List your company

General AI Assistant Task on GAIA (val)

96.23Level 1 Scoreagent-2030
34.110850.237966.36582.4921May 16, 2025Jul 16, 2025Sep 16, 2025Nov 17, 2025Jan 17, 2026Mar 20, 2026May 21, 2026

Evaluation results

MethodLinks
agent-20302025.0696.2390.757.6987.27————————
AGENTORCHESTRAVariant=Evolved2025.0696.2393.0288.4693.33————————
SMITHAgent Framework Category=w. Experience Sharing, Base Model Series=Claude and OpenAI series2025.1294.380.261.5—81.8———————
AGENTORCHESTRAVariant=Vanilla2025.0692.4588.3788.4689.7————————
MiroFlow + TPGOBackbone=GPT-5, Optimization Iterations=52026.0490.679.163.681.6———————1,765
DeSearch2025.0690.5772.0138.4672.73————————
AWorldAgent Framework Category=Multi-Agents w. Tool + Memory, Supervised Fine-tuned=true2025.1288.777.953.9—77.6———————
AWorld2025.0688.6877.9153.8577.58————————
Langfun2025.0688.6880.2357.6979.39————————
Alita2025.0688.6889.5376.9287.27————————
Co-Sight2025.0686.7973.2642.3172.73————————
ManusAgent Framework Category=Multi-Agents w. Tool + Memory, Base Model Series=Claude and OpenAI series2025.1286.570.157.7—73.9———————
Manus2025.0686.570.157.6973.9————————
OWLAgent Framework Category=Multi-Agents w. Tool + Memory, Base Model Series=Claude-series2025.1284.967.442.3—69.7———————
Langfun Agent v2.1Open/Close Source=Close Source, Main Model=Claude-3.7-sonnet2025.0583.0268.657.69———71.52—————
Trase Agent v0.3Open/Close Source=Close Source, Main Model=o12025.0583.0269.7746.15———70.3—————
OAgentsAgent Framework Category=w. Python Interpreter (w.o. Tool Reuse), Base Model Series=Claude-series2025.128374.453.9—66.773.9——————
MiroFlow + TPGOBackbone=GPT-5, Optimization Iterations=32026.0482.173.154.575.7———————2,278
OWL-RoleplayingOpen/Close Source=Open Source, Main Model=GPT-4o + o3-mini2025.0581.1354.6523.08———58.18—————
MiroFlowBackbone=GPT-5, Optimization Iterations=02026.0478.877.544.473.8———————4,014
AlitaAgent Framework Category=w. Tool Creation, Base Model Series=Claude and OpenAI series2025.1277.476.765.4—75.287.3——————
MementoAgent Framework Category=w. Experience Sharing, Base Model Series=OpenAI models2025.1277.469.861.5—70.987.9——————
MiroFlow + TPGOBackbone=GPT-5, Optimization Iterations=12026.0476.971.245.570.59———————3,680
SUPERVISORAGENTBase LLM=GPT-4.1, pass@k=3, framework=SMAS2025.1075.4762.7938.46———63.03369.52276.84409.05427.72—
o3-DR2025.0674.2969.0647.667.36————————
SUPERVISORAGENTBase LLM=GPT-4.1, pass@k=2, framework=SMAS2025.1073.5856.9834.62———58.79389.54270.07420.97529.2—
AutoAgentBackbone LLM=Claude-Sonnet-3.52026.0271.753.4926.9255.15————————
OWLBackbone LLM=GPT-4.12026.0271.75026.9253.33————————
Smolagents + PreFlectBackbone LLM=GPT-4.12026.0271.755.8138.4658.18————————
AutoAgentAgent Framework Category=Multi-Agents w. Tool + Memory, Base Model Series=Claude-series2025.1271.753.426.9—55.2———————
TapeAgentsAgent Framework Category=Multi-Agents w. Tool + Memory, Base Model Series=Claude-series2025.1271.753.530.8—55.8———————
