Skip to content

Benchmark

Toolathlon

Scores are percentages.

Models measured
40
Scores recorded
40
Sources
1
IQ weight
2.29

Score distribution

52.8%
Mean
50.6%
Median
14.7%
Std dev
35.2%
10th percentile
73.5%
90th percentile
18.8%
Min
18.8%78.4%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.29 for chat models, measured over 40 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1GLM 5.3 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim78.4%
2Muse Spark 1.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim75.6%
3DeepSeek V4 Pro 0813· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim74.1%
4Hy4 preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim74.1%
5Qwen 3.8 Flash Next· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73.5%
6Qwen3.8 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73.5%
7Kimi K3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73.2%
8GLM 5.3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73%
9Qwen3.8 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim72.5%
10DeepSeek V4 Flash 0731· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim70.3%
11Claude Opus 4.8· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim59.9%
12GPT-5.6 Sol· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim58%
13Gemini 3.5 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim56.5%
14GPT 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim55.6%
15GPT 5.4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim54.6%
16Inkling Small· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim54.4%
17Claude Sonnet 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim54.3%
18GPT-5.6 Luna· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim53.4%
19GPT-5.6 Terra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim53.1%
20Doubao Seed 2.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim50.6%
21Kimi K2.6· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim50%
22Laguna S 2.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim49.7%
23Gemini 3 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim49.4%
24Doubao Seed 2.1 Turbo· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim49.1%
25Hy3 (Deep Infra)· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim48.5%
26GLM 5.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim48.2%
27GPT 5.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim46.3%
28MiniMax M2.7· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim46.3%
29DeepSeek V4 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim43.5%
30MiniMax M2.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim43.5%
31GPT-5.4 mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim42.9%
32GLM 5.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim40.7%
33Qwen3.6 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim39.8%
34Qwen3.5 397B A17B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim38.3%
35GPT 5.4 Nano· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim35.5%
36DeepSeek Reasoner· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim35.2%
37DeepSeek V3.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim35.2%
38DeepSeek V3.2 Speciale· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim35.2%
39Qwen3.6 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim26.9%
40Qwen3 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim18.8%

Data credits: Data by LLM Stats