Agentic · tools
DeepSearchQA leaderboard
As of 2026-11-21, the highest measured score on DeepSearchQA is 96.0% by Atria Dawn Preview. 169 more models have estimated scores, calibrated from the benchmarks they were measured on.
Measured scores: benchlm.ai.
| # | Model | Score | Source |
|---|---|---|---|
| 1 | Qwen4 Max | 100.0% | estimated ± 7.9 pp, low confidence |
| 2 | Fugu Cyber | 100.0% | estimated ± 11.5 pp, low confidence |
| 3 | Atria Dawn Preview | 96.0% | measured |
| 4 | Claude Opus 5 | 95.0% | measured |
| 5 | Kimi K3 | 95.0% | measured |
| 6 | Claude Fable 5.1 | 94.3% | estimated ± 4.5 pp, medium confidence |
| 7 | Muse Wonder Full | 93.9% | estimated ± 8.2 pp, low confidence |
| 8 | GLM-5.3 | 93.8% | estimated ± 4.5 pp, high confidence |
| 9 | Grok 4.6 | 93.8% | estimated ± 4.5 pp, high confidence |
| 10 | Kimi K3.1 Pro | 93.7% | estimated ± 6.8 pp, low confidence |
| 11 | GPT-6 Astra | 93.6% | estimated ± 4.5 pp, high confidence |
| 12 | LongCat-2.5 | 93.5% | estimated ± 6.8 pp, low confidence |
| 13 | Claude Fable 5 | 93.5% | estimated ± 4.5 pp, high confidence |
| 14 | GPT-5.6 Sol | 93.4% | estimated ± 4.5 pp, high confidence |
| 15 | Ling 3.1 Flash | 93.3% | estimated ± 6.8 pp, low confidence |
| 16 | Qwen3.8 Max Preview | 93.3% | estimated ± 4.5 pp, high confidence |
| 17 | DeepSeek V4 Pro | 93.3% | estimated ± 4.5 pp, high confidence |
| 18 | Claude Opus 4.8 | 93.1% | measured |
| 19 | Qwen3.8-27B | 92.9% | estimated ± 4.5 pp, high confidence |
| 20 | Step 3.7 Flash | 92.8% | measured |
| 21 | Claude Sonnet 5 | 92.5% | estimated ± 4.5 pp, high confidence |
| 22 | Kimi K2.6 | 92.5% | measured |
| 23 | Muse Spark 1.2 | 92.5% | estimated ± 4.5 pp, high confidence |
| 24 | GPT-5.6 Terra | 92.4% | estimated ± 4.5 pp, high confidence |
| 25 | Apodex 1.1 | 92.4% | measured |
| 26 | Muse Wonder | 92.3% | estimated ± 8.2 pp, low confidence |
| 27 | GPT-5.6 Luna | 92.2% | estimated ± 4.5 pp, high confidence |
| 28 | GPT-5.5 Pro | 92.2% | estimated ± 6.8 pp, low confidence |
| 29 | Grok 4.5 | 92.1% | estimated ± 4.5 pp, high confidence |
| 30 | dots3-note Preview | 92.1% | measured |
| 31 | DeepSeek V4 Flash 0731 | 92.1% | estimated ± 4.5 pp, high confidence |
| 32 | Gemini 3.8 Flash | 91.9% | estimated ± 4.5 pp, high confidence |
| 33 | GPT-5.4 Pro | 91.6% | estimated ± 6.8 pp, low confidence |
| 34 | Claude Opus 4.7 | 91.6% | estimated ± 4.5 pp, high confidence |
| 35 | GLM-5.2 | 91.6% | estimated ± 4.5 pp, high confidence |
| 36 | Muse Spark Open | 91.3% | estimated ± 7.3 pp, low confidence |
| 37 | Qwen3.8 Max | 91.3% | estimated ± 7.9 pp, low confidence |
| 38 | Step 5 Preview | 91.2% | estimated ± 6.8 pp, low confidence |
