, CWE-Bench-AA Refusal Rate 11%, Terminal-Bench v4-AA 9%
- Ryan Schultz@ryan · 18 days agoNew index76.41 Opus 5.573.52 GPT-6 Astra72.83 GPT-6.1 Sol
8 benchmarks · TB 4.0 21%, DeepSWE 1.1 17%, FM Tier 4 16%
- Henry Goldsmith@henry · 18 days agoMy priors64.61 Opus 5.563.42 Sonnet 5.561.63 GPT-6 Astra
5 benchmarks · Furniture Assembly 32%, SciCode 22%, MLCR-AA 17%
- Cservid Zsombor@cservid · 18 days agoAdam's Capabilities Index
Also 3D Understanding Index
63.71 Muse Wonder Full63.02 Gemini 4 Argon60.13 Muse Wonder (Max)9 benchmarks · AA-Omniscience v1 Non-hallucination 37%, GDPval-AA v2.1 19%, AA-Omniscience v1 9%
- Nicholas Nore@nore · 18 days agoMy priors59.11 GPT-6.1 Terra56.72 GLM 5.355.33 DeepSeek V4.1 Flash 1017
12 benchmarks · Public Benefits 17%, GDPval-AA v2.1 14%, Humanity's Last Exam 14%
- Mustafa Mahmoud@mustafa · 19 days agoMy priors60.31 Opus 5.558.62 Sonnet 5.558.63 Kimi K3.1
7 benchmarks · Humanity's Last Exam 35%, Terminal-Bench v4-AA 34%, MLCR-AA 11%
- Morris Dweck@morris · 19 days agoMincode V1
Also My priors
63.21 Opus 5.559.22 Sonnet 5.559.13 GPT-6 Astra3 benchmarks · TB 4.0 44%, FrontierCode 1.1 36%, Arena WebDev 20%
- Michael Cartwright@pleb · 19 days agoMy priors66.31 Opus 5.560.52 GPT-6 Astra59.83 Fable 5.1
8 benchmarks · ProgramBench 95% 30%, Terminal-Bench v4-AA 26%, Humanity's Last Exam 19%
- Dhanabordee Mekintharanggur@pointmekin · 19 days agoMy priors66.91 Opus 5.561.32 GPT-6 Astra59.23 GPT-6.1 Sol
11 benchmarks · FrontierCode 1.1 28%, threejseval 14%, Terminal-Bench v4-AA 10%
- Brad Hilton@bradhilton · 19 days agoMy priors63.71 Gemini 4 Carbon61.92 Kimi K3.161.93 Sonnet 5.5
8 benchmarks · Terminal-Bench v4-AA 47%, Humanity's Last Exam 16%, ProgramBench 95% 10%
- Andy Phillips@cornishandy · 26 days agoFrom @adamholter61.71 Opus 5.560.42 Gemini 4 Carbon60.03 Sonnet 5.5
4 benchmarks · AA Index v4.3.2 25%, Arena Text 25%, Vals Index 25%
- z zz@yukikaze · 28 days agoMy priors75.51 GPT-6 Astra53.62 Opus 548.93 GPT-5.6 Sol
13 benchmarks · ARC-AGI-3 15%, FM Tier 4 11%, GPQA Diamond 9%
- Hedley Pugh@hedley · 28 days agoAdam's Capabilities Index67.21 Kimi K3.165.22 Gemini 4 Carbon62.63 Gemini 4 Carbon
2 benchmarks · Terminal-Bench v4-AA 50%, Vals TB Science 50%