Skip to content

Benchmark

Terminal-Bench

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

Models measured
61
Scores recorded
67
Sources
3
IQ weight
1.73

Score distribution

41.8%
Mean
39.5%
Median
18.5%
Std dev
21.8%
10th percentile
66.5%
90th percentile
3.4%
Min
3.4%84.7%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.73 for chat models, measured over 61 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
51MiMo V2 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim30.5%
52GLM 4.5 Air· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim30%
53Kimi K2 Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
30%
54Grok 4· Epoch AI Benchmarking Hub data27.2%
55Qwen3 Coder· Epoch AI Benchmarking Hub data27.2%
56Grok Code Fast 1· Epoch AI Benchmarking Hub data25.8%
57Nemotron 3 Super 120B A12B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim25.8%
58Qwen3.6 35B A3B· Epoch AI Benchmarking Hub data24.6%
59GPT-5 nano· Epoch AI Benchmarking Hub data21.8%
60GPT OSS 120B· Epoch AI Benchmarking Hub data18.7%
61gemini-2.5-flash-preview-09-2025· Epoch AI Benchmarking Hub data17.1%
62Gemini 2.5 Flash· Epoch AI Benchmarking Hub data17.1%
63GPT-5 nanomedium· Epoch AI Benchmarking Hub data11.5%
64Qwen3.5 9B· Epoch AI Benchmarking Hub data9.2%
65Nemotron 3 Nano 30B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim8.5%
66DeepSeek R1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim5.7%
67GPT OSS 20b· Epoch AI Benchmarking Hub data3.4%

Showing 51–67 of 67 results.

Data credits: Data by LLM Stats · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · Hugging Face official benchmark leaderboards; licence varies by benchmark