Benchmark
Dubesor Reason
Scores are percentages.
Benchmark sourceScores from Dubesor LLM Benchmark.
- Models measured
- 218
- Scores recorded
- 261
- Sources
- 1
- IQ weight
- 1.50
Score distribution
- 44.7%
- Mean
- 42.8%
- Median
- 24.3%
- Std dev
- 11.2%
- 10th percentile
- 76.9%
- 90th percentile
- 0%
- Min
This benchmark has a weight of 1.50 for chat models, measured over 218 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 |
|---|---|---|
| 251 | Gemini 1.5 Flash-8B· Dubesor LLM Benchmark | 4.6% |
| 252 | Gemma 3 1b it· Dubesor LLM Benchmark | 4.4% |
| 253 | OpenHermes 2.5 Mistral 7B· Dubesor LLM Benchmark | 4% |
| 254 | Qwen2 7B Instruct· Dubesor LLM Benchmark | 3.2% |
| 255 | ERNIE 4.5 21B A3B· Dubesor LLM Benchmark | 2.9% |
| 256 | jamba-1.6-mini· Dubesor LLM Benchmark | 2% |
| 257 | Qwen3 1.7B· Dubesor LLM Benchmark | 1.7% |
| 258 | Ministral 8B· Dubesor LLM Benchmark | 1.6% |
| 259 | Ministral 3B· Dubesor LLM Benchmark | 0.9% |
| 260 | MythoMax L2 13b· Dubesor LLM Benchmark | 0.6% |
| 261 | LFM-7b· Dubesor LLM Benchmark | 0% |
Showing 251–261 of 261 results.