Coding
Vibe Code Bench leaderboard
As of 2026-11-21, the highest measured score on Vibe Code Bench is 91.9% by Gemini 4 Argon. 164 more models have estimated scores, calibrated from the benchmarks they were measured on.
Measured scores: benchlm.ai.
| # | Model | Score | Source |
|---|---|---|---|
| 1 | Claude Fable 5.1 | 100.0% | estimated ± 10.0 pp, low confidence |
| 2 | Gemini 4 Argon | 91.9% | measured |
| 3 | Claude Opus 5.5 | 81.7% | estimated ± 5.6 pp, low confidence |
| 4 | GPT-5.6 Sol | 81.6% | estimated ± 10.0 pp, low confidence |
| 5 | Claude Fable 5 | 81.0% | estimated ± 5.6 pp, low confidence |
| 6 | Claude Opus 5 | 80.9% | estimated ± 5.6 pp, low confidence |
| 7 | GPT-6 Astra | 80.8% | estimated ± 5.6 pp, low confidence |
| 8 | Grok 4.6 | 78.6% | estimated ± 10.0 pp, low confidence |
| 9 | Mistral Large 4 | 78.4% | measured |
| 10 | SWE-2 | 78.2% | estimated ± 5.6 pp, low confidence |
| 11 | GPT-5.6 Terra | 77.9% | estimated ± 10.0 pp, low confidence |
| 12 | Gemini 3.8 Flash | 76.2% | estimated ± 10.0 pp, low confidence |
| 13 | Kimi K3 | 75.9% | estimated ± 10.0 pp, low confidence |
| 14 | Claude Opus 4.8 | 75.2% | estimated ± 5.6 pp, low confidence |
| 15 | Claude Haiku 5.5 | 75.2% | estimated ± 5.6 pp, low confidence |
| 16 | Claude Sonnet 5.5 | 75.0% | estimated ± 5.6 pp, low confidence |
| 17 | SWE-2 Flash | 74.4% | estimated ± 5.6 pp, low confidence |
| 18 | Muse Spark 1.3 | 73.9% | estimated ± 10.0 pp, low confidence |
| 19 | Gemini 3.7 Flash | 72.6% | estimated ± 5.6 pp, low confidence |
| 20 | Claude Sonnet 5 | 71.8% | estimated ± 5.6 pp, low confidence |
| 21 | SWE-1.7 | 71.4% | estimated ± 5.6 pp, low confidence |
| 22 | Claude Opus 4.7 | 71.0% | measured |
| 23 | GPT-5.5 | 69.8% | measured |
| 24 | GLM-5.3 | 69.6% | estimated ± 10.0 pp, low confidence |
| 25 | GPT-5.4 | 67.4% | measured |
| 26 | Composer 2 | 66.5% | estimated ± 6.5 pp, low confidence |
| 27 | Composer 2 Fast | 66.5% | estimated ± 6.5 pp, low confidence |
| 28 | Claude Mythos 5 | 66.3% | estimated ± 8.4 pp, low confidence |
| 29 | Ember-1 | 66.3% | estimated ± 8.4 pp, low confidence |
| 30 | Ornith-1.5-397B | 66.2% | estimated ± 8.4 pp, medium confidence |
| 31 | Qwen3.8-Flash-Next | 63.2% | estimated ± 10.0 pp, low confidence |
| 32 | Ornith-1.0-397B | 62.8% | estimated ± 8.4 pp, medium confidence |
| 33 | Inkling 2 Small | 62.2% | estimated ± 8.4 pp, medium confidence |
| 34 | GPT-5.3 Codex | 61.8% | measured |
| 35 | Grok 4.5 | 61.2% | estimated ± 10.0 pp, low confidence |
| 36 | Muse Spark 1.2 | 60.4% | estimated ± 10.0 pp, low confidence |
| 37 | Beam 1.0 501B-A23B | 59.8% | estimated ± 8.4 pp, medium confidence |
| 38 | Qwen3.8 Max Preview | 59.1% | estimated ± 10.0 pp, low confidence |
| 39 | GPT-5.6 Luna | 58.0% | estimated ± 10.0 pp, low confidence |
| 40 | Muse Spark 1.1 | 57.6% | estimated ± 10.0 pp, low confidence |
| 41 | Claude Opus 4.6 | 57.6% | measured |
| 42 | Claude Opus 4.5 | 55.5% | estimated ± 8.4 pp, medium confidence |