| 39 | GPT-5.5 | 91.1% | estimated ± 4.5 pp, high confidence |
| 40 | Hy4 preview | 91.0% | estimated ± 7.3 pp, low confidence |
| 41 | Gemini 3.7 Flash | 90.9% | estimated ± 4.5 pp, high confidence |
| 42 | Inkling 2 Small | 90.9% | measured |
| 43 | Ling 3.0 Flash Sante | 90.8% | measured |
| 44 | Claude Mythos 5 | 90.7% | estimated ± 6.8 pp, low confidence |
| 45 | ERNIE 5.5 Flash Preview | 90.3% | estimated ± 6.8 pp, low confidence |
| 46 | Gemini 3.8 Flash Cyber | 90.0% | estimated ± 11.5 pp, low confidence |
| 47 | Ultramarine 1 Flash | 90.0% | estimated ± 8.2 pp, low confidence |
| 48 | Quasar 438B | 89.9% | estimated ± 4.5 pp, high confidence |
| 49 | Ornith-1.5-397B | 89.7% | estimated ± 6.8 pp, low confidence |
| 50 | Claude Opus 5.5 | 89.7% | estimated ± 9.6 pp, low confidence |
| 51 | Claude Sonnet 5.5 | 89.7% | estimated ± 9.6 pp, low confidence |
| 52 | Grok 4.7 | 89.6% | estimated ± 9.6 pp, medium confidence |
| 53 | Gemini 4 Argon | 89.6% | estimated ± 9.6 pp, medium confidence |
| 54 | Claude Haiku 5.5 | 89.6% | estimated ± 9.6 pp, medium confidence |
| 55 | DeepSeek V4.1 Flash 1017 | 89.6% | estimated ± 9.6 pp, medium confidence |
| 56 | GPT-6.1 Sol | 89.6% | estimated ± 9.6 pp, medium confidence |
| 57 | GPT-6 Sol | 89.5% | estimated ± 9.6 pp, medium confidence |
| 58 | Muse Spark 1.3 | 89.4% | measured |
| 59 | MiniMax M3.1 Flash | 89.4% | estimated ± 9.6 pp, medium confidence |
| 60 | MiniMax M3 | 89.4% | estimated ± 4.5 pp, high confidence |
| 61 | GPT-6 Luna | 89.3% | estimated ± 9.6 pp, medium confidence |
| 62 | Gemini 3.6 Flash | 89.2% | estimated ± 4.5 pp, high confidence |
| 63 | Mistral Large 4 | 88.2% | estimated ± 6.8 pp, low confidence |
| 64 | Holo3-35B-A3B | 88.2% | estimated ± 7.9 pp, low confidence |
| 65 | Gemini 3.5 Flash | 88.1% | estimated ± 4.5 pp, high confidence |
| 66 | Apodex 1.1 Mini | 88.0% | estimated ± 9.6 pp, medium confidence |
| 67 | MiMo-V2.6-Pro | 87.7% | estimated ± 7.9 pp, low confidence |
| 68 | Qwen3.8-Flash-Next | 87.7% | estimated ± 8.2 pp, low confidence |
| 69 | Ling 3.0 Flash VL | 87.7% | estimated ± 9.6 pp, medium confidence |
| 70 | Hy3 | 87.4% | estimated ± 4.5 pp, high confidence |
| 71 | Hy3 Preview | 87.4% | estimated ± 4.5 pp, high confidence |
| 72 | GLM-5.1 | 87.2% | estimated ± 4.5 pp, high confidence |
| 73 | Inkling-Small | 87.1% | estimated ± 4.5 pp, high confidence |
| 74 | Inkling | 86.8% | estimated ± 4.5 pp, high confidence |
| 75 | MiMo-V2.6-Flash | 86.7% | estimated ± 7.9 pp, low confidence |
| 76 | Qwen3.7 Max | 86.6% | estimated ± 4.5 pp, high confidence |
| 77 | Sage-A1.5 | 86.4% | estimated ± 6.8 pp, low confidence |
