Benchmark
Apex Shortlist
Scores are percentages. Higher is better.
Benchmark sourceScores from BenchBoard docs.
- Models measured
- 2
- Scores recorded
- 5
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 65.4%
- Mean
- 74.9%
- Median
- 28.5%
- Std dev
- 9.3%
- 10th percentile
- 85.7%
- 90th percentile
- 9.3%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V4 FlashDeepSeek V4 official model card · Think Max· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 85.7% |
| 2 | Nemotron 3 UltraNeMo Evaluator SDK · with tools· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 84.8% |
| 3 | Nemotron 3 UltraNeMo Evaluator SDK · no tools· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 74.9% |
| 4 | DeepSeek V4 FlashDeepSeek V4 official model card · Think High· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 72.1% |
| 5 | DeepSeek V4 FlashDeepSeek V4 official model card · Non-Think· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 9.3% |