Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reasoning on AIME 2025 (Score, Tool-integrated Score)
Loading...
92.4
AIME Score
Nemotron-Cascade-2-30B-A3B
42.896
55.748
68.6
81.452
Jul 6, 2026
AIME Score
Tool-integrated AIME Score
Updated 18d ago
Evaluation Results
Method
Method
Links
AIME Score
Tool-integrated AIME Score
Nemotron-Cascade-2-30B-A3B
Context Length=1M, Eva...
2026.07
92.4
-
Qwen3.5 35B-A3B
Context Length=256K, E...
2026.07
91.9
-
Audex 30B-A3B
Context Length=1M, Eva...
2026.07
91.2
-
Qwen3 30B-A3B Thinking-2507
Context Length=256K, E...
2026.07
85
-
Qwen3-Omni 30B-A3B Thinking
Context Length=64K, Ev...
2026.07
73.7
-
Step-Audio R1.1 33B
Context Length=64K, Ev...
2026.07
44.8
-
Nemotron-Cascade-2-30B-A3B
Context Length=1M, Eva...
2026.07
-
98.6
Audex 30B-A3B
Context Length=1M, Eva...
2026.07
-
98.3
Feedback
Search any
task
Search any
task