CritPtBrowse 284 families
CritPt
Can the model reason accurately about difficult scientific material?
Version / measure
- Domain
- Science
- Ranked models
- 8
- Reported values
- 8
- Reports
- 1 · lab
- Direction
- Higher is better
- Status
- Version not specified
Rankings
Best reported score per model across effort settings
| # | Model | Best setting | Score |
|---|---|---|---|
| 1 | GPT-5.5OpenAI | reportedcost n/a1 value · Jun 16 · source | 27.1% |
| 2 | Claude Opus 4.8Anthropic | reportedcost n/a1 value · Jun 16 · source | 20.9% |
| 3 | GLM-5.2Z.aiOW | maxcost n/a1 value · Jun 16 · source | 20.9% |
| 4 | Gemini 3.1 ProGoogle | reportedcost n/a1 value · Jun 16 · source | 17.7% |
| 5 | Qwen3.7-MaxQwen | reportedcost n/a1 value · Jun 16 · source | 13.4% |
| 6 | DeepSeek V4 ProDeepSeekOW | reportedcost n/a1 value · Jun 16 · source | 12.9% |
| 7 | GLM-5.1Z.aiOW | reportedcost n/a1 value · Jun 16 · source | 4.6% |
| 8 | MiniMax M3MiniMaxOW | reportedcost n/a1 value · Jun 16 · source | 3.7% |
Effort curve
Score vs. reported cost. Lines connect complete sweeps only.
No cost-linked effort sweep for this version.
Definition and comparison boundarypublic methodology
Can the model reason accurately about difficult scientific material?
Scientific knowledge and reasoning under the benchmark's published question set. Higher is better. The value is the percentage reported in this lab's table.
Harness, tools, prompts, attempt count, and benchmark version can materially change the result. Compare within one reporting context.
Method / source ↗