| 78 | MiMo-V2.5-Pro | 85.9% | estimated ± 4.5 pp, high confidence |
| 79 | Kimi K2.7 Code | 85.8% | estimated ± 4.5 pp, high confidence |
| 80 | Nemotron 3 Ultra | 85.4% | estimated ± 4.5 pp, high confidence |
| 81 | Inkling 2 Mini | 85.3% | measured |
| 82 | Holo3-122B-A10B | 85.1% | estimated ± 7.9 pp, low confidence |
| 83 | Ling 3.0 Flash | 84.9% | estimated ± 4.5 pp, high confidence |
| 84 | Muse Spark 1.1 | 84.9% | measured |
| 85 | Qwen3.6-27B | 84.3% | estimated ± 4.5 pp, high confidence |
| 86 | Nemotron 3.5 Super VL 120B A12B | 84.1% | estimated ± 6.8 pp, low confidence |
| 87 | Qwen3.7 Plus | 84.1% | estimated ± 4.5 pp, high confidence |
| 88 | GPT-5.4 mini | 84.0% | estimated ± 4.5 pp, high confidence |
| 89 | Nemotron 3.5 Super VL 120B A12B NVFP4 | 83.8% | estimated ± 6.8 pp, low confidence |
| 90 | UI-Mate-27B | 83.6% | estimated ± 7.9 pp, low confidence |
| 91 | A.X K2 | 82.8% | estimated ± 9.6 pp, medium confidence |
| 92 | Agents-A1 | 82.7% | estimated ± 6.8 pp, low confidence |
| 93 | GPT-5.4 nano | 82.6% | estimated ± 4.5 pp, high confidence |
| 94 | Grok 4.3 | 82.2% | estimated ± 4.5 pp, high confidence |
| 95 | MiniMax M2.7 | 81.8% | estimated ± 4.5 pp, high confidence |
| 96 | Ripple-65B Preview | 81.1% | estimated ± 7.3 pp, low confidence |
| 97 | Claude Opus 4.5 | 81.1% | estimated ± 7.3 pp, low confidence |
| 98 | LFM3-1.7B | 81.1% | estimated ± 7.3 pp, low confidence |
| 99 | LLaDA2.2-flash | 81.1% | estimated ± 7.3 pp, low confidence |
| 100 | Qwen3.6 Plus | 81.1% | estimated ± 7.3 pp, low confidence |
| 101 | Solar Open 2 | 81.1% | estimated ± 7.3 pp, low confidence |
| 102 | Beam 1.0 501B-A23B NVFP4 | 81.1% | measured |
| 103 | Gemini 3.5 Flash-Lite | 80.9% | estimated ± 4.5 pp, high confidence |
| 104 | Beam 1.0 501B-A23B | 80.5% | measured |
| 105 | MiMo-V2.5 | 80.5% | estimated ± 10.2 pp, low confidence |
| 106 | Nemotron 3.5 Bolt 74B-A9B BF16 | 80.0% | estimated ± 6.8 pp, low confidence |
| 107 | Qwen3.6-35B-A3B | 80.0% | estimated ± 4.5 pp, high confidence |
| 108 | Beam 1.0 501B-A23B FP8 | 79.6% | measured |
| 109 | Qwen3.5 397B | 79.6% | estimated ± 6.8 pp, low confidence |
| 110 | Ornith-1.5-35B-A3B | 79.1% | estimated ± 6.8 pp, low confidence |
| 111 | Agents-A1-4B | 78.8% | estimated ± 6.8 pp, low confidence |
| 112 | Nemotron 3.5 Bolt 74B-A9B | 78.7% | estimated ± 6.8 pp, low confidence |
| 113 | GPT-5.2 | 78.4% | estimated ± 6.8 pp, low confidence |
| 114 | GPT-5.1-Codex | 78.4% | estimated ± 8.2 pp, low confidence |
| 115 | GPT-5.2-Codex | 78.3% | estimated ± 8.2 pp, low confidence |
| 116 | GLM-5 | 77.3% | estimated ± 6.8 pp, low confidence |
| 117 | Kimi K2.5 | 77.1% | measured |
