Skip to content

Benchmark

Terminal-Bench Hard

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

Models measured
5
Scores recorded
5
Sources
2
IQ weight
No weight published

Score distribution

27.3%
Mean
30.5%
Median
7.5%
Std dev
14%
10th percentile
36%
90th percentile
14%
Min
14%36%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Gemma 4 31B ITGemma 4 Technical Report · Table 5 · thinking mode unless noted· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.36%
2North Mini Code 1.0· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim31.1%
3MiMo V2 FlashMiMo-V2-Flash final evaluation · harness unspecified· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.30.5%
4Command A Plus 05 2026· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim25%
5Gemma 4 26B A4BGemma 4 Technical Report · Table 5 · thinking mode unless noted· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.14%

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.