Skip to main content
Evaluation sources/SciCode
ObservingCoding

SciCode

SciCode · Public model evaluation results from SciCode.

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

Fugu60.160.12026-08-05
Fugu Ultra58.758.72026-08-05
Qwen3.7 Max53.553.52026-05-19
Gemini 2.5 Pro42.842.82026-06-02
Step 3.5 Flash40.440.42026-06-02
Step 3.7 Flash4040.02026-06-15
Gemini 2.5 Flash39.439.42026-06-02
Step 3.5 Flash 260338.538.52026-06-02
GLM-4.638.438.42026-05-22
Qwen3 Max38.338.32026-05-30
Mistral Small 43838.02026-06-01
Mistral Large 336.236.22026-06-04
DeepSeek-R135.735.72026-03-11
GLM-4.534.834.82026-03-11
GLM-4.5-Air30.630.62026-05-30
Qwen3-Coder 30B-A3B Instruct27.827.82026-06-02
Llama-3.3-70B-Instruct2626.02026-03-11
Sonar22.922.92026-03-11
Sonar Pro22.622.62026-03-11
GLM-4.5V22.122.12026-04-29
Gemini 2.5 Flash-Lite19.319.32026-03-11

Frequently asked questions