Skip to content

Benchmark

Terminal-Bench 2.0

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

Models measured
60
Scores recorded
60
Sources
3
IQ weight
1.98

Score distribution

49.4%
Mean
49.4%
Median
14.7%
Std dev
30%
10th percentile
69%
90th percentile
22.5%
Min
22.5%82.7%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.98 for chat models, measured over 60 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1GPT 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim82.7%
2Claude Sonnet 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim80.4%
3GPT-5.3 Codex· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim77.3%
4Gemini 3.5 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim76.2%
5GPT 5.4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim75.1%
6Claude Opus 4.8· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim74.6%
7Qwen3.7 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim70.3%
8Qwen3.7 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim69.7%
9Claude Opus 4.7· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim69.4%
10GLM 5.1· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
69%
11Gemini 3.1 Pro Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim68.5%
12MiMo V2.5 Pro· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
68.4%
13DeepSeek V4 Pro· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim67.9%
14Kimi K2.6· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
66.7%
15MiMo V2.5· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
65.8%
16Claude Opus 4.6· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim65.4%
17GPT-5.2 Codex· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim64%
18Qwen3.6 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim61.6%
19GPT-5.4 mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim60%
20Claude Opus 4.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim59.3%
21Qwen3.6 27B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
59.3%
22Claude Sonnet 4.6· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim59.1%
23Muse Spark· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim59%
24MiMo V2 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim57.1%
25MiniMax M2.7· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
57%
26DeepSeek V4 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
56.9%
27GLM 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 3 sources
56.2%
28Hy3 (Deep Infra)· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim54.4%
29Gemini 3 Pro Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim54.2%
30GPT-5.1 Codex· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim52.8%
31Qwen3.5 397B A17B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 3 sources
52.5%
32Qwen3.6 35B A3B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
51.5%
33Step 3.5 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 3 sources
51%
34Kimi K2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 3 sources
50.8%
35Qwen3.5 122B-A10B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 3 sources
49.4%
36Gemini 3 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim47.6%
37DeepSeek Reasoner· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim46.4%
38DeepSeek V3.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
46.4%
39DeepSeek V3.2 Speciale· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim46.4%
40GPT 5.4 Nano· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim46.3%
41Mai Thinking 1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim46%
42Laguna M.1· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim45.8%
43Doubao Seed 1.8· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim45.2%
44Qwen3.5 27B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 3 sources
41.6%
45GLM 4.7· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 3 sources
41%
46Qwen3.5 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
40.5%
47ling-2.6-1t· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim40.5%
48MiMo V2 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
38.5%
49Laguna XS 2.1· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
37.5%
50Qwen3 Coder· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 3 sources
37.5%

Showing 1–50 of 60 results.

Data credits: Data by LLM Stats · OpenEvals/leaderboard-data, MIT (licence) · Hugging Face official benchmark leaderboards; licence varies by benchmark