bellard/quickjs

Public repository of the QuickJS Javascript Engine.

10,565 c
3,034
Generated Behavioral Tests
46.8%
Best Score
Claude Opus 4.8 (xhigh)

Hover a point for details · The line marks the Pareto frontier (best score per cost) · Click a point to see model details

21 runs
# Model Score Cost Calls
1 Claude Opus 4.8 (xhigh) 46.8% $18.15 110 trace →
2 GPT-5.6 Sol (xhigh) 35.8% $6.17 43 trace →
3 Claude Opus 4.7 (xhigh) 31.0% $31.65 261 trace →
4 GLM-5.2 28.6% $49.19 351 trace →
5 GPT 5.5 (xhigh) 21.3% $7.83 76 trace →
6 Gemini 3.7 Flash 20.5% $1.25 96 trace →
7 GPT 5.5 (high) 10.9% $3.51 30 trace →
8 GPT-5.6 Sol 7.9% $1.22 14 trace →
9 Gemini 3.6 Flash 7.2% $3.67 116 trace →
10 GPT 5.5 4.0% $1.67 26 trace →
11 Claude Opus 4.6 3.6% $16.39 248 trace →
12 GPT 5.4 1.2% $0.21 13 trace →
13 Claude Opus 4.7 1.2% $0.52 18 trace →
14 Gemini 3.1 Pro 1.0% $1.30 119 trace →
15 Claude Sonnet 4.6 0.0% $82.98 995 trace →
16 Claude Haiku 4.5 0.0% $0.55 124 trace →
17 Claude Opus 5 (xhigh) 0.0% $1.59 25 trace →
18 Gemini 3.5 Flash 0.0% $3.24 160 trace →
19 Gemini 3 Flash 0.0% $0.44 96 trace →
20 GPT 5.4 mini 0.0% $0.01 8 trace →
21 GPT 5 mini 0.0% $0.01 10 trace →

Click a row to replay how that model rebuilt this program, or the model name to open its full run