Benchmark
MedChemBench (Internal)
Science benchmarks measure how well models answer science questions. Scores are percentages.
All science benchmarksScores from LLM Stats data.
- Models measured
- 4
- Scores recorded
- 4
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 35.3%
- Mean
- 35%
- Median
- 8%
- Std dev
- 27.5%
- 10th percentile
- 48.3%
- 90th percentile
- 27.5%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Sol· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 48.3% |
| 2 | GPT-5.6 Terra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 35% |
| 3 | GPT-5.6 Luna· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 30.4% |
| 4 | GPT-rosalind-research· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 27.5% |
Data credits: Data by LLM Stats