| 118 | Claude 4.1 Opus | 77.1% | estimated ± 8.2 pp, low confidence |
| 119 | Qwen3.5-27B | 77.0% | estimated ± 6.8 pp, low confidence |
| 120 | Qwen3.5-35B-A3B | 77.0% | estimated ± 6.8 pp, low confidence |
| 121 | MiMo-V2-Pro | 77.0% | estimated ± 10.2 pp, low confidence |
| 122 | Gemini 3.5 Flash Cyber | 76.8% | estimated ± 11.5 pp, low confidence |
| 123 | Claude Mythos Preview | 76.8% | estimated ± 11.5 pp, low confidence |
| 124 | UI-Mate-9B | 76.2% | estimated ± 7.9 pp, low confidence |
| 125 | Ornith-1.5-9B | 76.1% | estimated ± 6.8 pp, low confidence |
| 126 | Qwen3.5 Plus | 76.0% | estimated ± 8.2 pp, low confidence |
| 127 | Claude 4 Sonnet | 76.0% | estimated ± 8.2 pp, low confidence |
| 128 | Spark-X2.6-4B | 75.6% | estimated ± 6.8 pp, low confidence |
| 129 | GLM-4.7 | 75.4% | estimated ± 6.8 pp, low confidence |
| 130 | GPT-5.3 Codex | 75.4% | estimated ± 7.9 pp, low confidence |
| 131 | Claude Haiku 4.5 | 75.2% | estimated ± 8.2 pp, low confidence |
| 132 | Sarvam 105B | 75.2% | estimated ± 6.8 pp, low confidence |
| 133 | Solar Pro 4 | 75.1% | estimated ± 6.8 pp, low confidence |
| 134 | LongCat-Flash-Lite-Sparse | 75.1% | estimated ± 6.8 pp, low confidence |
| 135 | GPT-5.1 | 75.0% | estimated ± 9.6 pp, medium confidence |
| 136 | Muse Spark | 74.8% | measured |
| 137 | Muse Glimmer 30B | 74.6% | measured |
| 138 | Sarvam 30B | 74.5% | estimated ± 6.8 pp, low confidence |
| 139 | Claude Sonnet 4.5 | 73.9% | estimated ± 7.9 pp, low confidence |
| 140 | Gemini 3 Flash | 73.8% | estimated ± 8.2 pp, low confidence |
| 141 | Gemini 3 Pro | 73.8% | estimated ± 8.2 pp, low confidence |
| 142 | Claude Opus 4.6 | 73.7% | measured |
| 143 | GPT-5.4 | 73.6% | measured |
| 144 | K-EXAONE 2.0 | 73.6% | estimated ± 9.6 pp, medium confidence |
| 145 | Claude Sonnet 4.6 | 73.4% | estimated ± 7.5 pp, low confidence |
| 146 | GPT-5 | 72.9% | estimated ± 8.2 pp, low confidence |
| 147 | Grok 4.1 | 72.6% | estimated ± 10.2 pp, low confidence |
| 148 | Qwen3.5-122B-A10B | 71.8% | estimated ± 4.5 pp, medium confidence |
| 149 | Mercury 3 | 71.3% | measured |
| 150 | Mistral Medium 3.5 128B | 71.1% | estimated ± 4.5 pp, medium confidence |
| 151 | Gemini 3.1 Pro | 69.7% | measured |
| 152 | Gemma 4 31B | 63.9% | estimated ± 4.5 pp, medium confidence |
| 153 | MiniCPM5-2B | 63.3% | estimated ± 9.6 pp, medium confidence |
| 154 | Grok 4.20 | 62.8% | measured |
| 155 | GPT-OSS 120B | 62.0% | estimated ± 4.5 pp, medium confidence |
| 156 | Nemotron 3.5 Lightning 30B A3B NVFP4 | 61.7% | estimated ± 4.5 pp, medium confidence |
| 157 | MiMo-V2-Flash | 52.9% | estimated ± 9.6 pp, medium confidence |
| 158 | Granite 4.2 8B | 49.2% | estimated ± 4.5 pp, medium confidence |
