Baichuan2-13B-Chat
Baichuan2-13B-Chat places in the top three on MT-Bench-101.
Released September 6th, 2023 Compare with others
12
Benchmarks with a score
0
Ranked first, out of five or more models
1
In the top three
Unknown lab Sep 2023
Baichuan2-13B-Chat
No Epoch Capabilities Index score yet
- MMLU-CF 48.3% #32 /37
- MathBench 20.9% #19 /21
- CFBench 32.2% #11 /19
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MT-Bench-101 | 7.00 | #2 of 6 | Official leaderboard | |
| BIG-Bench Hard | 47.2% | #25 of 45 | Claim in Yi: Open Foundation Models by 01.AI, via Epoch AI | |
| GAOKAO-Bench | 43.9% | #4 of 7 | Official leaderboard | |
| CFBench | 32.2% | #11 of 19 | Official leaderboard | |
| MMLU | 55.1% | #52 of 85 | Claim in Yi: Open Foundation Models by 01.AI, via Epoch AI | |
| MMLU-CF | 48.3% | #32 of 37 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GSM8K | 45.7% | #40 of 70 | Claim in Yi: Open Foundation Models by 01.AI, via Epoch AI | |
| SuperCLUE-Math6 | 36.8 | #3 of 4 | Official leaderboard | |
| MathBench | 20.9% | #19 of 21 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CFLUE Application | 39.6 | #2 of 4 | Official leaderboard | |
| FinEval | 47.8% | #6 of 7 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SuperCLUE-Safety | 78.8 | #5 of 7 | Official leaderboard |