Benchmark
Vals Vibe Code Bench v1.1
Coding benchmarks compare models on programming tasks. Scores are percentages.
- Models measured
- 119
- Scores recorded
- 119
- Sources
- 1
- IQ weight
- 1.95
Score distribution
- 52.2%
- Mean
- 64%
- Median
- 31.7%
- Std dev
- 5.1%
- 10th percentile
- 87.8%
- 90th percentile
- 0%
- Min
This benchmark has a weight of 1.95 for chat models, measured over 119 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 |
|---|---|---|
| 101 | Qwen3.6 27B· Vals AI | 11.9% |
| 102 | MiniMax M2.7· Vals AI | 11.9% |
| 103 | Claude Haiku 4.5thinking· Vals AI | 11.4% |
| 104 | Laguna M.1· Vals AI | 11% |
| 105 | Nemotron 3 Ultra· Vals AI | 7.6% |
| 106 | Laguna XS.2· Vals AI | 5.2% |
| 107 | DeepSeek V3.2· Vals AI | 5.1% |
| 108 | Grok 4.20· Vals AI | 4.1% |
| 109 | NVIDIA Nemotron 3.5 Super VL 120B· Vals AI | 3.7% |
| 110 | Mercury 2.5· Vals AI | 3.7% |
| 111 | Qwen3 Max· Vals AI | 3.5% |
| 112 | GLM 4.6· Vals AI | 3.1% |
| 113 | Mistral Medium 3.5· Vals AI | 2.9% |
| 114 | Grok 4.1 Fast· Vals AI | 1.2% |
| 115 | Gemini 2.5 Pro· Vals AI | 0.4% |
| 116 | Gemini 3.1 Flash Lite· Vals AI | 0% |
| 117 | Grok 4 Fast· Vals AI | 0% |
| 118 | Mistral Small2603· Vals AI | 0% |
| 119 | Nemotron 3.5 Lightning 30B A3B· Vals AI | 0% |
Showing 101–119 of 119 results.