AI BENCHY

Aibenchy

AI Benchmark Leaderboard

Language:

Benchmarks generated from Aibenchy test suites at 2026-02-16T00:55:25.158Z

Models Evaluated: 10

Total Runs: 40

Total Wrong: 21

Open model comparison selector

Rank

Model Name

Company ⓘ

Avg Score ⓘ

Value Score ⓘ

Tests Correct ⓘ

Z.ai: GLM 5 Reasoning (medium)

—

Z.ai

10.00

625.72

4/4

StepFun: Step 3.5 Flash No Reasoning Free Available

—

StepFun

8.00

0.00

3/4

Z.ai: GLM 5 No Reasoning

—

Z.ai

7.75

628.03

3/4

MiniMax: MiniMax M2.5 No Reasoning

—

MiniMax

7.75

545.23

3/4

Z.ai: GLM 4.7 Flash No Reasoning

—

Z.ai

5.50

6,306.47

2/4

Qwen: Qwen3 Coder Next Reasoning (medium)

—

Qwen

3.25

88,219.33

1/4

Qwen: Qwen3 Coder Next No Reasoning

—

Qwen

3.25

83,461.74

1/4

Z.ai: GLM 4.7 Flash Reasoning (medium)

—

Z.ai

3.25

442.97

1/4

MiniMax: MiniMax M2.5 Reasoning (medium)

—

MiniMax

3.25

143.91

1/4

#10

OpenAI: GPT-4o-mini No Reasoning

—

OpenAI

1.00

16,920.47

0/4

Quick Compare

Choose the first model, then click a second model to open a side-by-side page.

Compare Z.ai: GLM 5 against...

Compare StepFun: Step 3.5 Flash against...

Compare Z.ai: GLM 5 against...

Compare MiniMax: MiniMax M2.5 against...

Compare Z.ai: GLM 4.7 Flash against...

Compare Qwen: Qwen3 Coder Next against...

Compare Z.ai: GLM 4.7 Flash against...

Compare MiniMax: MiniMax M2.5 against...

Compare OpenAI: GPT-4o-mini against...