| 43 | Beam 1.0 501B-A23B NVFP4 | 53.9% | estimated ± 8.4 pp, medium confidence |
| 44 | GPT-5.2 | 53.5% | measured |
| 45 | Claude Opus 4.6 (Adaptive) | 53.5% | measured |
| 46 | MiniMax M3 | 52.2% | estimated ± 8.4 pp, medium confidence |
| 47 | Gemini 3.6 Flash | 51.8% | estimated ± 10.0 pp, low confidence |
| 48 | Claude Sonnet 4.6 | 51.5% | measured |
| 49 | Qwen3.7 Max | 51.2% | estimated ± 8.4 pp, medium confidence |
| 50 | GLM-5.2 | 50.5% | estimated ± 10.0 pp, low confidence |
| 51 | DeepSeek V4 Pro | 49.9% | measured |
| 52 | Inkling-Small | 49.2% | estimated ± 8.4 pp, medium confidence |
| 53 | Beam 1.0 501B-A23B FP8 | 49.2% | estimated ± 8.4 pp, medium confidence |
| 54 | Qwen3.8-27B | 48.9% | estimated ± 10.0 pp, low confidence |
| 55 | Gemini 3.5 Flash | 48.7% | measured |
| 56 | GPT-5.4 mini | 48.0% | measured |
| 57 | GPT-5.2-Codex | 37.9% | measured |
| 58 | Kimi K2.6 | 37.9% | measured |
| 59 | Inkling 2 Mini | 36.9% | estimated ± 8.4 pp, medium confidence |
| 60 | Quasar 438B | 35.5% | estimated ± 10.0 pp, low confidence |
| 61 | Apodex 1.1 Mini | 34.9% | estimated ± 10.0 pp, low confidence |
| 62 | Kimi K2.7 Code | 34.9% | estimated ± 10.0 pp, low confidence |
| 63 | DeepSeek V4 Flash 0731 | 34.1% | estimated ± 8.4 pp, medium confidence |
| 64 | Ornith-1.5-35B-A3B | 34.1% | estimated ± 8.4 pp, medium confidence |
| 65 | MiMo-V2.5-Pro | 34.0% | estimated ± 10.0 pp, low confidence |
| 66 | Gemini 3.1 Pro | 32.0% | measured |
| 67 | Hy3 | 32.0% | estimated ± 10.0 pp, low confidence |
| 68 | GLM-5.1 | 31.5% | measured |
| 69 | Kimi K2.5 | 27.9% | estimated ± 6.5 pp, low confidence |
| 70 | Gemma 4 31B | 27.7% | estimated ± 6.5 pp, low confidence |
| 71 | GLM-5 | 27.7% | estimated ± 6.5 pp, low confidence |
| 72 | Grok 4 | 27.7% | estimated ± 6.5 pp, low confidence |
| 73 | GPT-OSS 120B | 27.7% | estimated ± 6.5 pp, low confidence |
| 74 | DeepSeek V3.2 | 27.7% | estimated ± 6.5 pp, low confidence |
| 75 | GPT-OSS 20B | 27.7% | estimated ± 6.5 pp, low confidence |
| 76 | MiniMax M2.7 | 27.0% | measured |
| 77 | GPT-5.4 nano | 26.1% | measured |
| 78 | BTL-4 | 26.0% | estimated ± 8.4 pp, medium confidence |
| 79 | dots3-note Preview | 26.0% | estimated ± 8.4 pp, medium confidence |
| 80 | Qwen3.6 Plus | 25.6% | measured |
| 81 | GPT-5.1 | 24.6% | measured |
| 82 | Ling 3.0 Flash | 22.8% | estimated ± 10.0 pp, low confidence |
| 83 | Claude Sonnet 4.5 Thinking | 22.6% | measured |
| 84 | GPT-5.1-Codex-Max | 22.2% | measured |
| 85 | Gemini 3.5 Flash-Lite | 21.5% | estimated ± 10.0 pp, low confidence |
| 86 | MiMo-V2-Pro | 21.0% | estimated ± 8.4 pp, medium confidence |
| 87 | Claude Opus 4.5 Thinking | 20.6% | measured |
| 88 | GLM-4.7 | 20.6% | estimated ± 6.6 pp, low confidence |
| 89 | o4-mini | 20.2% | estimated ± 6.6 pp, low confidence |
| 90 | Gemini 3 Flash | 20.2% | measured |
| 91 | GPT-5 | 20.1% | measured |
| 92 | Muse Spark | 19.7% | measured |