SmolagentBase LLM=GPT-4.1, pass@k=32025.1071.763.9534.62———61.82502.4282.14605.05611.87—
desearchOpen/Close Source=Close Source, Main Model=GPT-4o2025.0571.758.1423.08———56.97—————
TapeAgentsOpen/Close Source=Open Source, Main Model=Claude-3.7-Sonnet2025.0571.753.4930.77———55.76—————
Auto-Deep-ResearchOpen/Close Source=Open Source, Main Model=Claude-3.7-Sonnet2025.0571.753.4926.92———55.15—————
AutoAgentOpen/Close Source=Open Source2025.0571.753.4930.77———55.15—————
Gemini-3-ProNumber of Agents=3, Backbone Model=Gemini-3-Pro2026.0169.8162.7934.6260.61————————
SmolagentBase LLM=GPT-4.1, pass@k=22025.1069.8159.330.77———58.18467.19275.85548.02589.92—
Ormind v0.1Open/Close Source=Close Source2025.0569.8154.6526.92———55.15—————
WebShaper-32BAgent Framework Category=Multi-Agents w. Tool + Memory, Supervised Fine-tuned=true2025.1269.25016.6—53.361.2——————
HF-ODRBackbone LLM=o12026.0267.9253.4934.6255.15————————
OAgentBackbone LLM=GPT-4.12026.0267.9253.4934.6255.15————————
Smolagents + PreFlectBackbone LLM=Gemini-2.5-pro2026.0267.9260.4738.4659.39————————
GPT-5-HighNumber of Agents=3, Backbone Model=GPT-5-High2026.0167.9241.8623.0847.27————————
AWorldBase LLM=GPT-4.12025.1067.9262.7934.62———60128.2769.61164.08133.65—
h2oGPTe Agent v1.6.8Open/Close Source=Close Source, Main Model=Claude-3.5-Sonnet2025.0567.9267.4442.31———63.64—————
Open Deep ResearchOpen/Close Source=Open Source, Main Model=o12025.0567.9253.4934.62———55.15—————
HF ODR2025.0667.9253.4934.6255.15————————
OpenDeepResearchAgent Framework Category=Multi-Agents w. Tool + Memory, Base Model Series=OpenAI models2025.1267.953.534.6—55.2———————
GPT-5.2Number of Agents=3, Backbone Model=GPT-5.22026.0166.0436.0546.1547.27————————
OAgentsBase LLM=GPT-4.12025.1066.0447.6719.23———49.09340.5260.27358.63444.11—
AngesOpen/Close Source=Close Source2025.0566.0465.1230.77———60—————
IdleSpecBackbone=Gemini-2.5-Flash, Use idle?=true2026.056646.532.1—————————
DeepSeek-V3.2Number of Agents=3, Backbone Model=DeepSeek-V3.22026.0164.1545.3546.1551.52————————
Sleep-time ComputeBackbone=Gemini-2.5-Flash, Use idle?=true2026.0562.944.220.5—————————
VanillaBackbone=Gemini-2.5-Flash, Use idle?=false2026.0562.339.925.6—————————
GLM-4.7Number of Agents=3, Backbone Model=GLM-4.72026.0162.2654.6542.3155.15————————
SmolagentBase LLM=GPT-4.1, pass@k=12025.1062.2653.4919.23———50.91527.76298.51619.59691.33—
SUPERVISORAGENTBase LLM=GPT-4.1, pass@k=1, framework=SMAS2025.1062.2651.1626.92———50.91371.12258.28404.96489.22—
Barcelona v0.1Open/Close Source=Close Source, Main Model=Claude-3.5-sonnet2025.0562.265026.92———50.3—————
InfantAgent-NextOpen/Close Source=Open Source, Main Model=Claude-3.7-Sonnet2025.0562.2662.7926.92———56.97—————
Sequential RevisionBackbone=Gemini-2.5-Flash, Use idle?=false2026.0561.642.321.8—————————
GPT-5Number of Agents=3, Backbone Model=GPT-52026.0160.3854.6542.3154.55————————
Gemini-2.5-ProNumber of Agents=3, Backbone Model=Gemini-2.5-Pro2026.0160.3853.4946.1554.55————————
