Skip to content

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
0%93.8%
The band covers the middle 80% of scores. The line marks the median.

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

#ModelScore
1Claude Fable 5.2· Vals AI93.8%
2Claude Sonnet 5.5· Vals AI92.4%
3Gemini 4 Argon· Vals AI91.9%
4Claude Haiku 5.5· Vals AI90.4%
5Claude Fable 5· Vals AI90.4%
6Claude Opus 5.5· Vals AI90.3%
7Claude Fable 5.1· Vals AI90.3%
8GPT-6.2 Astra· Vals AI89.9%
9GPT-6 Astra· Vals AI89.6%
10Gemini 4 Carbon· Vals AI89.1%
11GPT-6.1 Sol· Vals AI88.9%
12Claude Opus 5· Vals AI88.4%
13GPT-6 Sol· Vals AI87.8%
14Gemini 4 Hydrogen· Vals AI87.8%
15DeepSeek V4.1 Flash 1017· Vals AI87.7%
16GPT-6.2 Sol· Vals AI87.6%
17Qwen4 Max· Vals AI86.7%
18Grok 4.7· Vals AI86.2%
19Muse Wonder Full· Vals AI86%
20MiMo V2.6 Pro· Vals AI85.2%
21Kimi K3· Vals AI85%
22Kimi K3.1 Pro· Vals AI84.9%
23DeepSeek V4.1 Flash· Vals AI84.7%
24GPT-6.1 Terra· Vals AI84%
25Ember-1· Vals AI83.9%
26Muse Ember· Vals AI83.7%
27Muse Wonder· Vals AI83.1%
28Muse Spark 1.3· Vals AI82.9%
29Claude Opus 4.8· Vals AI82.7%
30DeepSeek V4 Pro 0813· Vals AI82.3%
31GPT-6 Luna· Vals AI81.6%
32Inkling 2 Small· Vals AI81.5%
33Claude Sonnet 5· Vals AI81.3%
34Hy 4· Vals AI81%
35GPT-5.6 Sol· Vals AI80.5%
36Muse Spark 1.2· Vals AI79.1%
37MiMo V2.6 Flash· Vals AI79%
38Gemini 3.8 Flash· Vals AI78.7%
39Mistral Large 4· Vals AI78.4%
40GLM 5.3· Vals AI78.1%
41Hy4 preview· Vals AI77.5%
42GPT-5.6 Luna· Vals AI77.1%
43Grok 4.6· Vals AI76.2%
44Muse Spark Open· Vals AI76.2%
45Hy4 Flash· Vals AI74.8%
46DeepSeek V4 Flash 0731· Vals AI74.7%
47GPT-5.6 Terra· Vals AI74.6%
48MiniMax M3.1 Flash· Vals AI73.9%
49Muse Spark 1.1· Vals AI72.2%
50Claude Opus 4.7· Vals AI71%

Showing 1–50 of 119 results.