Skip to content

Benchmark

BIG-Bench Hard

Scores are percentages.

Models measured
12
Scores recorded
12
Sources
1
IQ weight
2.16

Score distribution

78.8%
Mean
85.5%
Median
13.8%
Std dev
70.4%
10th percentile
89.2%
90th percentile
39.1%
Min
39.1%93.1%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.16 for chat models, measured over 12 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Claude 3.5 Sonnet· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim93.1%
2Gemini 1.5 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim89.2%
3Gemma 3 27B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim87.6%
4Claude 3 Opus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim86.8%
5Gemma 3 12B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim85.7%
6Gemini 1.5 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim85.5%
7Claude 3 Sonnet· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim82.9%
8phi-3.5-moe-instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim79.1%
9Claude 3 Haiku· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73.7%
10Gemma 3 4B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim72.2%
11Phi 4 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim70.4%
12Gemma 3 1b it· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim39.1%

Data credits: Data by LLM Stats