MonoScaleNumber of Agents=7, Backbone Model=Qwen-3-30B-A3B-Instruct, Memory Usage=true2026.0160.3847.6730.7749.09————————
MonoScaleNumber of Agents=10, Backbone Model=Qwen-3-30B-A3B-Instruct, Memory Usage=true2026.0160.3855.8142.3155.15————————
omneOpen/Close Source=Close Source, Main Model=o1-preview2025.0560.3844.1923.08———46.06—————
HF-ODRBackbone LLM=GPT-4.12026.0258.495034.6250.3————————
Qwen3-235B-InstructNumber of Agents=3, Backbone Model=Qwen3-235B-Instruct2026.0158.4947.6726.9247.88————————
HuggingFace AgentsOpen/Close Source=Open Source, Main Model=gpt-4o2025.0558.4943.0219.23———44.24—————
Magnetic-1Backbone LLM=o12026.0256.646.5123.0846.06————————
CodeAgentBase LLM=GPT-4.12025.1056.634.8823.08———40120.492.84131.9138.54—
DRP-val-v.1.0Open/Close Source=Close Source2025.0556.648.8415.38———46.06—————
Magnetic-1Open/Close Source=Open Source, Main Model=o12025.0556.646.5123.08———46.06—————
OWLBase LLM=GPT-4.12025.1056.5643.0229.16———45.4111.0767.72110.36209.34—
Multi-Agent Exp v0.1Open/Close Source=Open Source, Main Model=gpt-4-turbo2025.0554.7238.3711.54———39.39—————
SmolAgentsAgent Framework Category=w. Python Interpreter (w.o. Tool Reuse), Base Model Series=OpenAI models2025.1254.753.526.9—49.7———————
HAL AgentBackbone LLM=GPT-4.12026.0252.8355.8123.0849.7————————
MonoScaleNumber of Agents=5, Backbone Model=Qwen-3-30B-A3B-Instruct, Memory Usage=true2026.0152.8345.3542.3147.27————————
qbnlpOpen/Close Source=Close Source, Main Model=o12025.0552.8345.3523.08———44.24—————
LRC-HuaweiOpen/Close Source=Close Source2025.0552.8343.027.69———40.61—————
Agent-On-the-flyOpen/Close Source=Close Source, Main Model=QwQ-32B2025.0552.8343.027.69———40.61—————
AgentIM v1.1Open/Close Source=Close Source, Main Model=gpt-4-turbo2025.0550.9440.715.38———40—————
MonoScaleNumber of Agents=3, Backbone Model=Qwen-3-30B-A3B-Instruct, Memory Usage=false2026.0149.0647.6726.9244.84————————
CADMAS-CTXAPI Calls/Task=5.12026.0448.5—1844.2————————
StaticAPI Calls/Task=4.52026.0448.2—5.138.1————————
Learned RouterAPI Calls/Task=3.22026.0447—7.236.2————————
AutoGenAPI Calls/Task=18.42026.0446.1—6.535.4————————
FRIDAYOpen/Close Source=Open Source, Main Model=gpt-4-turbo2025.0545.2834.8811.54———34.55—————
IdleSpecBackbone=Gemma4-E4B, Use idle?=true2026.0543.428.314.1—————————
Sleep-time ComputeBackbone=Gemma4-E4B, Use idle?=true2026.0541.523.69—————————
Sequential RevisionBackbone=Qwen3.5-4B, Use idle?=false2026.0541.527.911.5—————————
IdleSpecBackbone=Qwen3.5-4B, Use idle?=true2026.0540.931.821.8—————————
Sequential RevisionBackbone=Gemma4-E4B, Use idle?=false2026.0539.626.49—————————
VanillaBackbone=Qwen3.5-4B, Use idle?=false2026.0537.726.411.5—————————
VanillaBackbone=Gemma4-E4B, Use idle?=false2026.0536.525.611.5—————————
Sleep-time ComputeBackbone=Qwen3.5-4B, Use idle?=true2026.0536.521.39—————————
MiroFlowAgent Framework Category=Multi-Agents w. Tool + Memory, Base Model Series=Claude-series2025.12————74.582.4——————