Skip to main content
Evaluation sources/Vibe Code Bench v1.1
ObservingCoding

Vibe Code Bench v1.1

Vals AI · Public model evaluation results from Vibe Code Bench v1.1.

Official evaluation
Source description

This source measures concrete delivery performance in Coding; raw scores are shown separately from the normalized capability score.

Limitation: Different versions, reasoning settings, and test sets may change scores; read them with the data date.

How it is used

Participating sources affect capability scores; reference, cross-reference, and observing sources are for comparison and verification only.

Model results from this source

Claude Sonnet 5.592.3992.42026-11-05
Gemini 4 Argon91.9191.92026-11-05
Claude Haiku 5.590.4490.42026-11-05
Claude Fable 590.3590.32026-11-05
Claude Opus 5.590.2990.32026-11-05
Claude Fable 5.190.2690.32026-11-05
GPT-6 Astra89.5989.62026-11-05
GPT-6.1 Sol88.9388.92026-11-05
Claude Opus 588.488.42026-11-05
GPT-6 Sol87.8287.82026-11-05
DeepSeek V4.1 Flash 101787.7387.72026-11-05
Grok 4.786.1786.22026-11-05
Muse Spark 1.385.8685.92026-11-05
MiMo V2.6 Pro85.2285.22026-11-05
Kimi K384.9785.02026-11-05
DeepSeek V4.1 Flash84.7484.72026-11-05
GPT-6.1 Terra8484.02026-11-05
Claude Opus 4.882.7282.72026-11-05
DeepSeek V4 Pro 081382.382.32026-11-05
GPT-6 Luna81.6581.72026-11-05
Mistral Large 481.5681.62026-11-05
Claude Sonnet 581.3381.32026-11-05
GPT-5.6 Sol80.580.52026-11-05
Muse Spark 1.279.179.12026-11-05
MiMo V2.6 Flash78.9679.02026-11-05
Gemini 3.8 Flash78.6578.72026-11-05
GLM 5.378.1378.12026-11-05
GPT-5.6 Luna77.0677.12026-11-05
Grok 4.676.2476.22026-11-05
DeepSeek V4 Flash 073174.7474.72026-11-05
GPT-5.6 Terra74.5974.62026-11-05
MiniMax M3.1 Flash73.9473.92026-11-05
Muse Spark 1.172.1672.22026-11-05
Claude Opus 4.77171.02026-11-05
Step 5 Preview70.470.42026-11-05
GPT-5.569.8569.82026-11-05
Grok 4.56969.02026-11-05
GPT-5.467.4267.42026-11-05
Qwen3.8 Max64.764.72026-11-05
Gemini 3.6 Flash6464.02026-11-05
GLM-5.263.9664.02026-11-05
Claude Sonnet 4.655.7755.82026-11-05
GPT-5.253.553.52026-11-05
Claude Opus 4.653.553.52026-11-05
GPT-5.4 mini47.9748.02026-11-05
Qwen3.7 Max47.6747.72026-11-05
MiniMax-M347.5747.62026-11-05
Kimi K2.7 Code47.2147.22026-11-05
Qwen3.7 Plus46.3946.42026-11-05
MiMo-V2.542.1742.22026-11-05
Kimi K2.637.8937.92026-11-05
Gemini 3.5 Flash Lite37.1637.22026-11-05
MiMo-V2.5-Pro34.1134.12026-11-05
GLM-5.131.4631.52026-11-05
GLM-5.3 Flash30.7630.82026-11-05
Qwen3.6 Plus25.5725.62026-11-05
GLM-523.3623.42026-11-05
Claude Sonnet 4.522.6222.62026-11-05
Claude Opus 4.520.6320.62026-11-05
GPT-520.0920.12026-11-05
Grok 4.319.419.42026-11-05
Inkling19.2119.22026-11-05
Inkling Small19.0519.12026-11-05
Kimi K2.517.5417.52026-11-05
Qwen3.5 Plus15.7415.72026-11-05
MiniMax-M2.514.8514.82026-11-05
GPT-5 mini14.1714.22026-11-05
Grok Build 0.113.3513.32026-11-05
Qwen3.6 27B11.9411.92026-11-05
MiniMax-M2.711.9311.92026-11-05
Claude Haiku 4.511.3911.42026-11-05
Laguna M.111.0411.02026-11-05
Laguna XS.25.215.22026-11-05
DeepSeek V3.25.115.12026-11-05
Grok 4.20 (Reasoning)4.064.12026-11-05
Qwen3 Max3.513.52026-11-05
GLM-4.63.093.12026-11-05
Ling-3.0-flash (free)2.912.92026-11-05
Gemini 2.5 Pro0.40.42026-11-05
Gemini 3.1 Flash Lite Preview00.02026-11-05

Frequently asked questions