List your company

General AI Assistant Tasks on GAIA

93.2AccuracyArgus-35B-A3B (Parallel)
30.48846.76963.0579.331Feb 2, 2026Feb 19, 2026Mar 8, 2026Mar 25, 2026Apr 11, 2026Apr 28, 2026May 15, 2026

Evaluation results

MethodLinks
Argus-35B-A3B (Parallel)Category=Parallel Agents, Mode=Parallel2026.0593.2———
Argus-35B-A3B (Solo)Category=Parallel Agents, Mode=Solo2026.0588———
Seed1.82026.0287.4———
Searcher-35B-A3BCategory=Parallel Agents2026.0584.5———
M2CLModel=Qwen-72B, Number of LLMs=642026.0284.2———
MiroThinker-1.7Category=Open-Source Deep Research Agents2026.0582.7———
Gemini-3.1-ProCategory=Proprietary Agents2026.0580.6———
REDSearcherSize=30B-A3B2026.0280.1———
Qwen3.5-35B-A3BCategory=Open-Source Agents2026.0580———
M2CLBackbone=Qwen-72B, Number of LLMs=322026.0279.7———
Seed-2.0-ProCategory=Proprietary Agents2026.0579.6———
Mementocrawl(s)=✓, visual=✓, file=✓, browser=✗, Backbone=O3 + GPT-4.12026.0379.4———
Kimi-K2.6Category=Open-Source Agents2026.0578.6———
GPT-5-Thinking-high2026.0276.7———
Claude-4.6-OpusCategory=Proprietary Agents2026.0575———
Gemini-3-Pro2026.0274.8———
WebSailorV2-30BSize=30B-A3B2026.0274.1———
Tongyi-DeepResearch HeavyCategory=Parallel Agents2026.0572.8———
M2CLModel=Qwen-72B, Number of LLMs=162026.0271.9———
Tongyi DeepResearch-30BSize=30B-A3B2026.0270.9———
Tongyi-DeepResearchCategory=Open-Source Deep Research Agents2026.0570.9———
OpenAI-o32026.0270.5———
GLM-5.0Category=Open-Source Agents2026.0570———
OWLcrawl(s)=✓, visual=✓, file=✓, browser=✓, Backbone=O3-mini + 4o + Claude-S3.72026.0369.7———
WebClipper (Hybrid)Category=Pruning Method, Base Model=Tongyi-DeepResearch, Variant=Hybrid2026.0269.50.74419.926,635
WebClipper (Eff)Category=Pruning Method, Base Model=Tongyi-DeepResearch, Variant=Efficiency2026.0268.40.7614.444,756
Claude-4-SonnetCategory=Close-sourced System2026.0268.3———
M2CLModel=Llama-70B, Number of LLMs=642026.0268.2———
Tongyi-DeepResearchCategory=Open-sourced Agent, Evaluation Environment=Unified2026.0268.20.73320.567,378
OpenAI DeepResearchCategory=Close-sourced System2026.0267.4———
M2CLBackbone=Qwen-72B, Number of LLMs=82026.0267.2———
Prompt ControlCategory=Pruning Method, Base Model=Tongyi-DeepResearch2026.0266.30.7318.76,752
Claude-4.5-sonnet2026.0266———
GLM-4.5 HeavyCategory=Parallel Agents2026.0566———
M2CLBackbone=Llama-70B, Number of LLMs=322026.0265.7———
DeepSeek-V4-Pro-MaxCategory=Open-Source Agents2026.0565.3———
M2CLModel=Llama-70B, Number of LLMs=162026.0261.5———
M2CLBase Model=Qwen-72B, Number of LLMs=42026.0260.3———
MacNetModel=Qwen-72B, Number of LLMs=642026.0259.5———
M2CLBackbone=Llama-70B, Number of LLMs=82026.0258.7———
INFOTREE2026.0556———
MacNetBackbone=Qwen-72B, Number of LLMs=322026.0254.7———
M2CLModel=Qwen-14B, Number of LLMs=642026.0251.8———
Coarse PruneCategory=Pruning Method, Base Model=Tongyi-DeepResearch2026.0251.40.63815.64,068
UIS-Digger (Pangu)crawl(s)=✓, visual=✓, file=✓, browser=✓, Backbone=PanGu-38B2026.0350.5———
MacNetModel=Qwen-72B, Number of LLMs=162026.0250.3———
Tree-GRPO2026.0550.1———
M2CLBase Model=Llama-70B, Number of LLMs=42026.0249.6———
