Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Scientific research reasoning on FrontierScience Research
Loading...
33.4
Accuracy
Seed-2.0-Pro
2.096
10.223
18.35
26.477
May 15, 2026
Accuracy
Updated 16d ago
Evaluation Results
Method
Method
Links
Accuracy
Seed-2.0-Pro
Category=Proprietary A...
2026.05
33.4
GPT-5.2
Category=Proprietary A...
2026.05
25.2
Argus-35B-A3B (Parallel)
Category=Parallel Agen...
2026.05
25
Claude-4.6-Opus
Category=Proprietary A...
2026.05
23.3
Gemini-3.1-Pro
Category=Proprietary A...
2026.05
20
Argus-35B-A3B (Solo)
Category=Parallel Agen...
2026.05
13.2
Qwen3.5-397B-A17B
Category=Open-Source A...
2026.05
11.7
MiroThinker-1.7
Category=Open-Source D...
2026.05
8.8
GLM-5.0
Category=Open-Source A...
2026.05
8.3
Searcher-35B-A3B
Category=Parallel Agents
2026.05
5.4
Qwen3.5-35B-A3B
Category=Open-Source A...
2026.05
3.3
Feedback
Search any
task
Search any
task