GLM-4-9B-Chat
GLM-4-9B-Chat places in the top three on 2 benchmarks.
14
Benchmarks with a score
0
Ranked first, out of five or more models
2
In the top three
Z.ai Jun 2024
GLM-4-9B-Chat
Open weights Small
No Epoch Capabilities Index score yet
- MMLU-CF 58.6% #20 /37
- MathBench 47.7% #12 /21
- CFBench 59.6% #7 /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 | |
|---|---|---|---|---|
| Vectara Hallucination Leaderboard (HHEM) | 1.30% | #8 of 148 | Official leaderboard | |
| CFBench | 59.6% | #7 of 19 | Official leaderboard | |
| WildBench | 41.2 | #25 of 47 | Official leaderboard | |
| MMLU-CF | 58.6% | #20 of 37 | Official leaderboard | |
| MMLU-Pro | 48% | #137 of 212 | Official leaderboard | |
| FaithJudge | 25.4% | #25 of 37 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MathBench | 47.7% | #12 of 21 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OdysseyArena Energy Dispatch | 0% | #2 of 8 | Official leaderboard | |
| SuperCLUE-Agent | 69.6 | #3 of 7 | Official leaderboard | |
| Berkeley Function Calling Leaderboard (BFCL) | 39.1% | #62 of 67 | Official leaderboard | |
| OdysseyArena AI Trading | -0.18% | #8 of 8 | Official leaderboard | |
| OdysseyArena Repo System | 0% | #8 of 8 | Official leaderboard | |
| OdysseyArena Turn on Lights | 0% | #8 of 8 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| FinEval | 58.4% | #4 of 7 | Official leaderboard |