Skip to content

Benchmark

AGIEval

Math benchmarks measure how well models solve maths problems. Scores are percentages. Higher is better.

Models and systems measured
4
Scores recorded
4
Sources
2
IQ weight
No weight published

Score distribution

55%
Mean
55.1%
Median
19.5%
Std dev
28.5%
10th percentile
83.4%
90th percentile
28.5%
Min
28.5%83.4%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#Model or systemScore
1Gemma 2 27B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim55.1%
2Gemma 2 9B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim52.8%
3ERNIE 4.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim28.5%

Not ranked

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

Model or systemScore
DeepSeek V4.1 Flash BaseEM · 3–5-shot· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.83.4%

Data credits: Data by LLM Stats · BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.