Benchmark
PutnamBench coq-wsolution solved
Math benchmarks measure how well models solve maths problems. Higher scores are better.
- Models measured
- 1
- Scores recorded
- 2
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 1
- Mean
- 1
- Median
- 0
- Std dev
- 1
- 10th percentile
- 1
- 90th percentile
- 1
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | GPT 4oCOPRA (GPT-4o), coq-wsolution, pass@1, pass@1 w/ T=0.0; 1988 B1.· PutnamBench | 1 |
| 2 | GPT 4oGPT-4o, coq-wsolution, pass@10, pass@10 w/ T=0.7; 1988 B1.· PutnamBench | 1 |
Data credits: Trishul Lab, PutnamBench public submitted results. Model identities and scaffold budgets preserved; result licence unstated.