MacNetModel=Llama-70B, Number of LLMs=642026.0249———
M2CLBackbone=Qwen-14B, Number of LLMs=322026.0249———
DebateModel=Qwen-72B, Number of LLMs=642026.0247.6———
UIS-Digger (Qwen)crawl(s)=✓, visual=✓, file=✓, browser=✓, Backbone=Qwen3-32B2026.0347.6———
Kimi-K2-Instruct-0905Category=Open-sourced Agent, Evaluation Environment=Unified2026.0246.90.6256.451,281
DebateBackbone=Qwen-72B, Number of LLMs=322026.0246.6———
MacNetBackbone=Llama-70B, Number of LLMs=322026.0246.5———
MacNetBackbone=Qwen-72B, Number of LLMs=82026.0246.4———
Qwen3-235B-A22B-Instruct-2507Category=Open-sourced Agent, Evaluation Environment=Unified2026.0245.60.6127.141,128
BoNModel=Qwen-72B, Number of LLMs=642026.0244.9———
Flat GRPO2026.0544.8———
DebateModel=Qwen-72B, Number of LLMs=162026.0244.1———
M2CLModel=Qwen-14B, Number of LLMs=162026.0243.9———
BoNBackbone=Qwen-72B, Number of LLMs=322026.0243.9———
MacNetModel=Llama-70B, Number of LLMs=162026.0243.8———
DyLANModel=Qwen-72B, Number of LLMs=642026.0243.7———
BoNModel=Qwen-72B, Number of LLMs=162026.0243.3———
GPTSwarmModel=Qwen-72B, Number of LLMs=642026.0243———
DebateBackbone=Qwen-72B, Number of LLMs=82026.0242.9———
DyLANBackbone=Qwen-72B, Number of LLMs=322026.0242.9———
MacNetModel=Qwen-14B, Number of LLMs=642026.0242.7———
GPTSwarmBackbone=Qwen-72B, Number of LLMs=322026.0242.7———
M2CLBackbone=Qwen-14B, Number of LLMs=82026.0242———
M2CLModel=Qwen-7B, Number of LLMs=642026.0242———
MacNetBase Model=Qwen-72B, Number of LLMs=42026.0242———
GPTSwarmModel=Qwen-72B, Number of LLMs=162026.0241.3———
BoNBackbone=Qwen-72B, Number of LLMs=82026.0241.2———
DyLANModel=Qwen-72B, Number of LLMs=162026.0241.1———
MacNetBackbone=Llama-70B, Number of LLMs=82026.0240.7———
DebateBase Model=Qwen-72B, Number of LLMs=42026.0240.7———
DyLANBackbone=Qwen-72B, Number of LLMs=82026.0240.4———
GPTSwarmBackbone=Qwen-72B, Number of LLMs=82026.0240.3———
M2CLModel=Llama-14B, Number of LLMs=642026.0240.3———
MacNetBackbone=Qwen-14B, Number of LLMs=322026.0239.8———
M2CLBackbone=Qwen-7B, Number of LLMs=322026.0239.7———
DeepSeek-R1-671BCategory=Open-sourced Agent, Evaluation Environment=Unified2026.0239.20.5574.011,468
GPTSwarmBase Model=Qwen-72B, Number of LLMs=42026.0239———
BoNBase Model=Qwen-72B, Number of LLMs=42026.0238.6———
M2CLBackbone=Llama-14B, Number of LLMs=322026.0238.5———
DyLANBase Model=Qwen-72B, Number of LLMs=42026.0238.2———
M2CLBase Model=Qwen-14B, Number of LLMs=42026.0237.2———
WebExplorerCategory=Open-sourced Agent2026.0237.20.52112.883,560
M2CLModel=Qwen-7B, Number of LLMs=162026.0236.5———
MacNetBase Model=Llama-70B, Number of LLMs=42026.0236.5———
M2CLModel=Llama-14B, Number of LLMs=162026.0236.2———
MacNetModel=Qwen-14B, Number of LLMs=162026.0235.5———
BoNModel=Llama-70B, Number of LLMs=642026.0233.9———
M2CLBackbone=Llama-14B, Number of LLMs=82026.0233.6———
M2CLBackbone=Qwen-7B, Number of LLMs=82026.0233.6———
BoNModel=Llama-70B, Number of LLMs=162026.0233.2———
DebateModel=Llama-70B, Number of LLMs=162026.0233———
BoNBackbone=Llama-70B, Number of LLMs=82026.0232.9———