List your company

Complex Reasoning on GAIA Text

76.4AccuracyOpenAI-GPT-5-high
48.94456.07263.270.328Apr 20, 2026

Evaluation results

MethodLinks
OpenAI-GPT-5-highContext Window=128k, Memory Mechanism=Disabled2026.0476.4
Minimax-M2Context Window=128k, Memory Mechanism=Disabled2026.0475.7
GLM-4.6Context Window=128k, Memory Mechanism=Disabled2026.0471.9
LiteResearcher-4BContext Window=128k, Memory Mechanism=Disabled2026.0471.3
Claude-4.5-SonnetContext Window=128k, Memory Mechanism=Disabled2026.0471.2
Tongyi DeepResearch 30BContext Window=128k, Memory Mechanism=Disabled2026.0470.9
Claude-4-SonnetContext Window=128k, Memory Mechanism=Disabled2026.0468.3
Mirothinker 8BContext Window=128k, Memory Mechanism=Disabled2026.0466.4
SFR-DeepResearchContext Window=128k, Memory Mechanism=Disabled2026.0466
AgentCPM-Explore-4BContext Window=128k, Memory Mechanism=Disabled2026.0463.9
DeepSeek-V3.2Context Window=128k, Memory Mechanism=Disabled2026.0463.5
DeepSeek-V3.1Context Window=128k, Memory Mechanism=Disabled2026.0463.1
Kimi-K2-0905Context Window=128k, Memory Mechanism=Disabled2026.0460.2
ASearcher QWQ v2Context Window=128k, Memory Mechanism=Disabled2026.0458.7
DeepMiner-32BContext Window=128k, Memory Mechanism=Disabled2026.0458.7
AFM-RL-32BContext Window=128k, Memory Mechanism=Disabled2026.0455.3
WebSailor 30BContext Window=128k, Memory Mechanism=Disabled2026.0453.2
WebDancer (QwQ)Context Window=128k, Memory Mechanism=Disabled2026.0451.5
WebExplorer-8BContext Window=128k, Memory Mechanism=Disabled2026.0450