| 93 | Apodex 1.1 | 17.6% | estimated ± 8.4 pp, medium confidence |
| 94 | Qwen3.7 Plus | 17.6% | estimated ± 8.4 pp, medium confidence |
| 95 | Inkling | 16.6% | estimated ± 8.4 pp, medium confidence |
| 96 | Mistral Medium 3.5 128B | 16.6% | estimated ± 8.4 pp, medium confidence |
| 97 | Grok 4.3 | 16.1% | estimated ± 10.0 pp, low confidence |
| 98 | Qwen3.5 Plus | 15.7% | measured |
| 99 | MiniMax M2.5 | 14.9% | measured |
| 100 | o1 | 14.5% | estimated ± 10.0 pp, low confidence |
| 101 | Step 3.7 Flash | 14.4% | estimated ± 10.0 pp, low confidence |
| 102 | Gemini 3 Pro | 14.3% | measured |
| 103 | Gemma 4 26B A4B | 14.2% | estimated ± 10.0 pp, low confidence |
| 104 | GPT-5 mini | 14.2% | measured |
| 105 | GPT-5.1-Codex | 13.1% | measured |
| 106 | Claude Sonnet 4.5 | 12.8% | estimated ± 8.4 pp, medium confidence |
| 107 | Qwen3.6-27B | 12.8% | estimated ± 8.4 pp, medium confidence |
| 108 | Claude Haiku 4.5 Thinking | 11.4% | measured |
| 109 | o1-preview | 11.3% | estimated ± 10.0 pp, low confidence |
| 110 | Gemma 4 12B | 9.8% | estimated ± 10.0 pp, low confidence |
| 111 | Command A+ | 8.4% | estimated ± 10.0 pp, low confidence |
| 112 | Mistral Small 4 | 7.9% | estimated ± 10.0 pp, low confidence |
| 113 | Ripple-65B Preview | 7.8% | estimated ± 8.4 pp, medium confidence |
| 114 | Trinity-Large-Preview | 7.6% | estimated ± 10.0 pp, low confidence |
| 115 | Trinity-Large-Thinking | 7.6% | estimated ± 10.0 pp, low confidence |
| 116 | Ling 2.6 Flash | 7.3% | estimated ± 10.0 pp, low confidence |
| 117 | Gemini 1.5 Pro | 6.7% | estimated ± 10.0 pp, low confidence |
| 118 | Qwen3.5 397B | 6.3% | estimated ± 8.4 pp, medium confidence |
| 119 | GPT-4 Turbo | 5.9% | estimated ± 10.0 pp, low confidence |
| 120 | GPT-4.1 mini | 5.5% | estimated ± 10.0 pp, low confidence |
| 121 | Mistral Large 3 | 5.4% | estimated ± 10.0 pp, low confidence |
| 122 | Muse Glimmer 30B | 5.4% | estimated ± 8.4 pp, medium confidence |
| 123 | Claude 3 Opus | 5.3% | estimated ± 10.0 pp, low confidence |
| 124 | Llama 4 Maverick | 4.2% | estimated ± 10.0 pp, low confidence |
| 125 | Grok 4.20 | 4.1% | measured |
| 126 | Ornith-1.0-35B | 4.0% | estimated ± 8.4 pp, medium confidence |
| 127 | Celeris-1 | 3.6% | estimated ± 10.0 pp, low confidence |
| 128 | Nemotron 3 Nano 30B | 3.6% | estimated ± 10.0 pp, low confidence |
| 129 | Qwen3 Max | 3.5% | measured |
| 130 | Nemotron 3 Nano Omni 30B A3B | 3.4% | estimated ± 10.0 pp, low confidence |
| 131 | GLM-4.6 | 3.1% | measured |
| 132 | Ultravox v0.6 Llama 3.3 70B | 2.9% | estimated ± 10.0 pp, low confidence |
| 133 | GPT-4o mini | 2.8% | estimated ± 10.0 pp, low confidence |
| 134 | GPT-4.1 nano | 2.7% | estimated ± 10.0 pp, low confidence |
| 135 | Gemma 3 27B | 2.4% | estimated ± 10.0 pp, low confidence |
| 136 | Gemma 4 E4B | 2.2% | estimated ± 10.0 pp, low confidence |
| 137 | MiMo-V2-Omni | 2.1% | estimated ± 8.4 pp, medium confidence |
| 138 | Llama 4 Scout | 1.9% | estimated ± 10.0 pp, low confidence |
