Skip to content

Benchmark

Artificial Analysis Coding Agent Index

Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are index points. Higher is better.

Models measured
10
Scores recorded
12
Sources
1
IQ weight
No weight published

Score distribution

69.1
Mean
72.5
Median
9.7
Std dev
61.2
10th percentile
77.4
90th percentile
42.7
Min
42.780
The band covers the middle 80% of scores. The line marks the median.

Results

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

ModelScore
Claude Fable 5Artificial Analysis Coding Agent Index v1.1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.77.2
Claude Fable 5Artificial Analysis Coding Agent Index v1.4· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.67.2
Claude Opus 4.8Artificial Analysis Coding Agent Index v1.1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.72.5
Claude Opus 5Artificial Analysis Coding Agent Index v1.4· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.68.1
Gemini 3.1 Pro PreviewArtificial Analysis Coding Agent Index v1.1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.42.7
Gemini 3.8 FlashArtificial Analysis Coding Agent Index v1.4· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.61.2
GPT 5.5Artificial Analysis Coding Agent Index v1.1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.76.4
GPT-5.6 LunaArtificial Analysis Coding Agent Index v1.1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.74.6
GPT-5.6 SolArtificial Analysis Coding Agent Index v1.1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.80
GPT-5.6 SolArtificial Analysis Coding Agent Index v1.4· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.65.1
GPT-5.6 TerraArtificial Analysis Coding Agent Index v1.1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.77.4
GPT-6 AstraArtificial Analysis Coding Agent Index v1.4· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.67

Data credits: 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.