Benchmark
Agents' Last Exam
Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages. Higher is better.
- Models measured
- 32
- Scores recorded
- 32
- Sources
- 2
- IQ weight
- 0.00
Score distribution
- 38.8%
- Mean
- 35.4%
- Median
- 14.8%
- Std dev
- 25.2%
- 10th percentile
- 56.4%
- 90th percentile
- 12.4%
- Min
This benchmark has a weight of 0.00 for chat models, measured over 32 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 | GPT-6.2 Astra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 78.3% |
| 2 | GPT-6.2 Sol· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 73% |
| 3 | GPT-6.1 Terra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 60% |
| 4 | GPT-6 Astra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 59.3% |
| 5 | GPT-6 Sol· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 56.4% |
| 6 | GPT-5.6 Sol· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 52.7% |
| 7 | Qwen3.8 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 52.4% |
| 8 | Qwen 3.8 Flash Next· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 51.2% |
| 9 | Qwen3.8 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 51.2% |
| 10 | GPT-6 Luna· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 50.9% |
| 11 | GPT-5.6 Terra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 50.4% |
| 12 | GPT-5.6 Luna· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 50.3% |
| 13 | Kimi K3.1 Pro· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 43.2% |
| 14 | Qwen 3.8 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 42.9% |
| 15 | Doubao Seed 2.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 41.4% |
| 16 | Gemini 4 Argon· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 39.5% |
| 17 | DeepSeek V4.1 Flash 1017· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 35.4% |
| 18 | DeepSeek V4.1 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 31.8% |
| 19 | MiMo V2.6 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 31.6% |
| 20 | MiMo V2.6 Pro RL· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 31.6% |
| 21 | MiniMax M3.1 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 29.6% |
| 22 | ERNIE 5.5 Flash Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 29% |
| 23 | GLM 5.3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 28.5% |
| 24 | Kimi K3· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 28.3% |
| 25 | MiMo V2.6 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 27.6% |
| 26 | DeepSeek V4 Flash Vision Exp· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 27.3% |
| 27 | Gemini 3.7 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 26.3% |
| 28 | GLM 5.3 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 26.3% |
| 29 | DeepSeek V4 Pro 0813· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 25.7% |
| 30 | DeepSeek V4 Flash 0731· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 25.2% |
| 31 | Hy4 preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 22.8% |
| 32 | DeepSeek V4 Pro· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 12.4% |
Data credits: Data by LLM Stats · Hugging Face official benchmark leaderboards; licence varies by benchmark