| 139 | LFM2.5-2.6B | 1.8% | estimated ± 10.0 pp, low confidence |
| 140 | Laguna M.1 | 1.8% | estimated ± 8.4 pp, medium confidence |
| 141 | Gemma 4 E2B | 1.7% | estimated ± 10.0 pp, low confidence |
| 142 | Claude 4.1 Opus | 1.6% | estimated ± 8.4 pp, medium confidence |
| 143 | Hy3 Preview | 1.5% | estimated ± 8.4 pp, medium confidence |
| 144 | Step 3.5 Flash | 1.5% | estimated ± 8.4 pp, medium confidence |
| 145 | Flint | 1.3% | estimated ± 8.4 pp, medium confidence |
| 146 | Grok 4.1 Fast (Reasoning) | 1.2% | measured |
| 147 | MAI-Thinking-1 | 0.7% | estimated ± 8.4 pp, medium confidence |
| 148 | MiMo-V2-Flash | 0.7% | estimated ± 8.4 pp, medium confidence |
| 149 | Qwen3.6-35B-A3B | 0.7% | estimated ± 8.4 pp, medium confidence |
| 150 | Claude Haiku 4.5 | 0.6% | estimated ± 8.4 pp, medium confidence |
| 151 | Jais-3-MoVA-36B-A4B | 0.4% | estimated ± 8.4 pp, medium confidence |
| 152 | Gemini 2.5 Pro | 0.4% | measured |
| 153 | Claude 4 Sonnet | 0.4% | estimated ± 8.4 pp, medium confidence |
| 154 | MAI-Code-1.1-Flash | 0.3% | estimated ± 8.4 pp, medium confidence |
| 155 | Claude 4 Opus | 0.3% | estimated ± 8.4 pp, medium confidence |
| 156 | Jais-3-32B | 0.3% | estimated ± 8.4 pp, medium confidence |
| 157 | Qwen3.5-27B | 0.3% | estimated ± 8.4 pp, medium confidence |
| 158 | Qwen3.5-122B-A10B | 0.2% | estimated ± 8.4 pp, medium confidence |
| 159 | Nemotron 3 Ultra | 0.2% | estimated ± 8.4 pp, medium confidence |
| 160 | Nemotron 3.5 Super VL 120B A12B | 0.1% | estimated ± 8.4 pp, medium confidence |
| 161 | Nemotron 3.5 Super VL 120B A12B NVFP4 | 0.1% | estimated ± 8.4 pp, medium confidence |
| 162 | Laguna XS 2.1 | 0.1% | estimated ± 8.4 pp, medium confidence |
| 163 | Grok Code Fast 1 | 0.1% | estimated ± 8.4 pp, medium confidence |
| 164 | Ornith-1.5-9B | 0.1% | estimated ± 8.4 pp, medium confidence |
| 165 | Solar Pro 4 | 0.1% | estimated ± 8.4 pp, medium confidence |
| 166 | Solar Open 2 | 0.1% | estimated ± 8.4 pp, medium confidence |
| 167 | Jais-3-375B-A23B | 0.0% | estimated ± 8.4 pp, medium confidence |
| 168 | Jais-3-7B | 0.0% | estimated ± 8.4 pp, medium confidence |
| 169 | o3 | 0.0% | estimated ± 6.6 pp, low confidence |
| 170 | Laguna XS.2 | 0.0% | estimated ± 8.4 pp, medium confidence |
| 171 | Qwen3-Coder 480B-A35B | 0.0% | estimated ± 8.4 pp, medium confidence |
| 172 | Ornith-1.0-9B | 0.0% | estimated ± 8.4 pp, medium confidence |
| 173 | Qwen3.5-35B-A3B | 0.0% | estimated ± 8.4 pp, medium confidence |
| 174 | K-EXAONE 2.0 | 0.0% | estimated ± 8.4 pp, medium confidence |
| 175 | LongCat-Flash-Lite-Sparse | 0.0% | estimated ± 8.4 pp, medium confidence |
| 176 | DeepSeek V3.1 | 0.0% | estimated ± 8.4 pp, medium confidence |
| 177 | Kimi K2 | 0.0% | estimated ± 8.4 pp, medium confidence |
| 178 | Spark-X2.6-4B | 0.0% | estimated ± 8.4 pp, low confidence |
| 179 | Claude 3.7 Sonnet | 0.0% | estimated ± 8.4 pp, low confidence |
| 180 | Ternary Bonsai 2 27B | 0.0% | estimated ± 8.4 pp, low confidence |
