Benchmark
Toolathlon
Scores are percentages.
All reasoning benchmarksScores from LLM Stats data.
- 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
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
| # | Model | Score |
|---|---|---|
| 1 | GLM 5.3 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 78.4% |
| 2 | Muse Spark 1.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 75.6% |
| 3 | DeepSeek V4 Pro 0813· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 74.1% |
| 4 | Hy4 preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 74.1% |
| 5 | Qwen 3.8 Flash Next· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 73.5% |
| 6 | Qwen3.8 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 73.5% |
| 7 | Kimi K3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 73.2% |
| 8 | GLM 5.3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 73% |
| 9 | Qwen3.8 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 72.5% |
| 10 | DeepSeek V4 Flash 0731· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 70.3% |
| 11 | Claude Opus 4.8· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 59.9% |
| 12 | GPT-5.6 Sol· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 58% |
| 13 | Gemini 3.5 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 56.5% |
| 14 | GPT 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 55.6% |
| 15 | GPT 5.4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 54.6% |
| 16 | Inkling Small· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 54.4% |
| 17 | Claude Sonnet 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 54.3% |
| 18 | GPT-5.6 Luna· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 53.4% |
| 19 | GPT-5.6 Terra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 53.1% |
| 20 | Doubao Seed 2.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 50.6% |
| 21 | Kimi K2.6· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 50% |
| 22 | Laguna S 2.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 49.7% |
| 23 | Gemini 3 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 49.4% |
| 24 | Doubao Seed 2.1 Turbo· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 49.1% |
| 25 | Hy3 (Deep Infra)· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 48.5% |
| 26 | GLM 5.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 48.2% |
| 27 | GPT 5.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 46.3% |
| 28 | MiniMax M2.7· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 46.3% |
| 29 | DeepSeek V4 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 43.5% |
| 30 | MiniMax M2.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 43.5% |
| 31 | GPT-5.4 mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 42.9% |
| 32 | GLM 5.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 40.7% |
| 33 | Qwen3.6 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 39.8% |
| 34 | Qwen3.5 397B A17B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 38.3% |
| 35 | GPT 5.4 Nano· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 35.5% |
| 36 | DeepSeek Reasoner· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 35.2% |
| 37 | DeepSeek V3.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 35.2% |
| 38 | DeepSeek V3.2 Speciale· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 35.2% |
| 39 | Qwen3.6 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 26.9% |
| 40 | Qwen3 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 18.8% |
Data credits: Data by LLM Stats