| 159 | Command A+ | 48.7% | estimated ± 4.5 pp, medium confidence |
| 160 | Gemini 2.5 Pro | 48.1% | estimated ± 4.5 pp, medium confidence |
| 161 | Granite 4.2 30B | 45.2% | estimated ± 9.6 pp, medium confidence |
| 162 | Gemma 4 26B A4B | 43.8% | estimated ± 9.6 pp, medium confidence |
| 163 | Ling 3.0 Tiny | 43.2% | estimated ± 9.6 pp, medium confidence |
| 164 | Mistral Large 3 | 38.9% | estimated ± 4.5 pp, medium confidence |
| 165 | Claude 3.5 Haiku | 34.7% | estimated ± 9.6 pp, medium confidence |
| 166 | DeepSeek V3 0324 | 34.7% | estimated ± 9.6 pp, medium confidence |
| 167 | Gemma 4 12B | 34.7% | estimated ± 9.6 pp, medium confidence |
| 168 | Gemma 4 E2B | 34.7% | estimated ± 9.6 pp, medium confidence |
| 169 | Gemma 4 E4B | 34.7% | estimated ± 9.6 pp, medium confidence |
| 170 | GPT-4.1 mini | 34.7% | estimated ± 9.6 pp, medium confidence |
| 171 | GPT-4.1 nano | 34.7% | estimated ± 9.6 pp, medium confidence |
| 172 | GPT-4o | 34.7% | estimated ± 9.6 pp, medium confidence |
| 173 | GPT-4o mini | 34.7% | estimated ± 9.6 pp, medium confidence |
| 174 | Granite 4.2 3B | 34.7% | estimated ± 9.6 pp, medium confidence |
| 175 | K-Exaone | 34.7% | estimated ± 9.6 pp, medium confidence |
| 176 | LFM2.5-2.6B | 34.7% | estimated ± 9.6 pp, medium confidence |
| 177 | Ling 2.6 Flash | 34.7% | estimated ± 9.6 pp, medium confidence |
| 178 | Llama 3.3 70B | 34.7% | estimated ± 9.6 pp, medium confidence |
| 179 | Mistral Small 3.1 | 34.7% | estimated ± 9.6 pp, medium confidence |
| 180 | Nemotron 3 Nano Omni 30B A3B | 34.7% | estimated ± 9.6 pp, medium confidence |
| 181 | North Mini Code | 34.7% | estimated ± 9.6 pp, medium confidence |
| 182 | Solar Pro 3 | 34.7% | estimated ± 9.6 pp, medium confidence |
| 183 | Ultravox v0.6 Llama 3.3 70B | 34.7% | estimated ± 9.6 pp, medium confidence |
| 184 | Mercury 2.5 | 34.0% | measured |
| 185 | Mistral Small 4 | 27.3% | estimated ± 4.5 pp, medium confidence |
| 186 | GPT-OSS 20B | 26.7% | estimated ± 4.5 pp, medium confidence |
| 187 | Trinity-Large-Preview | 23.2% | estimated ± 4.5 pp, medium confidence |
| 188 | Trinity-Large-Thinking | 23.2% | estimated ± 4.5 pp, medium confidence |
| 189 | Nemotron 3 Nano 30B | 20.7% | estimated ± 4.5 pp, medium confidence |
| 190 | DeepSeek V3 | 17.0% | estimated ± 4.5 pp, medium confidence |
| 191 | Celeris-1 | 14.5% | estimated ± 4.5 pp, medium confidence |
| 192 | Llama 4 Maverick | 13.9% | estimated ± 4.5 pp, medium confidence |
| 193 | Llama 4 Scout | 12.5% | estimated ± 4.5 pp, medium confidence |
| 194 | Gemma 3 27B | 3.5% | estimated ± 4.5 pp, medium confidence |
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