| 181 | Nemotron 3 Super 100B | 0.0% | estimated ± 8.4 pp, low confidence |
| 182 | GLM-4.7-Flash | 0.0% | estimated ± 8.4 pp, low confidence |
| 183 | DeepSeek-R1-0528 | 0.0% | estimated ± 8.4 pp, low confidence |
| 184 | Granite 4.2 30B | 0.0% | estimated ± 8.4 pp, low confidence |
| 185 | MiniMax M1 80k | 0.0% | estimated ± 8.4 pp, low confidence |
| 186 | GPT-4.1 | 0.0% | estimated ± 8.4 pp, low confidence |
| 187 | ZAYA1-74B-Preview | 0.0% | estimated ± 8.4 pp, low confidence |
| 188 | Nemotron 3.5 Lightning 30B A3B NVFP4 | 0.0% | estimated ± 8.4 pp, low confidence |
| 189 | LFM2.5-24B-A2B | 0.0% | estimated ± 8.4 pp, low confidence |
| 190 | K-Exaone | 0.0% | estimated ± 8.4 pp, low confidence |
| 191 | o3-mini | 0.0% | estimated ± 8.4 pp, low confidence |
| 192 | LLaDA2.2-flash | 0.0% | estimated ± 8.4 pp, low confidence |
| 193 | DeepSeek-R1 | 0.0% | estimated ± 8.4 pp, low confidence |
| 194 | Claude 3.5 Sonnet | 0.0% | estimated ± 8.4 pp, low confidence |
| 195 | Granite 4.2 8B | 0.0% | estimated ± 8.4 pp, low confidence |
| 196 | Mellum2.1-12B-A2.5B-Thinking | 0.0% | estimated ± 8.4 pp, low confidence |
| 197 | Devstral Small | 0.0% | estimated ± 8.4 pp, low confidence |
| 198 | MiniCPM5-2B | 0.0% | estimated ± 8.4 pp, low confidence |
| 199 | Sarvam 105B | 0.0% | estimated ± 8.4 pp, low confidence |
| 200 | LFM3-1.7B | 0.0% | estimated ± 8.4 pp, low confidence |
| 201 | DeepSeek V3 | 0.0% | estimated ± 8.4 pp, low confidence |
| 202 | Claude 3.5 Haiku | 0.0% | estimated ± 8.4 pp, low confidence |
| 203 | Gemini 3.1 Flash-Lite | 0.0% | measured |
| 204 | Grok 4 Fast (Reasoning) | 0.0% | measured |
All leaderboards
Agentic · terminal
- AA Terminal-Bench 2.1
- AA Terminal-Bench 4.0
- Terminal-Bench 4.0
- Terminal-Bench 2.0
- Terminal-Bench 2.1
- Terminal-Bench 3.0
- Terminal-Bench Hard
- Terminal-Bench-Science 0.1
- Terminal-Bench 4.1
- Terminal-Bench 2.1 (Vals AI)
Agentic · tools
- AA Agentic Index
- AA-AnalystAgent
- AA AutomationBench
- CWE-Bench-AA
- AA Cyber Index
- DeepsecBench-AA
- AA EnterpriseOps-Gym
- GDP.pdf
- AA Harvey LAB v1.0
- Harvey LAB-AA v1.1
- AA ITBench
- AA Tau3 Banking
- Agents' Last Exam
- APEX-Agents
- APEX-Agents-AA
- ApprenticeBench
- AutomationBench
- BFCL v4
- BrowseComp
- Claw-Eval
- CWE-bench v1
- CWE-bench
- CyberGym
- DeepPlanning
- DeepSearchQA
- DRACO
- ExploitGym
- Finance Agent v2
- GDPval-AA
- Gert Labs
- Hermes Bench
- Hermes Index
- HLE w/ tools
- JobBench
- LifeVal
- MazeBench
- MCP Atlas
- MCP-Tasks
- MKA
- OSWorld 2.1
- OSWorld 2.1 Offline
- OSWorld-Verified
- OSWorld 2.0
- PinchBench
- QwenClawBench
- ResearchClawBench
- SkillsBench
- τ²-bench results
- τ³-bench results
- Toolathlon
- Toolathlon-Verified
- VITA-Bench
- WideResearch
Coding
- AA Coding Index
- AA LiveCodeBench
- AA-SciCode
- Bug Hunt Bench
- CursorBench 3.1
- CursorBench 3.2
- CursorBench 4.0
- cursorBench41
- DeepSWE
- FrontierCode 1.1 Main
- FrontierCode 2.0
