Skip to content

Benchmark

GDPval-AA 2.1

Agentic benchmarks measure how well models carry out tasks that take several steps.

Models measured
8
Scores recorded
8
Sources
1
IQ weight
2.28

Score distribution

1,631.4
Mean
1,831
Median
271.5
Std dev
1,319
10th percentile
1,846
90th percentile
1,072
Min
1,0721,846
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.28 for chat models, measured over 8 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 Opus 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim1,846
2Kimi K3.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim1,846
3Claude Sonnet 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim1,844
4Claude Fable 5.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim1,831
5MiMo V2.6 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim1,673
6Claude Haiku 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim1,620
7Inkling 2 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim1,319
8Solar Mini 4· LLM Stats data1,072

Data credits: Data by LLM Stats