CritPt (no tools)
CritPt - critical point identification benchmark, no tools variant.
Category
STEM & Reasoning
Max Score
100.0
Score Type
percent
Active
Yes
Model Scores
Scores for CritPt (no tools)
| Model | Score | Date | Verified |
|---|---|---|---|
| NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 |
7.89%
|
04.06.2026 | Verified |
| MiniMax-M2.7 |
0.60
|
04.06.2026 | Unverified |
| GLM-5.1 |
9.78%
|
04.06.2026 | Unverified |
| Kimi K2.6 |
26.81%
|
04.06.2026 | Unverified |
| Qwen3.5-397B-A17B |
5.68%
|
04.06.2026 | Unverified |
| DeepSeek-V4-Pro |
42.27%
|
04.06.2026 | Unverified |
| DeepSeek-V4-Flash |
31.55%
|
04.06.2026 | Unverified |
| Kimi K3 |
71.92%
|
18.08.2026 | Verified |
| GLM-5.2 |
64.04%
|
17.06.2026 | Verified |
| Gemini 3.1 Pro |
53.94%
|
17.06.2026 | Unverified |
| GPT-5.5 |
83.60%
|
17.06.2026 | Unverified |
| Claude Opus 4.8 |
64.04%
|
17.06.2026 | Unverified |
| Qwen3.7-Max |
40.38%
|
17.06.2026 | Unverified |
| MiniMax-M3 |
9.78%
|
17.06.2026 | Unverified |
| Hy3 |
13.56%
|
28.08.2026 | Verified |
| Hy4 preview |
51.42%
|
28.08.2026 | Verified |
| DeepSeek V4 Pro |
54.89%
|
28.08.2026 | Verified |
| Qwen3.8-2.4T-A95B |
61.20%
|
28.08.2026 | Verified |
| GLM-5.3 |
58.36%
|
28.08.2026 | Verified |
| GPT-5.6 Sol |
100.00%
|
28.08.2026 | Verified |
| Claude Opus 5 |
89.91%
|
28.08.2026 | Verified |