- FrontierCode 1.1 Extended
- FrontierSWE v2
- LiveCodeBench
- LiveCodeBench Pro
- LiveCodeBench v6
- NL2Repo
- OpenHarmony Bench v1.2
- OpenHarmony Bench v1.0
- PostTrainBench
- PostTrainBench v1
- PostTrainBench v1.1
- ProgramBench
- React Native Evals
- ScarfBench
- SciCode
- SWE-Atlas Codebase QnA
- SWE-bench Pro
- SWE-bench Verified
- SWE-Rebench
- SWE-Marathon
- Vals LiveCodeBench
- Vals SWE-bench
- Vibe Code Bench
- VulcanBench Frontier v4
- VulcanBench v3
Math
- AIME 2024
- AIME 2025
- AIME26
- FrontierMath v2 (Tier 4)
- FrontierMath v2 (Tiers 1-3)
- HMMT Feb 2025
- HMMT Feb 2026
- HMMT Nov 2025
- IMOAnswerBench
- MATH-500
- MMAnswerBench
Knowledge & reasoning
- AA-GPQA Diamond
- HealthBench Professional (length-adjusted, Artificial Analysis)
- HealthBench Professional (raw, Artificial Analysis)
- AA-HLE
- AA MMLU-Pro
- ARC-AGI-2
- ARC-AGI-3 Provider Adapter
- ARC-AGI-1
- ARC-AGI-3
- Artificial Analysis Intelligence Index
- BBH
- BioBasicsBench
- BioMysteryBench (human-difficult)
- BioMysteryBench (human-solvable)
- C-Eval
- CritPt
- GPQA
- GPQA Diamond
- HealthBench (raw)
- HealthBench Hard
- HealthBench (length-adjusted)
- HealthBench Professional
- HealthBench Professional (raw)
- HLE
- HLE w/o tools
- HLE-Verified
- JevBench 1.4
- LABBench2
- MedXpertQA (Text)
- MMLU
- MMLU-Pro
- MMLU-Pro (Arcee)
- MMLU-Redux
- MMMLU
- AA-Omniscience Accuracy
- SimpleQA
- STEMBench
- SuperGPQA
- Vals GPQA Diamond
- Vals MMLU-Pro
Instruction following
Multilingual
Vision & documents
- AA-MMMU-Pro
- AI2D_TEST
- BabyVision
- BabyVision w/ Python
- BenchCAD Vision2Code (no tools)
- BenchCAD Vision2Code (tools)
- CC-OCR
- Chartography (no tools)
- Chartography (tools)
- CharXiv
- CharXiv w/o tools
- CountBench
- DynaMath
- ERQA
- LVBench
- MathVision
- MathVision w/ Python
- MedXpertQA (MM)
- MLVU (M-Avg)
- MMMU
- MMMU-Pro
- MMMU-Pro w/ Python
- MMVU
- OCRBench V2
- OfficeQA
- OfficeQA Pro
- OmniDocBench 1.5
- ParseBench-1
- ParseBench-2
- PerceptionBench
- RealWorldQA
- RefCOCO (avg)
- ScreenSpot Pro
- SimpleVQA
- SWE-bench Multimodal
- Video-MME (w/o subtitle)
- Video-MME (with subtitle)
- VideoMMMU
- V*
- We-Math
- ZeroBench
- ZeroBench w/ Python
Long context
General
- HLE-MultiChoice (Decision Index)
- Artificial Analysis Decision Index v1.0
- Artificial Analysis Decision Index
- When2Call (Decision Index)
- WildGuardTest (Decision Index)
- BabaIsBench
- BinaryAudit
- BlenderWorld (text-only)
- Chess Puzzles
- CompileBench
- Cookie-Bench
- DAYJOB
- DAYJOB Healthcare
- Decision Index Full Score
- EBR-bench
- ExploitBench
- ExploitBench Internal Port
- FACTS Multimodal
- FailureSensorIQ
- FrontierPhysics
- Furniture Assembly
- Decision Index Arts
- Decision Index Knowledge
- Decision Index Language
- Decision Index Retrieval
- Decision Index Tools
- MaxxBench
- MirrorCode
- Mystery Game Puzzles
- NYT Connections
- OTelBench
- SEC-Bench Pro
- SkillsBench official leaderboard (BenchFlow)
- SpireClimb
- StealthMark