Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
General AI Assistant Task on GAIA-127 (Accuracy)
Loading...
23.6
Accuracy
OpenThinkerAgent-32B
4.256
9.278
14.3
19.322
Jun 23, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
OpenThinkerAgent-32B
Train Size=100K, Metho...
2026.06
23.6
Nemotron-Terminal-32B
Train Size=264K, Metho...
2026.06
22.3
DeepSWE-Preview
Train Size=4.5K, Metho...
2026.06
16.5
Nemotron-Terminal-8B
Train Size=264K, Train...
2026.06
14.4
SWE-Lego-Qwen3-32B
Train Size=18K, Method...
2026.06
12.9
SA-SWE-32B
Train Size=4.5K, Metho...
2026.06
11.5
Qwen3-32B
Train Size=N/A, Method...
2026.06
9.7
SERA-32B
Train Size=25K, Method...
2026.06
8.7
OT-Agent-ColdSFT+RL-8B
Base Model=OpenThinker...
2026.06
6.8
OT-Agent-SFT-8B (100K)
Base Model=OpenThinker...
2026.06
6.6
SWE-Lego-Qwen3-8B
Base Model=Qwen3-8B, T...
2026.06
6
OT-Agent-SFT-8B (10K)
Base Model=OpenThinker...
2026.06
5.5
Endless Terminals
Base Model=Qwen3-8B, T...
2026.06
5.2
Qwen3-8B
Base Model=N/A, Train...
2026.06
5
Feedback
Search any
task
Search any
task